Imaging for personalized medicine. Objectives. Robust Radiomics Methods. Hugo Aerts

Size: px
Start display at page:

Download "Imaging for personalized medicine. Objectives. Robust Radiomics Methods. Hugo Aerts"

Transcription

1 HARVARD MEDICAL SCHOOL Robust Radiomics Methods Hugo Aerts Director, Computational Imaging and Bioinformatics Lab (CIBL) Dana-Farber Cancer Institute, Brigham and Women s Hospital Harvard Medical School Objectives - Describe the motivation for integrating imaging with genomic and clinical data - Describe robust methodology underlying quantitative radiomic analysis - Describe biomarker quantification studies in Radiomics and Imaging-Genomics (Radiogenomics) Imaging for personalized medicine Advantages of Imaging: - Performed non-invasively - Covers the total 3D volume - Already performed in clinical practice - Multiple times during treatment for diagnosis, staging, radiation oncology planning, response assessment Disadvantages of Imaging: - Probes the cancer at the macroscopic level - Often qualitative not quantitative - Very heterogeneous acquisition protocols: - comparisons between patients difficult - comparisons same patient in time difficult - Storage of only reconstructed images (not the raw data) 1

2 Imaging Representative CT images of lung cancer Tumors are different Medical imaging can capture these phenotypic differences Integrating Imaging and Genomic Data Radiomic Data Clinical Data Genomic Data Radiomics Imaging-Genomics Radiomics Data Feature extraction Clinical Data Metabolome Proteome Transcriptome Genome Biologic Data Integrating Tissue Imaging data with the underlying Biology 2

3 Area= mm 2 Perimeter=152.4 mm Volume=2615 mm 3 Surf. area= mm 2 Surf. Area/volume=0.42 mm -1 Density, Necrosis Mean = HU SD = HU Min = -249 HU Max = 118 HU Spiculations Slope at margin =133.5±31.3 HU/mm Low density inclusions Rel. vol.= 0.21 mm 3 Number=110 Volume=4.89±8.35 mm 3 Radiomics rational - Radiographic images are typically analysed qualitatively by radiologist, often with non-standard lexicon. - At most, unidirectional measurements (RECIST) - Radiomics aims to provide a comprehensive quantification of the tumor phenotype using automated image characterisation algorithms - We hypothesize that radiomic analyses of standard of care images can improve diagnostic, prognostic and predictive power - Automation is key: automatic quantitative feature algorithms to extract quantitative data instead of qualitative data, reduce observer variation by manual annotation, and increase speed of workflow. Radiomics: Quantify the tumor phenotype Convert Images to mineable data in high throughput (radiomics) *Lambin et al.eur J Cancer 2012 PAGE 8 *Kumar et al. Magn Reson Imaging 2012 Radiomics: Workflow & Challenges Image Acquisition, Reconstruction, Standardization, Storage PAGE 9 3

4 Radiomics: Workflow & Challenges Image Acquisition, reconstruction, standardization, storage Automate, Validate, Reproducibility Automatic segmentation: 1) Automated method for high throughput of images. 2) Reducing the high intra- and inter-observer variability observed for target definition. PAGE 10 Automatic tumor delineation using 3D-Slicer Developing algorithms for fast, semi-automated, and accurate delineation Automatic tumor delineation using 3D-Slicer *Velazquez et al, Sci Rep

5 Manual 3D-Slicer Manual 3D-Slicer Area= mm 2 Perimeter=152.4 mm Volume=2615 mm 3 Surf. area= mm 2 Surf. Area/volume=0.42 mm -1 Density, Necrosis Mean = HU SD = HU Min = -249 HU Max = 118 HU Spiculations Slope at margin =133.5±31.3 HU/mm Low density inclusions Rel. vol.= 0.21 mm 3 Number=110 Volume=4.89±8.35 mm 3 3D-Slicer region growing algorithm *Velazquez et al, Sci Rep Uncertainty Region Uncertainty Region Segmentation uncertainty was significantly smaller with 3D-Slicer (Velazquez et al, Sci Rep. 2013) Radiomics features based on 3D-Slicer delineations are more stable (Parmar et al. PLOS One 2014) Radiomics: Workflow & Challenges Image Acquisition, reconstruction, standardization, storage Automate, Validate, Reproducibility Definition, Informative, Reproducibility, Robustness PAGE 15 5

6 Stats Texture Wavelet Shape LoG Radiomic Feature Set (current release ~1600 features) Texture Stats RLGL GCLM GLSZM RLGL GCLM GLSZM GLCM GLRL Texture Stats RLGL GCLM GLSZM Kurtosis: Entropy: Radiomic features can capture tumor phenotypic details HARVARD MEDICAL SCHOOL Robust Radiomics Data Analysis (Feature Selection & Machine learning) Motivation Predictive/Prognostic models having high accuracy, reliability and efficiency can be vital factors driving success of Radiomics. Need for the machine-learning models. Radiomics suffers from the curse of dimensionality. Need for the feature selection. Different feature selection and machine-learning classification methods have to be investigated. 6

7 Radiomics Features HARVARD MEDICAL SCHOOL Radiomics Dimensionality Reduction Matrix of 440 Radiomics features (422 NSCLC patients) Spearman's rank correlation coefficient Radiomics Features Feature selection: RIDER test retest Rider test retest reproducibility to select the most reproducible tumor image features extracted from CT images of 31 non-small cell lung cancer (NSCLC) patients. CT scans acquired within fifteen minutes. All primary lung cancers were segmented using Definiens 440 radiomics features were extracted from these segmented tumor regions Intraclass Correlation Coefficient (ICC) was calculated for each feature as a stability index Scan 1 Scan 2 [ Lung CT image with segmented tumor region shown with green outline] Robust Machine Learning in Radiomics *Parmar et al. submitted 7

8 Nnet DT BST BY BAG RF MARS SVM DA NN GLM PLSR Nnet DT Count Value Machine Learning in Radiomics % variance Feature Selection Methods Color Key and Histogram Value RELF FSCR GINI CHSQ JMI CIFE DISR MIM CMIM ICAP TSCR MRMR MIFS WLCX ML Classification Methods *Parmar et al. submitted Stability for feature selection and Classification *Parmar et al. submitted Machine Learning in Radiomics Classifiers FS_method size Classifiers:size Factors FS:size Classifiers:FS Residuals *Parmar et al. submitted 8

9 Radiomics Features Wavelet Imaging-Genomics across cancer types I) CT Imaging II) Feature Extrac on III) Analysis Radiomic Features Gene expression *Aerts et al. Nature Comm Tumor Intensity Tumor Shape Clinical Data Tumor Texture Wavelet Radiomics analysis on CT imaging of >1000 patients with Lung or H&N cancer Developed and validated a prognostic radiomics signature that can be applied across cancer types Imaging-Genomics analysis showed strong correlations between radiomics and genomics data z-score Patients Lung1 Dataset 422 NSCLC Patients MAASTRO Clinic Intensity Shape Texture HHH HHL HLH HLL LHH LHL LLH LLL Clusters I II III T-stage N-stage M-stage Overall Stage >1 I II IIIA IIIB IV Histology adenocarcinoma squamous cell carcinoma large cell carcinoma not otherwise speci ed (nos) NA Radiomics CT Workflow Radiomics Signature: 1 Statistics Energy 2 ShapeCompactness 3 Gray Level Nonuniformity 4 Wavelet Gray Level Nonuniformity HLH 7 datasets with a total of 1018 patients 9

10 Survival probability Survival probability Survival Probability Radiomics CT Signature Performance Lung cancer cohorts Head & neck cancer cohorts Survival time (days) Performance Model: - CI = 0.65 on the Lung2 Validation Dataset (n=225) Survival time (days) Performance Model: - CI = 0.69 on Maastro H&N dataset (n=136) - CI = 0.69 on VU H&N dataset (n=95) *Aerts et al. Nature Comm Radiomics CT Signature Performance - Signature performed significantly better compared to volume in all datasets. - Signature performance was better than TNM staging in Lung2 and H&N2, and comparable in the H&N1 dataset. - Combining the signature with TNM showed significant improvement in all datasets. Additional Validation of Prognostic Signature 542 Oropharyngeal squamous cell carcinoma (OPSCC) treated at Princess Margaret Hospital (PMH) in Toronto. a Kaplan-Meier Radiomic Signature b Kaplan-Meier Radiomics Signature * * * * * <= Median *** * > Median * ** * ** * * **** * ** ******** * * * ** * *** * ** * * ***** ** * * *** ***** ** ** * * ********* **** * * * *** ** * ** *** *** ** *** * **** * * * * ** ** ***** **** ****** ****** * * * * *********** * * ********** * *** * ** *** * * ******** * ***** *** * ** *** *** ********* * **** ** *** * * * **** * **** ** *** ** ***** * * * <= Median > Median ** * *** *********** ** * * ** *** ** * ****** **** ** ** *** * * **** * * * **** *** ** ** * * *** * ** * * * PMH: all (n=542) PMH: no CT artifacts (n=267) PMH: artifacts (n=275) MAASTRO (n=136) VUmc (n=95) Survival time (days) Survival time (days) C-index was: PMH1: (P<2.72e-9), PMH2: (P<2.7e-6) and PMH3: (P<5.35e-6) Radiomics signature could be validated in an additional large OPSCC cohort *Leijnaar et al. Acta Onco

11 GSEA of Prognostic Radiomics Signature Dataset of 89 Stage I NSCLC patients treated with surgery Radiomics-Genomics in NSCLC I) Medical Image (B) D1 D2 R+G n=262 Enrichment analysis Radiomic feature Pathway II) Segmentation Correlation to pathway activity III) 3D mask Independent validations R+G n=89 Identification of modules Radiomic feature IV) Feature extraction Pathway Association to clinical data R+G+C n=224 V) Data integration Clinical characterization of module s Independent validations R+G+C n=87 Meta-analysis *Grossmann et al. Submitted Color Key Stats Shape LoG_sigma Wavelet RLGL GLSZM GLCM Association Heatmap Radiomics-Genomics Value TRNA_AMINOACYLATION MITOCHONDRIAL_TRNA_AMINO ACYLATION CYTOSOLIC_TRNA_AMINO ACYLATION DOUBLE_STRAND_BREAK_REP AIR PROCESSIVE_SYNTHESIS_ON_THE_LA GGING_STRAND HOMOLOGOUS_RECOMBINATION_REPAIR_OF_REPLICATION_INDEPENDENT_DOUBLE_STRAND_BREAKS FANCONI_ANEMIA_PATHWAY RECRUITMENT_OF_MITOTIC_CENTROSOME_PROTEINS_AND_COMPLEXES LOSS_OF_NLP_FR OM_MITOTIC_CENTROSOMES MITOTIC_G2_G2_M_PHASES KINESINS PROTEIN_FOLDING GLUCOSE_METABOLISM GLYCOLYSIS ACETYLCHOLINE_BINDING_AND_DO WNSTREAM_EVENTS PREFOLDIN_MEDIATED_TRANSFER_OF_SUBSTRA TE_TO_CCT_TRIC FORMATION_OF_TUBULIN_FOLDING_INTERMEDIA TES_BY_CCT_TRIC SIGNALLING_TO_P38_VIA_RIT_AND_RIN PROLONGED_ERK_A CTIVATION_EVENTS SHC1_EVENTS_IN_EGFR_SIGNALING PROCESSING_OF_CAPPED_INTR ONLESS_PRE_MRNA AMINO_ACID_SYNTHESIS_AND_INTERCONVERSION_TRANSAMINA TION GLUCONEOGENESIS DESTABILIZATION_OF_MRNA_BY_KSRP MICRORNA_MIRNA_BIOGENESIS REGULATORY_RNA_PATHWAYS INFLUENZA_LIFE_CYCLE INFLUENZA_VIRAL_RNA_TRANSCRIPTION_AND_REPLICA TION 3_UTR_MEDIATED_TRANSLATIONAL_REGULATION TRANSLATION SRP_DEPENDENT_CO TRANSLATIONAL_PROTEIN_TARGETING_TO_MEMBRANE PEPTIDE_CHAIN_ELONGA TION NONSENSE_MEDIATED_DECAY_ENHANCED_BY_THE_EXON_JUNCTION_COMPLEX ACTIVATION_OF_THE_MRNA_UPON_BINDING_OF_THE_CAP_BINDING_COMPLEX_AND_EIFS_AND_SUBSEQ UENT_BINDING_TO_43S FORMATION_OF_THE_TERNAR Y_COMPLEX_AND_SUBSEQ UENTLY_THE_43S_COMPLEX METABOLISM_OF_RNA METABOLISM_OF_MRNA ABORTIVE_ELONGATION_OF_HIV1_TRANSCRIPT_IN_THE_ABSENCE_OF_T AT MITOCHONDRIAL_PR OTEIN_IMPORT BASE_EXCISION_REPAIR RESOLUTION_OF_AP_SITES_VIA_THE_MUL TIPLE_NUCLEO TIDE_PATCH_REPLACEMENT_PATHWAY POST_CHAPER ONIN_TUBULIN_FOLDING_PATHWAY RESPIRATORY_ELECTRON_TRANSPORT RESPIRATORY_ELECTRON_TRANSPORT_ATP_SYNTHESIS_BY_CHEMIOSMO TIC_COUPLING_AND_HEA T_PRODUCTION_BY_UNCOUPLING_PR OTEINS_ TCA_CYCLE_AND_RESPIRA TORY_ELECTRON_TRANSPORT RNA_POL_III_TRANSCRIPTION_TERMINA TION RNA_POL_III_CHAIN_ELONGA TION RNA_POL_III_TRANSCRIPTION_INITIA TION_FROM_TYPE_3_PROMOTER RNA_POL_III_TRANSCRIPTION_INITIA TION_FROM_TYPE_2_PROMOTER RNA_POL_III_TRANSCRIPTION PROCESSING_OF_CAPPED_INTR ON_CONTAINING_PRE_MRNA MRNA_SPLICING MRNA_PROCESSING MRNA_SPLICING_MINOR_PATHWAY TRANSCRIPTION_COUPLED_NER_TC_NER NUCLEOTIDE_EXCISION_REPAIR FORMATION_OF_THE_HIV1_EARLY_ELONGATION_COMPLEX GLOBAL_GENOMIC_NER_GG_NER TRANSPORT_OF_MATURE_TRANSCRIPT_T O_CYTOPLASM CLEAVAGE_OF_GROWING_TRANSCRIPT_IN_THE_TERMINA TION_REGION_ MRNA_3_END_PR OCESSING G2_M_CHECKPOINTS ACTIVATION_OF_ATR_IN_RESPONSE_T O_REPLICATION_STRESS ACTIVATION_OF_THE_PRE_REPLICA TIVE_COMPLEX EXTENSION_OF_TELOMERES LAGGING_STRAND_SYNTHESIS DNA_STRAND_ELONGATION DNA_REPAIR CYCLIN_A_B1_ASSOCIA TED_EVENTS_DURING_G2_M_TRANSITION G1_S_SPECIFIC_TRANSCRIPTION E2F_MEDIATED_REGULATION_OF_DNA_REPLICATION MEIOTIC_SYNAPSIS AMYLOIDS RNA_POL_I_PR OMOTER_OPENING PACKAGING_OF_TELOMERE_ENDS RNA_POL_I_TRANSCRIPTION DEPOSITION_OF_NEW_CENP A_CONTAINING_NUCLEOSOMES_AT_THE_CENTR OMERE RNA_POL_I_RNA_POL_III_AND_MIT OCHONDRIAL_TRANSCRIPTION TRANSCRIPTION TELOMERE_MAINTENANCE MEIOTIC_RECOMBINATION MEIOSIS CHROMOSOME_MAINTENANCE DNA_REPLICATION MITOTIC_M_M_G1_PHASES MITOTIC_PROMETAPHASE CELL_CYCLE_MIT OTIC CELL_CYCLE CELL_CYCLE_CHECKPOINTS G1_S_TRANSITION S_PHASE SYNTHESIS_OF_DNA METABOLISM_OF_NUCLEO TIDES METABOLISM_OF_CARBOHYDRA TES CHONDROITIN_SULFATE_BIOSYNTHESIS SYNTHESIS_AND_INTERCONVERSION_OF_NUCLEO TIDE_DI_AND_TRIPHOSPHA TES GLYCOSAMINOGLYCAN_METABOLISM HS_GAG_BIOSYNTHESIS DIABETES_PATHWAYS KERATAN_SULFATE_KERATIN_METABOLISM KERATAN_SULFATE_BIOSYNTHESIS ACTIVATED_TAK1_MEDIATES_P38_MAPK_A CTIVATION JNK_C_JUN_KINASES_PHOSPHOR YLATION_AND_ACTIVATION_MEDIATED_BY_ACTIVATED_HUMAN_TAK1 ARMS_MEDIATED_ACTIVATION IL1_SIGNALING METABOLISM_OF_AMINO_A CIDS_AND_DERIVATIVES APOPTOSIS NCAM_SIGNALING_FOR_NEURITE_OUT_GR OWTH ACTIVATION_OF_CHAPER ONE_GENES_BY_XBP1S YAP1_AND_WWTR1_TAZ_STIMULATED_GENE_EXPRESSION GAP_JUNCTION_ASSEMBLY GAP_JUNCTION_TRAFFICKING HEPARAN_SULFATE_HEPARIN_HS_GAG_METABOLISM CHONDROITIN_SULFATE_DERMATAN_SULFATE_METABOLISM A_TETRASACCHARIDE_LINKER_SEQ UENCE_IS_REQ UIRED_FOR_GAG_SYNTHESIS COLLAGEN_FORMATION EXTRACELLULAR_MATRIX_ORGANIZATION ASSOCIATION_OF_TRIC_CCT_WITH_T ARGET_PROTEINS_DURING_BIOSYNTHESIS METABOLISM_OF_PROTEINS UNFOLDED_PR OTEIN_RESPONSE PERK_REGULATED_GENE_EXPRESSION ACTIVATION_OF_GENES_BY_ATF4 PYRUVATE_METABOLISM G1_PHASE PYRIMIDINE_METABOLISM INTRINSIC_PATHWAY_FOR_APOPTOSIS ACTIVATION_OF_BH3_ONLY_PROTEINS RNA_POL_II_TRANSCRIPTION_PRE_INITIA TION_AND_PROMOTER_OPENING RNA_POL_II_TRANSCRIPTION RNA_POL_II_PRE_TRANSCRIPTION_EVENTS MRNA_CAPPING HIV_LIFE_CYCLE LATE_PHASE_OF_HIV_LIFE_CYCLE TRANSPORT_OF_RIBONUCLEOPR OTEINS_INTO_THE_HOST_NUCLEUS GLUCOSE_TRANSPOR T TRANSPORT_OF_MATURE_MRNA_DERIVED_FR OM_AN_INTRONLESS_TRANSCRIPT METABOLISM_OF_NON_CODING_RNA NEP_NS2_INTERA CTS_WITH_THE_CELLULAR_EXPOR T_MACHINERY INTERACTIONS_OF_VPR_WITH_HOST_CELLULAR_PR OTEINS REGULATION_OF_GLUCOKINASE_BY_GLUCOKINASE_REGULA TORY_PROTEIN APC_CDC20_MEDIATED_DEGRADATION_OF_NEK2A INHIBITION_OF_THE_PR OTEOLYTIC_ACTIVITY_OF_APC_C_REQ UIRED_FOR_THE_ONSET_OF_ANAPHASE_BY_MIT OTIC_SPINDLE_CHECKPOINT_COMPONENTS APC_C_CDC20_MEDIATED_DEGRADATION_OF_CYCLIN_B PHOSPHORYLATION_OF_THE_APC_C CONVERSION_FR OM_APC_C_CDC20_T O_APC_C_CDH1_IN_LATE_ANAPHASE ASSEMBLY_OF_THE_PRE_REPLICA TIVE_COMPLEX ORC1_REMOVAL_FROM_CHROMATIN REGULATION_OF_MITOTIC_CELL_CYCLE MITOTIC_G1_G1_S_PHASES M_G1_TRANSITION APC_C_CDH1_MEDIATED_DEGRADATION_OF_CDC20_AND_O THER_APC_C_CDH1_TARGETED_PR OTEINS_IN_LATE_MITOSIS_EARLY_G1 APC_C_CDC20_MEDIATED_DEGRADATION_OF_MITOTIC_PROTEINS HIV_INFECTION G0_AND_EARLY_G1 FACTORS_INVOLVED_IN_MEGAKAR YOCYTE_DEVELOPMENT_AND_PLA TELET_PRODUCTION P53_INDEPENDENT_G1_S_DNA_D AMAGE_CHECKPOINT SCF_BETA_TRCP_MEDIATED_DEGRADATION_OF_EMI1 CDT1_ASSOCIATION_WITH_THE_CDC6_ORC_ORIGIN_COMPLEX AUTODEGRADATION_OF_CDH1_BY_CDH1_APC_C CYCLIN_E_ASSOCIATED_EVENTS_DURING_G1_S_TRANSITION_ SCFSKP2_MEDIATED_DEGRADATION_OF_P27_P21 CDK_MEDIATED_PHOSPHORYLATION_AND_REMO VAL_OF_CDC6 P53_DEPENDENT_G1_DNA_D AMAGE_RESPONSE DESTABILIZATION_OF_MRNA_BY_A UF1_HNRNP_D0 HOST_INTERACTIONS_OF_HIV_FACTORS REGULATION_OF_MRNA_STABILITY_BY_PR OTEINS_THAT_BIND_AU_RICH_ELEMENTS MHC_CLASS_II_ANTIGEN_PRESENT ATION PURINE_METABOLISM OLFACTORY_SIGNALING_PATHWAY ANTIVIRAL_MECHANISM_BY_IFN_STIMULA TED_GENES ANTIGEN_PROCESSING_UBIQ UITINATION_PROTEASOME_DEGRADATION REGULATION_OF_ORNITHINE_DECARBO XYLASE_ODC AUTODEGRADATION_OF_THE_E3_UBIQ UITIN_LIGASE_COP1 VIF_MEDIATED_DEGRADATION_OF_APOBEC3G ER_PHAGOSOME_PATHWAY ACTIVATION_OF_NF_KAPPAB_IN_B_CELLS REGULATION_OF_INSULIN_LIKE_GR OWTH_FACTOR_IGF_ACTIVITY_BY_INSULIN_LIKE_GR OWTH_FACTOR_BINDING_PR OTEINS_IGFBPS N_GLYCAN_ANTENNAE_ELONGA TION_IN_THE_MEDIAL_TRANS_GOLGI AMINO_ACID_TRANSPOR T_ACROSS_THE_PLASMA_MEMBRANE FATTY_ACYL_COA_BIOSYNTHESIS INSULIN_SYNTHESIS_AND_PR OCESSING AMINE_DERIVED_HORMONES SIGNALING_BY_HIPPO NOD1_2_SIGNALING_PATHWAY BASIGIN_INTERA CTIONS SIGNALING_BY_SCF_KIT PPARA_ACTIVATES_GENE_EXPRESSION POST_TRANSLATIONAL_PROTEIN_MODIFICATION ASPARAGINE_N_LINKED_GLYCOSYLATION CROSS_PRESENTATION_OF_SOLUBLE_EXOGENOUS_ANTIGENS_ENDOSOMES ANTIGEN_PROCESSING_CR OSS_PRESENTATION DOWNSTREAM_SIGNALING_EVENTS_OF_B_CELL_RECEPT OR_BCR SIGNALING_BY_WNT CLASS_I_MHC_MEDIATED_ANTIGEN_PR OCESSING_PRESENTATION REGULATION_OF_APOPTOSIS ACTIVATION_OF_KAINATE_RECEPTORS_UPON_GLUTAMATE_BINDING G_BETA_GAMMA_SIGNALLING_THR OUGH_PLC_BETA PRE_NOTCH_TRANSCRIPTION_AND_TRANSLA TION PRE_NOTCH_EXPRESSION_AND_PR OCESSING NEF_MEDIATES_DOWN_MODULATION_OF_CELL_SURFACE_RECEPTORS_BY_RECRUITING_THEM_T O_CLATHRIN_ADAPTERS NCAM1_INTERACTIONS HS_GAG_DEGRADATION SMOOTH_MUSCLE_CONTRA CTION ADHERENS_JUNCTIONS_INTERA CTIONS MEMBRANE_TRAFFICKING DEGRADATION_OF_THE_EXTRA CELLULAR_MATRIX GLUTATHIONE_CONJUGATION SEMA4D_INDUCED_CELL_MIGRA TION_AND_GROWTH_CONE_COLLAPSE METABOLISM_OF_VITAMINS_AND_COFACTORS METABOLISM_OF_POLYAMINES SIGNALING_BY_CONSTITUTIVEL Y_ACTIVE_EGFR SIGNALING_BY_ROBO_RECEPTOR SIGNALLING_TO_ERKS SIGNALLING_TO_RAS ENDOSOMAL_SORTING_COMPLEX_REQ UIRED_FOR_TRANSPOR T_ESCRT CHOLESTEROL_BIOSYNTHESIS ELONGATION_ARREST_AND_RECO VERY SHC_RELATED_EVENTS SHC_MEDIATED_SIGNALLING SHC1_EVENTS_IN_ERBB4_SIGNALING GRB2_EVENTS_IN_ERBB2_SIGNALING BMAL1_CLOCK_NPAS2_ACTIVATES_CIRCADIAN_EXPRESSION CIRCADIAN_CLOCK NOTCH1_INTRACELLULAR_DOMAIN_REGULA TES_TRANSCRIPTION CIRCADIAN_REPRESSION_OF_EXPRESSION_BY_REV_ERBA RORA_ACTIVATES_CIRCADIAN_EXPRESSION DESTABILIZATION_OF_MRNA_BY_BRF1 DESTABILIZATION_OF_MRNA_BY_TRISTETRAPR OLIN_TTP DEADENYLATION_DEPENDENT_MRNA_DECA Y APOPTOTIC_EXECUTION_PHASE SMAD2_SMAD3_SMAD4_HETER OTRIMER_REGULATES_TRANSCRIPTION DEADENYLATION_OF_MRNA CITRIC_ACID_CYCLE_TCA_CYCLE REGULATION_OF_HYPOXIA_INDUCIBLE_FACTOR_HIF_BY_OXYGEN PYRUVATE_METABOLISM_AND_CITRIC_A CID_TCA_CYCLE POST_TRANSLATIONAL_MODIFICATION_SYNTHESIS_OF_GPI_ANCHORED_PR OTEINS SYNTHESIS_OF_GLYCOSYLPHOSPHATIDYLINOSITOL_GPI BIOSYNTHESIS_OF_THE_N_GLYCAN_PRECURSOR_DOLICHOL_LIPID_LINKED_OLIGOSA CCHARIDE_LLO_AND_TRANSFER_T O_A_NASCENT_PR OTEIN PKB_MEDIATED_EVENTS FORMATION_OF_RNA_POL_II_ELONGA TION_COMPLEX_ FORMATION_OF_TRANSCRIPTION_COUPLED_NER_TC_NER_REP AIR_COMPLEX RNA_POL_I_TRANSCRIPTION_TERMINA TION SPHINGOLIPID_DE_NO VO_BIOSYNTHESIS ZINC_TRANSPOR TERS O_LINKED_GLYCOSYLATION_OF_MUCINS GLYCOGEN_BREAKDO WN_GLYCOGENOLYSIS SIGNALING_BY_TGF_BETA_RECEPTOR_COMPLEX DOWNREGULATION_OF_TGF_BETA_RECEPTOR_SIGNALING TGF_BETA_RECEPTOR_SIGNALING_A CTIVATES_SMADS SIGNALING_BY_ERBB4 TRANSCRIPTIONAL_A CTIVITY_OF_SMAD2_SMAD3_SMAD4_HETER OTRIMER FRS2_MEDIATED_CASCADE SHC_MEDIATED_CASCADE SIGNALING_BY_FGFR_MUTANTS INSULIN_RECEPT OR_SIGNALLING_CASCADE SIGNALING_BY_INSULIN_RECEPT OR PIP3_ACTIVATES_AKT_SIGNALING PI3K_AKT_ACTIVATION OXYGEN_DEPENDENT_PR OLINE_HYDROXYLATION_OF_HYPOXIA_INDUCIBLE_FACTOR_ALPHA SULFUR_AMINO_A CID_METABOLISM RNA_POL_I_TRANSCRIPTION_INITIA TION THROMBOXANE_SIGNALLING_THR OUGH_TP_RECEPT OR SIGNAL_AMPLIFICATION ADP_SIGNALLING_THR OUGH_P2RY1 GASTRIN_CREB_SIGNALLING_P ATHWAY_VIA_PKC_AND_MAPK G_ALPHA_Q_SIGNALLING_EVENTS THROMBIN_SIGNALLING_THR OUGH_PROTEINASE_ACTIVATED_RECEPTORS_PARS G_BETA_GAMMA_SIGNALLING_THR OUGH_PI3KGAMMA CLASS_B_2_SECRETIN_F AMILY_RECEPTORS GLUCAGON_TYPE_LIGAND_RECEPT ORS G_ALPHA1213_SIGNALLING_EVENTS SIGNALLING_BY_NGF SIGNALING_BY_EGFR_IN_CANCER DOWNSTREAM_SIGNAL_TRANSDUCTION PI3K_CASCADE NEGATIVE_REGULATION_OF_FGFR_SIGNALING NGF_SIGNALLING_VIA_TRKA_FR OM_THE_PLASMA_MEMBRANE SIGNALING_BY_FGFR_IN_DISEASE SIGNALING_BY_FGFR DOWNSTREAM_SIGNALING_OF_A CTIVATED_FGFR PI_3K_CASCADE PROSTACYCLIN_SIGNALLING_THR OUGH_PROSTACYCLIN_RECEPT OR INHIBITION_OF_INSULIN_SECRETION_BY_ADRENALINE_NORADRENALINE ADP_SIGNALLING_THR OUGH_P2RY12 G_PROTEIN_ACTIVATION G_PROTEIN_BETA_GAMMA_SIGNALLING INWARDLY_RECTIFYING_K_CHANNELS INHIBITION_OF_VOLTAGE_GATED_CA2_CHANNELS_VIA_GBET A_GAMMA_SUBUNITS HDL_MEDIATED_LIPID_TRANSPOR T P75_NTR_RECEPT OR_MEDIATED_SIGNALLING CELL_DEATH_SIGNALLING_VIA_NRA GE_NRIF_AND_NADE NRAGE_SIGNALS_DEATH_THROUGH_JNK SIGNALING_BY_NO TCH REGULATION_OF_BETA_CELL_DEVELOPMENT TIE2_SIGNALING EGFR_DOWNREGULATION SIGNAL_TRANSDUCTION_BY_L1 SIGNALING_BY_NO TCH1 NEPHRIN_INTERA CTIONS SIGNALING_BY_NOD AL SIGNALING_BY_ILS SEMA4D_IN_SEMAPHORIN_SIGNALING IL_2_SIGNALING EICOSANOID_LIGAND_BINDING_RECEPT ORS CD28_CO_STIMULATION SEMAPHORIN_INTERA CTIONS GROWTH_HORMONE_RECEPT OR_SIGNALING AXON_GUIDANCE SIGNALING_BY_PDGF DEFENSINS BETA_DEFENSINS PROTEOLYTIC_CLEAVAGE_OF_SNARE_COMPLEX_PR OTEINS BOTULINUM_NEUR OTOXICITY TRANSPORT_OF_GLUCOSE_AND_O THER_SUGARS_BILE_SAL TS_AND_ORGANIC_A CIDS_METAL_IONS_AND_AMINE_COMPOUNDS INTERFERON_SIGNALING CYTOKINE_SIGNALING_IN_IMMUNE_SYSTEM SIGNALING_BY_THE_B_CELL_RECEPT OR_BCR THE_ROLE_OF_NEF_IN_HIV1_REPLICA TION_AND_DISEASE_PATHOGENESIS GPVI_MEDIATED_ACTIVATION_CASCADE TRAF6_MEDIATED_IRF7_ACTIVATION TOLL_RECEPTOR_CASCADES ACTIVATED_TLR4_SIGNALLING TRAF6_MEDIATED_INDUCTION_OF_NFKB_AND_MAP_KINASES_UPON_TLR7_8_OR_9_A CTIVATION MYD88_MAL_CASCADE_INITIA TED_ON_PLASMA_MEMBRANE NFKB_AND_MAP_KINASES_A CTIVATION_MEDIATED_BY_TLR4_SIGNALING_REPER TOIRE CELL_SURFACE_INTERACTIONS_AT_THE_VASCULAR_WALL TCR_SIGNALING DOWNSTREAM_TCR_SIGNALING IRON_UPTAKE_AND_TRANSPOR T TRANSPORT_OF_INORGANIC_CATIONS_ANIONS_AND_AMINO_A CIDS_OLIGOPEPTIDES AMINE_LIGAND_BINDING_RECEPT ORS CTLA4_INHIBITORY_SIGNALING ANTIGEN_PRESENTATION_FOLDING_ASSEMBLY_AND_PEPTIDE_LO ADING_OF_CLASS_I_MHC REGULATION_OF_KIT_SIGNALING REGULATION_OF_SIGNALING_BY_CBL LIGAND_GATED_ION_CHANNEL_TRANSPOR T CREB_PHOSPHORYLATION_THROUGH_THE_ACTIVATION_OF_CAMKII REGULATION_OF_GENE_EXPRESSION_IN_BET A_CELLS GABA_SYNTHESIS_RELEASE_REUPT AKE_AND_DEGRAD ATION SIGNALING_BY_FGFR1_FUSION_MUT ANTS SIGNALING_BY_FGFR1_MUTANTS SPHINGOLIPID_METABOLISM GLYCOSPHINGOLIPID_METABOLISM ACTIVATED_POINT_MUTANTS_OF_FGFR2 PTM_GAMMA_CARBOXYLATION_HYPUSINE_FORMATION_AND_ARYLSULFATASE_ACTIVATION NUCLEOTIDE_BINDING_DOMAIN_LEUCINE_RICH_REPEA T_CONTAINING_RECEPTOR_NLR_SIGNALING_PATHWAYS ENOS_ACTIVATION_AND_REGULATION METAL_ION_SLC_TRANSPOR TERS SLC_MEDIATED_TRANSMEMBRANE_TRANSPOR T AMINO_ACID_AND_OLIGOPEPTIDE_SLC_TRANSPOR TERS MYOGENESIS MAP_KINASE_ACTIVATION_IN_TLR_CASCADE APOPTOTIC_CLEAVAGE_OF_CELLULAR_PR OTEINS FORMATION_OF_INCISION_COMPLEX_IN_GG_NER DOWNREGULATION_OF_SMAD2_3_SMAD4_TRANSCRIPTIONAL_A CTIVITY LATENT_INFECTION_OF_HOMO_SAPIENS_WITH_MYCOBA CTERIUM_TUBERCULOSIS TRANSFERRIN_ENDOCYT OSIS_AND_RECYCLING INSULIN_RECEPT OR_RECYCLING TRANSPORT_TO_THE_GOLGI_AND_SUBSEQ UENT_MODIFICATION SYNTHESIS_SECRETION_AND_DEA CYLATION_OF_GHRELIN SYNTHESIS_SECRETION_AND_INA CTIVATION_OF_GLP1 INCRETIN_SYNTHESIS_SECRETION_AND_INA CTIVATION SIGNALING_BY_BMP SIGNALING_BY_ERBB2 FATTY_ACID_TRIACYLGLYCEROL_AND_KETONE_BODY_METABOLISM ERK_MAPK_TARGETS MAPK_TARGETS_NUCLEAR_EVENTS_MEDIA TED_BY_MAP_KINASES NUCLEAR_EVENTS_KINASE_AND_TRANSCRIPTION_F ACTOR_ACTIVATION DEVELOPMENTAL_BIOLOGY TRANSCRIPTIONAL_REGULA TION_OF_WHITE_ADIPOCYTE_DIFFERENTIA TION GAB1_SIGNALOSOME PI3K_EVENTS_IN_ERBB2_SIGNALING PI3K_EVENTS_IN_ERBB4_SIGNALING PHASE_II_CONJUGATION PEROXISOMAL_LIPID_METABOLISM CTNNB1_PHOSPHOR YLATION_CASCADE BRANCHED_CHAIN_AMINO_A CID_CATABOLISM CELL_CELL_COMMUNICATION CELL_JUNCTION_ORGANIZA TION TIGHT_JUNCTION_INTERA CTIONS CELL_CELL_JUNCTION_ORGANIZA TION GENERIC_TRANSCRIPTION_P ATHWAY SYNTHESIS_OF_PIPS_AT_THE_GOLGI_MEMBRANE NUCLEAR_SIGNALING_BY_ERBB4 L1CAM_INTERA CTIONS TRIF_MEDIATED_TLR3_SIGNALING TRAF6_MEDIATED_NFKB_ACTIVATION RECYCLING_PATHWAY_OF_L1 TRAFFICKING_OF_GLUR2_CONT AINING_AMPA_RECEPTORS SYNTHESIS_OF_PC PRE_NOTCH_PROCESSING_IN_GOLGI XENOBIOTICS ENERGY_DEPENDENT_REGULA TION_OF_MTOR_BY_LKB1_AMPK ACTIVATED_AMPK_STIMULATES_FATTY_ACID_OXIDATION_IN_MUSCLE ABCA_TRANSPOR TERS_IN_LIPID_HOMEOST ASIS REGULATION_OF_IFNA_SIGNALING GENERATION_OF_SECOND_MESSENGER_MOLECULES INTERFERON_ALPHA_BETA_SIGNALING METABOLISM_OF_STER OID_HORMONES_AND_VITAMINS_A_AND_D STEROID_HORMONES NEGATIVE_REGULATORS_OF_RIG_I_MDA5_SIGNALING RIG_I_MDA5_MEDIATED_INDUCTION_OF_IFN_ALPHA_BET A_PATHWAYS LIPOPROTEIN_METABOLISM TERMINATION_OF_O_GLYCAN_BIOSYNTHESIS CHYLOMICRON_MEDIATED_LIPID_TRANSPOR T LIPID_DIGESTION_MOBILIZATION_AND_TRANSPOR T NITRIC_OXIDE_STIMULATES_GUANYLATE_CYCLASE CGMP_EFFECTS INTEGRATION_OF_ENERGY_METABOLISM OPIOID_SIGNALLING REGULATION_OF_INSULIN_SECRETION REGULATION_OF_INSULIN_SECRETION_BY_GLUCA GON_LIKE_PEPTIDE1 GLUCAGON_SIGNALING_IN_METABOLIC_REGULATION G_ALPHA_Z_SIGNALLING_EVENTS AMINE_COMPOUND_SLC_TRANSPOR TERS NA_CL_DEPENDENT_NEUR OTRANSMITTER_TRANSPOR TERS NETRIN1_SIGNALING NUCLEAR_RECEPT OR_TRANSCRIPTION_PATHWAY PLC_BETA_MEDIATED_EVENTS OTHER_SEMAPHORIN_INTERA CTIONS P130CAS_LINKA GE_TO_MAPK_SIGNALING_FOR_INTEGRINS GRB2_SOS_PROVIDES_LINKA GE_TO_MAPK_SIGNALING_FOR_INTERGRINS_ STRIATED_MUSCLE_CONTRA CTION MUSCLE_CONTRA CTION IL_RECEPTOR_SHC_SIGNALING SIGNALING_BY_RHO_GTPASES VOLTAGE_GATED_POTASSIUM_CHANNELS POTASSIUM_CHANNELS GABA_RECEPTOR_ACTIVATION GABA_B_RECEPT OR_ACTIVATION CREB_PHOSPHORYLATION_THROUGH_THE_ACTIVATION_OF_RAS POST_NMDA_RECEPTOR_ACTIVATION_EVENTS ACTIVATION_OF_NMDA_RECEPTOR_UPON_GLUTAMATE_BINDING_AND_POSTSYNAPTIC_EVENTS NEUROTRANSMITTER_RECEPT OR_BINDING_AND_DO WNSTREAM_TRANSMISSION_IN_THE_POSTSYNAPTIC_CELL NEURONAL_SYSTEM TRANSMISSION_A CROSS_CHEMICAL_SYNAPSES TRAFFICKING_OF_AMPA_RECEPTORS INTERACTION_BETWEEN_L1_AND_ANKYRINS CD28_DEPENDENT_PI3K_AKT_SIGNALING RAS_ACTIVATION_UOPN_CA2_INFUX_THR OUGH_NMDA_RECEPTOR UNBLOCKING_OF_NMD A_RECEPTOR_GLUTAMATE_BINDING_AND_A CTIVATION PEPTIDE_LIGAND_BINDING_RECEPT ORS CLASS_A1_RHODOPSIN_LIKE_RECEPT ORS GPCR_LIGAND_BINDING G_ALPHA_I_SIGNALLING_EVENTS PLATELET_ACTIVATION_SIGNALING_AND_A GGREGATION RESPONSE_TO_ELEVATED_PLATELET_CYTOSOLIC_CA2_ IMMUNOREGULATORY_INTERACTIONS_BETWEEN_A_LYMPHOID_AND_A_NON_LYMPHOID_CELL PHOSPHORYLATION_OF_CD3_AND_TCR_ZET A_CHAINS PD1_SIGNALING PLATELET_AGGREGATION_PLUG_FORMATION INTEGRIN_ALPHAIIB_BETA3_SIGNALING HEMOSTASIS INTEGRIN_CELL_SURF ACE_INTERACTIONS CHEMOKINE_RECEPT ORS_BIND_CHEMOKINES IL_3_5_AND_GM_CSF_SIGNALING INFLAMMASOMES INTERFERON_GAMMA_SIGNALING INNATE_IMMUNE_SYSTEM COSTIMULATION_BY_THE_CD28_F AMILY NUCLEOTIDE_LIKE_PURINERGIC_RECEPT ORS ANTIGEN_ACTIVATES_B_CELL_RECEPT OR_LEADING_TO_GENERATION_OF_SECOND_MESSENGERS ION_CHANNEL_TRANSPOR T ION_TRANSPORT_BY_P_TYPE_ATPASES TRANSMEMBRANE_TRANSPOR T_OF_SMALL_MOLECULES FGFR_LIGAND_BINDING_AND_A CTIVATION NEUROTRANSMITTER_RELEASE_CYCLE GLUTAMATE_NEUROTRANSMITTER_RELEASE_CYCLE PLATELET_SENSITIZATION_BY_LDL TRIGLYCERIDE_BIOSYNTHESIS DARPP_32_EVENTS SYNTHESIS_OF_PIPS_AT_THE_PLASMA_MEMBRANE PI_METABOLISM PLATELET_HOMEOSTASIS GLYCEROPHOSPHOLIPID_BIOSYNTHESIS PHOSPHOLIPID_METABOLISM METABOLISM_OF_LIPIDS_AND_LIPOPR OTEINS EFFECTS_OF_PIP2_HYDR OLYSIS INTRINSIC_PATHWAY FORMATION_OF_FIBRIN_CLO T_CLOTTING_CASCADE ABC_FAMILY_PROTEINS_MEDIATED_TRANSPORT G_ALPHA_S_SIGNALLING_EVENTS RAP1_SIGNALLING COMPLEMENT_CASCADE AQUAPORIN_MEDIATED_TRANSPORT REGULATION_OF_WATER_BALANCE_BY_RENAL_A QUAPORINS PHOSPHOLIPASE_C_MEDIATED_CASCADE PKA_MEDIATED_PHOSPHORYLATION_OF_CREB CA_DEPENDENT_EVENTS DAG_AND_IP3_SIGNALING PHASE1_FUNCTIONALIZA TION_OF_COMPOUNDS BIOLOGICAL_OXIDATIONS RIP_MEDIATED_NFKB_ACTIVATION_VIA_DAI TAK1_ACTIVATES_NFKB_BY_PHOSPHOR YLATION_AND_ACTIVATION_OF_IKKS_COMPLEX CYTOCHROME_P450_ARRANGED_BY_SUBSTRA TE_TYPE ENDOGENOUS_STER OLS GOLGI_ASSOCIATED_VESICLE_BIOGENESIS TRANS_GOLGI_NETW ORK_VESICLE_B UDDING TRANSPORT_OF_VITAMINS_NUCLEOSIDES_AND_RELA TED_MOLECULES LYSOSOME_VESICLE_BIOGENESIS PLATELET_CALCIUM_HOMEOST ASIS ACTIVATED_NOTCH1_TRANSMITS_SIGNAL_T O_THE_NUCLEUS BILE_ACID_AND_BILE_SALT_METABOLISM SYNTHESIS_OF_BILE_A CIDS_AND_BILE_SALTS SYNTHESIS_OF_BILE_A CIDS_AND_BILE_SALTS_VIA_7ALPHA_HYDR OXYCHOLESTER OL ACYL_CHAIN_REMODELLING_OF_PS ACYL_CHAIN_REMODELLING_OF_PG SYNTHESIS_OF_PA ACYL_CHAIN_REMODELLING_OF_PI ACYL_CHAIN_REMODELLING_OF_PE ACYL_CHAIN_REMODELLING_OF_PC Molecular Pathways 2 Wavelet_HLL_rlgl_lowGrayLevelRunEmphasis Wavelet_HLL_rlgl_shortRunLowGrayLevEmpha Wavelet_LHH_rlgl_longRunLowGrayLevEmpha Wavelet_HHH_rlgl_lowGrayLevelRunEmphasis Wavelet_HHH_rlgl_shortRunLowGrayLevEmpha Wavelet_LHL_rlgl_lowGrayLevelRunEmphasis Wavelet_LHL_rlgl_shortRunLowGrayLevEmpha Wavelet_LLH_rlgl_lowGrayLevelRunEmphasis Wavelet_LLH_rlgl_shortRunLowGrayLevEmpha Wavelet_HHH_rlgl_longRunLowGrayLevEmpha Wavelet_HHL_rlgl_longRunLowGrayLevEmpha Wavelet_HLH_rlgl_longRunLowGrayLevEmpha Wavelet_LHH_glcm_infoCorr2 Wavelet_HHH_glcm_infoCorr2 Wavelet_HHL_stats_median Wavelet_HLH_stats_median GLSZM_zonePercentage Wavelet_LLH_stats_min Wavelet_LHL_stats_min Wavelet_LLL_rlgl_longRunLowGrayLevEmpha RLGL_longRunLowGrayLevEmpha GLCM_clusShade Wavelet_LLL_glcm_clusShade Wavelet_LHH_stats_median Wavelet_LHH_stats_mean Wavelet_HLL_stats_entropy Wavelet_HLL_glcm_sumEntro Wavelet_HLL_glcm_entrop2 Wavelet_HLL_glcm_dissimilar Wavelet_HLL_glcm_diffEntro Wavelet_HLL_glcm_contrast Wavelet_LHH_glcm_clusProm Wavelet_HLH_glcm_clusProm Wavelet_HHL_glcm_clusProm Wavelet_LHL_glcm_clusProm Wavelet_LLH_glcm_clusProm GLCM_sumEntro Wavelet_LLL_glcm_sumEntro Stats_entropy Wavelet_LLL_stats_entropy Wavelet_LLL_glcm_entrop2 GLCM_entrop2 Stats_skewness Wavelet_LLL_stats_skewness Wavelet_LLL_rlgl_shortRunLowGrayLevEmpha Wavelet_LLL_rlgl_lowGrayLevelRunEmphasis RLGL_lowGrayLevelRunEmphasis RLGL_shortRunLowGrayLevEmpha Wavelet_LHH_stats_min Wavelet_LHH_rlgl_lowGrayLevelRunEmphasis Wavelet_LHH_rlgl_shortRunLowGrayLevEmpha Wavelet_HHL_rlgl_lowGrayLevelRunEmphasis Wavelet_HHL_rlgl_shortRunLowGrayLevEmpha Shape_surfVolRatio Wavelet_HLH_rlgl_lowGrayLevelRunEmphasis Wavelet_HLH_rlgl_shortRunLowGrayLevEmpha RLGL_shortRunEmphasis RLGL_runPercentage Wavelet_LLL_rlgl_shortRunEmphasis Wavelet_LLL_rlgl_runPercentage Wavelet_HLL_rlgl_shortRunEmphasis Wavelet_HLL_rlgl_runPercentage Wavelet_LLL_glcm_contrast GLCM_contrast GLCM_dissimilar Wavelet_LLL_glcm_dissimilar GLCM_diffEntro Wavelet_LLL_glcm_diffEntro LoG_sigma_0_5_mm_3D_stats_mean LoG_sigma_0_5_mm_3D_stats_meanPos LoG_sigma_1_5_mm_3D_stats_meanPos LoG_sigma_1_mm_3D_stats_meanPos LoG_sigma_2_mm_3D_stats_mean LoG_sigma_2_mm_3D_stats_meanPos LoG_sigma_3_mm_3D_stats_meanPos LoG_sigma_4_mm_3D_stats_meanPos LoG_sigma_4_5_mm_3D_stats_meanPos LoG_sigma_3_5_mm_3D_stats_mean LoG_sigma_3_5_mm_3D_stats_meanPos LoG_sigma_2_5_mm_3D_stats_meanPos LoG_sigma_5_mm_3D_stats_mean LoG_sigma_5_mm_3D_stats_meanPos LoG_sigma_1_5_mm_3D_stats_mean LoG_sigma_1_mm_3D_stats_mean LoG_sigma_2_5_mm_3D_stats_mean LoG_sigma_3_mm_3D_stats_mean LoG_sigma_4_mm_3D_stats_mean LoG_sigma_4_5_mm_3D_stats_mean LoG_sigma_0_5_mm_2D_stats_meanPos LoG_sigma_1_5_mm_2D_stats_meanPos LoG_sigma_1_mm_2D_stats_mean LoG_sigma_1_mm_2D_stats_meanPos LoG_sigma_2_mm_2D_stats_meanPos LoG_sigma_2_5_mm_2D_stats_meanPos LoG_sigma_3_5_mm_2D_stats_meanPos LoG_sigma_3_mm_2D_stats_meanPos LoG_sigma_4_5_mm_2D_stats_mean LoG_sigma_4_5_mm_2D_stats_meanPos LoG_sigma_4_mm_2D_stats_meanPos LoG_sigma_5_mm_2D_stats_meanPos LoG_sigma_0_5_mm_2D_stats_mean LoG_sigma_1_5_mm_2D_stats_mean LoG_sigma_2_mm_2D_stats_mean LoG_sigma_2_5_mm_2D_stats_mean LoG_sigma_3_5_mm_2D_stats_mean LoG_sigma_3_mm_2D_stats_mean LoG_sigma_4_mm_2D_stats_mean LoG_sigma_5_mm_2D_stats_mean Wavelet_LHH_glcm_contrast Wavelet_LHH_glcm_clusTend Wavelet_LHH_glcm_entrop2 Wavelet_LHH_glcm_dissimilar Wavelet_LHH_glcm_diffEntro Wavelet_LHH_glcm_sumEntro Wavelet_LHH_stats_entropy Wavelet_LHH_rlgl_runPercentage Wavelet_LHH_rlgl_shortRunEmphasis Wavelet_HHH_rlgl_shortRunEmphasis Wavelet_HHH_rlgl_runPercentage Wavelet_HHL_rlgl_runPercentage Wavelet_HHL_rlgl_shortRunEmphasis Wavelet_LHL_glcm_clusTend Wavelet_LHL_glcm_contrast Wavelet_LHL_glcm_entrop2 Wavelet_LHL_glcm_dissimilar Wavelet_LHL_glcm_diffEntro Wavelet_LHL_glcm_sumEntro Wavelet_LHL_stats_entropy Wavelet_HHL_glcm_clusTend Wavelet_HHL_glcm_sumEntro Wavelet_HHL_glcm_contrast Wavelet_HHL_stats_entropy Wavelet_HHL_glcm_entrop2 Wavelet_HHL_glcm_dissimilar Wavelet_HHL_glcm_diffEntro Wavelet_HHH_glcm_clusProm Wavelet_HHH_glcm_entrop2 Wavelet_HHH_glcm_clusTend Wavelet_HHH_glcm_dissimilar Wavelet_HHH_glcm_diffEntro Wavelet_HHH_glcm_sumEntro Wavelet_HHH_glcm_contrast Wavelet_HHH_stats_entropy Wavelet_HLH_glcm_clusTend Wavelet_HLH_glcm_sumEntro Wavelet_HLH_glcm_dissimilar Wavelet_HLH_glcm_diffEntro Wavelet_HLH_glcm_contrast Wavelet_HLH_stats_entropy Wavelet_HLH_glcm_entrop2 Wavelet_HLH_rlgl_runPercentage Wavelet_HLH_rlgl_shortRunEmphasis Wavelet_LLH_rlgl_runPercentage Wavelet_LLH_rlgl_shortRunEmphasis Wavelet_LHL_rlgl_runPercentage Wavelet_LHL_rlgl_shortRunEmphasis Wavelet_LLH_glcm_clusTend Wavelet_LLH_glcm_contrast Wavelet_LLH_glcm_dissimilar Wavelet_LLH_glcm_diffEntro Wavelet_LLH_glcm_sumEntro Wavelet_LLH_stats_entropy Wavelet_LLH_glcm_entrop2 Wavelet_HLL_glcm_infoCorr2 Wavelet_HLL_glcm_correl1 Wavelet_HLL_stats_min Wavelet_HLH_glcm_correl1 Wavelet_HHL_glcm_correl1 GLCM_infoCorr2 Wavelet_LLL_glcm_infoCorr2 Wavelet_LHL_rlgl_longRunLowGrayLevEmpha Wavelet_LLH_rlgl_longRunLowGrayLevEmpha Wavelet_LLH_glcm_clusShade Wavelet_LLH_stats_skewness Wavelet_LHL_stats_skewness Shape_compactness2 Shape_sphericity Wavelet_HLH_stats_min Wavelet_HHL_stats_min Wavelet_HHH_stats_min Wavelet_HLH_glcm_infoCorr2 Wavelet_HHL_glcm_infoCorr2 Wavelet_LHL_glcm_infoCorr2 Wavelet_LLH_glcm_infoCorr2 Wavelet_HLL_glcm_clusTend Wavelet_HLL_glcm_clusProm Wavelet_HHL_glcm_clusShade GLSZM_intensityVariability GLSZM_lowIntensityEmphasis GLSZM_lowIntensitySmallAreaEmp Wavelet_LHH_glcm_clusShade Wavelet_LHH_stats_skewness Wavelet_LLL_glcm_clusTend GLCM_clusTend Wavelet_LLL_stats_md Stats_md Wavelet_LLL_stats_std Wavelet_LLL_stats_var Stats_std Stats_var LoG_sigma_3_5_mm_3D_stats_std LoG_sigma_3_mm_3D_stats_std LoG_sigma_2_5_mm_3D_stats_std LoG_sigma_2_mm_3D_stats_std LoG_sigma_1_mm_3D_stats_std LoG_sigma_0_5_mm_3D_stats_std LoG_sigma_1_5_mm_3D_stats_std LoG_sigma_4_5_mm_3D_stats_std LoG_sigma_4_mm_3D_stats_std LoG_sigma_5_mm_3D_stats_std LoG_sigma_5_mm_2D_stats_std LoG_sigma_4_5_mm_2D_stats_std LoG_sigma_4_mm_2D_stats_std LoG_sigma_3_5_mm_2D_stats_std LoG_sigma_3_mm_2D_stats_std LoG_sigma_2_5_mm_2D_stats_std LoG_sigma_2_mm_2D_stats_std LoG_sigma_1_mm_2D_stats_std LoG_sigma_0_5_mm_2D_stats_std LoG_sigma_1_5_mm_2D_stats_std Wavelet_HLL_stats_md Wavelet_HLL_stats_rms Wavelet_HLL_stats_std Wavelet_HLL_stats_var Wavelet_HLH_stats_rms Wavelet_HLH_stats_std Wavelet_HLH_stats_var Wavelet_HHH_stats_rms Wavelet_HHH_stats_std Wavelet_HHH_stats_var Wavelet_HHL_stats_md Wavelet_HHH_stats_md Wavelet_HLH_stats_md Wavelet_HHL_stats_rms Wavelet_HHL_stats_std Wavelet_HHL_stats_var Wavelet_LHL_stats_std Wavelet_LHL_stats_var Wavelet_LHL_stats_rms Wavelet_LHH_stats_rms Wavelet_LHH_stats_std Wavelet_LHH_stats_var Wavelet_LHL_stats_md Wavelet_LHH_stats_md Wavelet_LLH_stats_md Wavelet_LLH_stats_rms Wavelet_LLH_stats_std Wavelet_LLH_stats_var Wavelet_HHL_stats_mean Wavelet_HLH_stats_mean Stats_min Wavelet_LLL_stats_min GLCM_infoCorr1 Wavelet_LLL_glcm_infoCorr1 Wavelet_LLH_glcm_infoCorr1 Wavelet_HLL_glcm_infoCorr1 LoG_sigma_5_mm_2D_stats_entropy LoG_sigma_5_mm_2D_stats_entropyPos LoG_sigma_5_mm_3D_stats_entropyPos LoG_sigma_4_mm_2D_stats_entropy LoG_sigma_4_mm_2D_stats_entropyPos LoG_sigma_4_5_mm_2D_stats_entropyPos LoG_sigma_3_5_mm_2D_stats_entropyPos LoG_sigma_3_mm_2D_stats_entropyPos LoG_sigma_2_5_mm_2D_stats_entropy LoG_sigma_2_5_mm_2D_stats_entropyPos LoG_sigma_1_5_mm_2D_stats_entropyPos LoG_sigma_2_mm_2D_stats_entropyPos LoG_sigma_2_mm_2D_stats_entropy LoG_sigma_0_5_mm_2D_stats_entropyPos LoG_sigma_1_mm_2D_stats_entropyPos LoG_sigma_4_5_mm_3D_stats_entropy LoG_sigma_5_mm_3D_stats_entropy LoG_sigma_4_mm_3D_stats_entropy LoG_sigma_3_mm_3D_stats_entropy LoG_sigma_2_5_mm_3D_stats_entropy LoG_sigma_2_mm_3D_stats_entropy LoG_sigma_1_5_mm_3D_stats_entropy LoG_sigma_1_mm_3D_stats_entropy LoG_sigma_1_mm_2D_stats_entropy LoG_sigma_0_5_mm_2D_stats_entropy LoG_sigma_1_5_mm_2D_stats_entropy LoG_sigma_3_5_mm_2D_stats_entropy LoG_sigma_4_5_mm_2D_stats_entropy LoG_sigma_3_mm_2D_stats_entropy LoG_sigma_4_5_mm_3D_stats_entropyPos LoG_sigma_4_mm_3D_stats_entropyPos LoG_sigma_3_mm_3D_stats_entropyPos LoG_sigma_3_5_mm_3D_stats_entropy LoG_sigma_3_5_mm_3D_stats_entropyPos LoG_sigma_2_mm_3D_stats_entropyPos LoG_sigma_2_5_mm_3D_stats_entropyPos LoG_sigma_1_mm_3D_stats_entropyPos LoG_sigma_1_5_mm_3D_stats_entropyPos LoG_sigma_0_5_mm_3D_stats_entropy LoG_sigma_0_5_mm_3D_stats_entropyPos LoG_sigma_2_5_mm_2D_stats_uniformity LoG_sigma_3_mm_2D_stats_uniformity LoG_sigma_4_5_mm_2D_stats_uniformity LoG_sigma_3_5_mm_2D_stats_uniformity LoG_sigma_0_5_mm_2D_stats_uniformity LoG_sigma_1_5_mm_2D_stats_uniformity LoG_sigma_1_mm_2D_stats_uniformity LoG_sigma_0_5_mm_3D_stats_uniformity LoG_sigma_2_mm_3D_stats_uniformity LoG_sigma_2_5_mm_3D_stats_uniformity LoG_sigma_5_mm_3D_stats_uniformity LoG_sigma_3_5_mm_3D_stats_uniformity LoG_sigma_0_5_mm_3D_stats_uniformityPos LoG_sigma_1_5_mm_3D_stats_uniformity LoG_sigma_1_5_mm_3D_stats_uniformityPos LoG_sigma_1_mm_3D_stats_uniformity LoG_sigma_1_mm_3D_stats_uniformityPos LoG_sigma_2_mm_3D_stats_uniformityPos LoG_sigma_2_5_mm_3D_stats_uniformityPos LoG_sigma_3_mm_3D_stats_uniformity LoG_sigma_3_mm_3D_stats_uniformityPos LoG_sigma_3_5_mm_3D_stats_uniformityPos LoG_sigma_3_5_mm_2D_stats_uniformityPos LoG_sigma_4_mm_2D_stats_uniformityPos LoG_sigma_4_5_mm_2D_stats_uniformityPos LoG_sigma_4_mm_2D_stats_uniformity LoG_sigma_3_mm_2D_stats_uniformityPos LoG_sigma_5_mm_2D_stats_uniformity LoG_sigma_5_mm_2D_stats_uniformityPos LoG_sigma_0_5_mm_2D_stats_uniformityPos LoG_sigma_1_5_mm_2D_stats_uniformityPos LoG_sigma_1_mm_2D_stats_uniformityPos LoG_sigma_2_mm_2D_stats_uniformity LoG_sigma_2_mm_2D_stats_uniformityPos LoG_sigma_2_5_mm_2D_stats_uniformityPos LoG_sigma_4_5_mm_3D_stats_uniformity LoG_sigma_4_5_mm_3D_stats_uniformityPos LoG_sigma_5_mm_3D_stats_uniformityPos LoG_sigma_4_mm_3D_stats_uniformity LoG_sigma_4_mm_3D_stats_uniformityPos Wavelet_HLH_rlgl_longRunHighGrayLevEmpha Wavelet_LLH_glcm_invDiffnorm Wavelet_LLH_glcm_invDiffmomnor Wavelet_LLH_stats_kurtosis Wavelet_HHL_rlgl_longRunHighGrayLevEmpha Wavelet_LHH_rlgl_longRunHighGrayLevEmpha Wavelet_LLH_rlgl_longRunHighGrayLevEmpha GLCM_invDiffmomnor Wavelet_LLL_glcm_invDiffmomnor GLCM_invDiffnorm Wavelet_LLL_glcm_invDiffnorm Wavelet_LHL_rlgl_longRunEmphasis Wavelet_LLH_rlgl_longRunEmphasis Wavelet_LHH_stats_kurtosis Wavelet_LHH_glcm_invDiffmomnor Wavelet_LHH_glcm_invDiffnorm Wavelet_HHL_glcm_invDiffnorm Wavelet_HHL_glcm_invDiffmomnor Wavelet_HHL_stats_kurtosis Wavelet_LHL_glcm_invDiffnorm Wavelet_LHL_glcm_invDiffmomnor Wavelet_LHL_stats_kurtosis Wavelet_HLH_glcm_invDiffmomnor Wavelet_HLH_glcm_invDiffnorm Wavelet_HLH_stats_kurtosis Wavelet_HHH_glcm_invDiffnorm Wavelet_HHH_glcm_invDiffmomnor Wavelet_HLH_rlgl_longRunEmphasis Wavelet_HLH_glcm_maxProb Wavelet_HLH_glcm_energy Wavelet_HLH_stats_uniformity Wavelet_HLH_glcm_homogeneity1 Wavelet_HLH_glcm_homogeneity2 Wavelet_LLH_glcm_inverseVar Wavelet_HLH_glcm_inverseVar Wavelet_LLH_stats_uniformity Wavelet_LLH_glcm_energy Wavelet_LLH_glcm_maxProb Wavelet_LLH_glcm_homogeneity2 Wavelet_LLH_glcm_homogeneity1 Wavelet_LHL_glcm_homogeneity1 Wavelet_LHL_glcm_homogeneity2 Wavelet_LHL_glcm_maxProb Wavelet_LHL_glcm_energy Wavelet_LHL_stats_uniformity Wavelet_LHL_glcm_inverseVar Wavelet_HHL_glcm_homogeneity2 Wavelet_HHL_glcm_homogeneity1 Wavelet_HHL_glcm_maxProb Wavelet_HHL_rlgl_longRunEmphasis Wavelet_HHL_glcm_energy Wavelet_HHL_stats_uniformity Wavelet_HHL_glcm_inverseVar Wavelet_HHH_stats_uniformity Wavelet_HHH_glcm_inverseVar Wavelet_HHH_glcm_energy Wavelet_HHH_glcm_homogeneity2 Wavelet_HHH_glcm_homogeneity1 Wavelet_HHH_rlgl_longRunEmphasis Wavelet_HHH_glcm_maxProb Wavelet_HHH_stats_kurtosis Wavelet_LHH_glcm_homogeneity1 Wavelet_LHH_glcm_homogeneity2 Wavelet_LHH_glcm_inverseVar Wavelet_LHH_glcm_energy Wavelet_LHH_stats_uniformity Wavelet_LHH_glcm_maxProb Wavelet_LHH_rlgl_longRunEmphasis LoG_sigma_5_mm_3D_stats_skewness LoG_sigma_4_5_mm_3D_stats_skewness LoG_sigma_4_mm_2D_stats_skewness LoG_sigma_3_5_mm_2D_stats_skewness LoG_sigma_5_mm_2D_stats_skewness LoG_sigma_4_5_mm_2D_stats_skewness LoG_sigma_0_5_mm_2D_stats_skewness LoG_sigma_1_5_mm_2D_stats_skewness LoG_sigma_1_mm_2D_stats_skewness LoG_sigma_2_mm_2D_stats_skewness LoG_sigma_3_mm_2D_stats_skewness LoG_sigma_2_5_mm_2D_stats_skewness LoG_sigma_0_5_mm_3D_stats_skewness LoG_sigma_1_5_mm_3D_stats_skewness LoG_sigma_1_mm_3D_stats_skewness LoG_sigma_2_mm_3D_stats_skewness LoG_sigma_2_5_mm_3D_stats_skewness LoG_sigma_3_mm_3D_stats_skewness LoG_sigma_4_mm_3D_stats_skewness LoG_sigma_3_5_mm_3D_stats_skewness LoG_sigma_5_mm_3D_stats_kurtosis LoG_sigma_4_5_mm_3D_stats_kurtosis LoG_sigma_5_mm_2D_stats_kurtosis LoG_sigma_4_5_mm_2D_stats_kurtosis LoG_sigma_4_mm_2D_stats_kurtosis LoG_sigma_4_mm_3D_stats_kurtosis LoG_sigma_3_5_mm_3D_stats_kurtosis LoG_sigma_3_mm_3D_stats_kurtosis LoG_sigma_2_5_mm_3D_stats_kurtosis LoG_sigma_2_mm_3D_stats_kurtosis LoG_sigma_1_mm_3D_stats_kurtosis LoG_sigma_0_5_mm_3D_stats_kurtosis LoG_sigma_1_5_mm_3D_stats_kurtosis LoG_sigma_3_5_mm_2D_stats_kurtosis LoG_sigma_3_mm_2D_stats_kurtosis LoG_sigma_2_5_mm_2D_stats_kurtosis LoG_sigma_2_mm_2D_stats_kurtosis LoG_sigma_1_mm_2D_stats_kurtosis LoG_sigma_0_5_mm_2D_stats_kurtosis LoG_sigma_1_5_mm_2D_stats_kurtosis Wavelet_LLL_stats_rms Stats_rms Wavelet_LLL_stats_mean Stats_mean RLGL_longRunHighGrayLevEmpha Wavelet_LLL_rlgl_longRunHighGrayLevEmpha RLGL_longRunEmphasis GLCM_homogeneity1 GLCM_homogeneity2 Wavelet_LLL_rlgl_longRunEmphasis Wavelet_LLL_glcm_homogeneity1 Wavelet_LLL_glcm_homogeneity2 Wavelet_LLL_stats_kurtosis Stats_kurtosis Wavelet_LLL_stats_median Stats_median Wavelet_LLL_glcm_energy GLCM_energy GLCM_maxProb Wavelet_LLL_glcm_maxProb Stats_uniformity Wavelet_LLL_stats_uniformity Wavelet_HLL_glcm_invDiffnorm Wavelet_HLL_glcm_invDiffmomnor GLCM_inverseVar Wavelet_HLL_rlgl_longRunEmphasis Wavelet_HLL_glcm_homogeneity1 Wavelet_HLL_glcm_homogeneity2 Wavelet_HLL_stats_kurtosis Wavelet_HLL_stats_uniformity Wavelet_HLL_glcm_maxProb Wavelet_HLL_glcm_energy Wavelet_LHH_rlgl_grayLevelNonuniformity Wavelet_LLH_rlgl_grayLevelNonuniformity Wavelet_LHL_rlgl_grayLevelNonuniformity Wavelet_HHL_rlgl_grayLevelNonuniformity Wavelet_HHH_rlgl_grayLevelNonuniformity Wavelet_HLH_rlgl_grayLevelNonuniformity Shape_compactness Wavelet_HLL_rlgl_runLengthNonuniformity Shape_volume Shape_surface RLGL_grayLevelNonuniformity Wavelet_LLL_rlgl_grayLevelNonuniformity Wavelet_HLL_rlgl_grayLevelNonuniformity Wavelet_LHH_rlgl_runLengthNonuniformity Wavelet_HHH_rlgl_runLengthNonuniformity Stats_energy Stats_totalenergy Wavelet_LLL_stats_energy Wavelet_LLL_stats_totalenergy Wavelet_HLL_stats_energy Wavelet_HLL_stats_totalenergy Shape_maxDiameter3D Shape_maxDiameter3D_pdist Shape_maxDiameter2Dy Shape_maxDiameter2Dx Wavelet_LHL_stats_energy Wavelet_LHL_stats_totalenergy Wavelet_LHH_stats_energy Wavelet_LHH_stats_totalenergy Wavelet_HLL_rlgl_longRunHighGrayLevEmpha Shape_voxelNum RLGL_runLengthNonuniformity Wavelet_LLL_rlgl_runLengthNonuniformity Shape_maxDiameter2Dz Wavelet_HLH_rlgl_runLengthNonuniformity Wavelet_HHL_rlgl_runLengthNonuniformity Wavelet_LLH_rlgl_runLengthNonuniformity Wavelet_LHL_rlgl_runLengthNonuniformity Wavelet_HLH_glcm_autocorr Wavelet_HLH_glcm_sumAvg Wavelet_HLH_glcm_sumSquares Wavelet_HLH_glcm_sumVar Wavelet_HLH_rlgl_highGrayLevelRunEmphasis Wavelet_HHL_glcm_sumVar Wavelet_HHL_glcm_sumAvg Wavelet_HHL_rlgl_highGrayLevelRunEmphasis Wavelet_HHL_glcm_sumSquares Wavelet_HHL_glcm_autocorr Wavelet_LLL_stats_range Stats_range GLSZM_highIntensityEmphasis Wavelet_HLH_rlgl_shortRunHighGrayLevEmpha Wavelet_HHL_rlgl_shortRunHighGrayLevEmpha Wavelet_LHH_rlgl_shortRunHighGrayLevEmpha Wavelet_LHH_glcm_sumSquares Wavelet_LHH_rlgl_highGrayLevelRunEmphasis Wavelet_LHH_glcm_sumVar Wavelet_LHH_glcm_sumAvg Wavelet_LHH_glcm_autocorr GLSZM_sizeZoneVariability Wavelet_LHH_stats_max GLSZM_highIntensitySmallAreaEmp Wavelet_LHH_stats_range Wavelet_LLH_stats_range GLCM_autocorr GLCM_sumSquares GLCM_sumAvg RLGL_highGrayLevelRunEmphasis GLCM_sumVar Wavelet_LLL_rlgl_highGrayLevelRunEmphasis Wavelet_LLL_glcm_sumAvg Wavelet_LLL_glcm_sumVar Wavelet_LLL_glcm_autocorr Wavelet_LLL_glcm_sumSquares Wavelet_LHL_stats_max Wavelet_LHL_stats_range Wavelet_HHH_rlgl_longRunHighGrayLevEmpha Wavelet_LHL_rlgl_longRunHighGrayLevEmpha Wavelet_LLL_rlgl_shortRunHighGrayLevEmpha RLGL_shortRunHighGrayLevEmpha Wavelet_LLH_stats_max Wavelet_LLH_stats_energy Wavelet_LLH_stats_totalenergy Wavelet_LLL_stats_max Stats_max Wavelet_LLH_stats_median Wavelet_LHL_stats_median Wavelet_LLH_stats_mean Wavelet_LHL_stats_mean Wavelet_HLL_stats_mean Wavelet_HLL_stats_median Wavelet_LLL_glcm_clusProm GLCM_clusProm Wavelet_LLL_glcm_correl1 GLCM_correl1 Wavelet_HLL_glcm_sumAvg Wavelet_HLL_rlgl_highGrayLevelRunEmphasis Wavelet_HLL_glcm_sumSquares Wavelet_HLL_glcm_autocorr Wavelet_HLL_glcm_sumVar Wavelet_LHL_glcm_clusShade Wavelet_HLL_rlgl_longRunLowGrayLevEmpha Wavelet_HHH_stats_median Wavelet_HHH_stats_mean Wavelet_HHL_stats_skewness Wavelet_LHL_glcm_correl1 Wavelet_LLH_glcm_correl1 Wavelet_HHH_rlgl_shortRunHighGrayLevEmpha Wavelet_HHH_rlgl_highGrayLevelRunEmphasis Wavelet_HHH_glcm_sumSquares Wavelet_HHH_glcm_autocorr Wavelet_HHH_glcm_sumVar Wavelet_HHH_glcm_sumAvg Wavelet_LHL_rlgl_highGrayLevelRunEmphasis Wavelet_LHL_glcm_sumSquares Wavelet_LHL_glcm_sumVar Wavelet_LHL_glcm_autocorr Wavelet_LHL_glcm_sumAvg Wavelet_LLH_rlgl_highGrayLevelRunEmphasis Wavelet_LLH_glcm_sumSquares Wavelet_LLH_glcm_sumVar Wavelet_LLH_glcm_sumAvg Wavelet_LLH_glcm_autocorr Wavelet_HLL_rlgl_shortRunHighGrayLevEmpha Wavelet_LLH_rlgl_shortRunHighGrayLevEmpha Wavelet_LHL_rlgl_shortRunHighGrayLevEmpha Shape_spherDisprop Wavelet_LLL_glcm_inverseVar Wavelet_HLL_glcm_inverseVar Wavelet_HHL_glcm_infoCorr1 Wavelet_HLH_glcm_infoCorr1 Wavelet_LHL_glcm_infoCorr1 Wavelet_HHH_glcm_correl1 Wavelet_LHH_glcm_correl1 Wavelet_HHH_glcm_clusShade Wavelet_HHH_stats_skewness Wavelet_HLL_stats_skewness Wavelet_HLL_glcm_clusShade GLSZM_smallAreaEmphasis Wavelet_HLH_glcm_clusShade Wavelet_HLH_stats_skewness GLSZM_lowIntensityLargeAreaEmp GLSZM_largeAreaEmphasis GLSZM_highIntensityLarteAreaEmp Wavelet_HHH_glcm_infoCorr1 Wavelet_LHH_glcm_infoCorr1 Wavelet_HLH_stats_energy Wavelet_HLH_stats_totalenergy Wavelet_HHL_stats_energy Wavelet_HHL_stats_totalenergy Wavelet_HHH_stats_energy Wavelet_HHH_stats_totalenergy Wavelet_HHL_stats_range Wavelet_HHL_stats_max Wavelet_HHH_stats_range Wavelet_HHH_stats_max Wavelet_HLL_stats_max Wavelet_HLL_stats_range Wavelet_HLH_stats_range Wavelet_HLH_stats_max (A) Radiomic Features Strong correlation between Radiomic data and Molecular Pathways 11

12 Prognostic Power (Concordance Index) Radiomics-Genomics association modules 13 association modules were identified and independently validated Radiomics Modules associate with distinct biological processes Modules are significantly associated with clinical parameters: survival (3), histology (5), stage (10) Clinical-Radiomics-Genomics Prognostic Signatures Genomic Signature: Hou et al., genes for Post-treatment survival Radiomics Signature: Aerts et al., 2014 (I) Statistics Energy (II) Shape Compactness (III) Grey Level Nonuniformity (IV) Wavelet Grey Level Nonuniformity HLH Radiomics significantly adds to prognostic gene-signatures Imaging-Genomics in GBM 12

13 Methods: Manual delineations A B Manual slice-by-slice contouring of the abnormal signal on T1c and FLAIR images C Necrosis Contrast Enhancement Edema Tumor Bulk Tutal Total Tumor Volume FAST algorithm to segment contrast-enhancing and necrotic sub-volumes on T1c Final contours were all manually reviewed and edited by expert neuro-radiologists PAGE 37 *Grossmann et al. Submitted Prognostic value of volumetric features *Grossmann et al. Submitted Imaging-Genomics Pathway Analysis of MRI Derived Volumetric Tumor Phenotype Features in Glioblastoma n=96 GBM patients from TCGA-GBM cohort 13

14 Volumetric features predict mutational status in GBM patients N=76 GBM patients from TCGA-GBM cohort *Gutman et al. Submitted TP53 positive/negative TP53 mutated tumors had significantly smaller CE and necrotic volumes (p=0.012 and 0.017, respectively) compared to wild-type. *Gutman et al. Submitted Quantitative Imaging: Current Status & Outlook - Imaging moves towards a computational data science (bioinformatics) - Due to advances in imaging, quantitative imaging is currently possible - Large retrospective and prospective potential - Large number of imaging features defined & successfully implemented - Robust feature extraction pipeline implemented in 3D-Slicer (Python / Matlab) - Radiomics signatures are prognostic across cancer types - Radiomics data is strongly association with driving biological processes - Ongoing: Delta radiomics change of image features - Ongoing: Preclinical models with tumor models having inducible KO - Ongoing: Radiomics in clinical trial data 14

15 Take home message The field of Forensic Bioinformatics (Keith Baggerly, MD Anderson) Investigating the reproducibility and methodology of scientific studies in retrospect. They request the data from the investigators, they assess the used statistics, methods, results, and conclusions. They find a large number of studies that are wrong or even fraud Duke Scandal (Anil Potti) Accused of falsifying data regarding the use of microarray genetic analysis for personalized cancer treatment. Publications in various prestigious scientific journals were retracted (including PNAS, Lancet Oncology, Nature Medicine, JAMA, JCO, NEJM). Forensic Radiology Forensic Radiology 15

Quantitative Radiomics System: Decoding the Tumor Phenotype

Quantitative Radiomics System: Decoding the Tumor Phenotype HARVARD MEDICAL SCHOOL Quantitative Radiomics System: Decoding the Tumor Phenotype Hugo Aerts Director, Computational Imaging and Bioinformatics Lab (CIBL) Dana-Farber Cancer Institute, Brigham and Women

More information

Quantitative Radiomics System Decoding the Tumor Phenotype. John Quackenbush and Hugo Aerts

Quantitative Radiomics System Decoding the Tumor Phenotype. John Quackenbush and Hugo Aerts Quantitative Radiomics System Decoding the Tumor Phenotype John Quackenbush and Hugo Aerts The Radiomics Hypothesis The tumor s structural phenotype reflects its molecular and clinical properties. This

More information

8/1/2017. Imaging and Molecular Biomarkers of Lung Cancer Prognosis. Disclosures. The Era of Precision Oncology

8/1/2017. Imaging and Molecular Biomarkers of Lung Cancer Prognosis. Disclosures. The Era of Precision Oncology Imaging and Molecular Biomarkers of Lung Cancer Prognosis Ruijiang Li, PhD Assistant Professor of Radiation Oncology 08/01/2017 Stanford University Department of Radiation Oncology School of Medicine Disclosures

More information

Radiomics: a new era for tumour management?

Radiomics: a new era for tumour management? Radiomics: a new era for tumour management? Irène Buvat Unité Imagerie Moléculaire In Vivo (IMIV) CEA Service Hospitalier Frédéric Joliot Orsay, France irene.buvat@u-psud.fr http://www.guillemet.org/irene

More information

Objectives. Image analysis and Informatics. Cancer is not being cured. The bad news. One of the problems

Objectives. Image analysis and Informatics. Cancer is not being cured. The bad news. One of the problems Image analysis and Informatics Robert J. Gillies, Dept. Radiology H. Lee Moffitt Cancer Center Tampa, FLORIDA Objectives Describe the motivation underlying analyses of tumor heterogeneity Describe the

More information

Machine Learning methods for Quantitative Radiomic Biomarkers

Machine Learning methods for Quantitative Radiomic Biomarkers Machine Learning methods for Quantitative Radiomic Biomarkers The Harvard community has made this article openly available. Please share how this access benefits you. Your story matters Citation Parmar,

More information

8/1/2018. Radiomics Certificate, AAPM Radiomics Certificate, AAPM Introduction to Radiomics

8/1/2018. Radiomics Certificate, AAPM Radiomics Certificate, AAPM Introduction to Radiomics Radiomics Certificate, AAPM 2018 Directors Ahmed Hosny, Hugo Aerts, Dana-Farber Cancer Center Laurence Court, University of Texas MD Anderson Cancer Center Faculty Xenia Fave, University of California

More information

Fully automatic GBM segmentation in the TCGA-GBM dataset: Prognosis and correlation with VASARI features

Fully automatic GBM segmentation in the TCGA-GBM dataset: Prognosis and correlation with VASARI features Fully automatic GBM segmentation in the TCGA-GBM dataset: Prognosis and correlation with VASARI features Hugo J.W.L. Aerts, Harvard University Emmanuel Rios Velazquez, Harvard University Raphael Meier,

More information

8/10/2016. PET/CT Radiomics for Tumor. Anatomic Tumor Response Assessment in CT or MRI. Metabolic Tumor Response Assessment in FDG-PET

8/10/2016. PET/CT Radiomics for Tumor. Anatomic Tumor Response Assessment in CT or MRI. Metabolic Tumor Response Assessment in FDG-PET PET/CT Radiomics for Tumor Response Evaluation August 1, 2016 Wei Lu, PhD Department of Medical Physics www.mskcc.org Department of Radiation Oncology www.umaryland.edu Anatomic Tumor Response Assessment

More information

Radiomics for outcome modeling: state-of-the-art and challenges

Radiomics for outcome modeling: state-of-the-art and challenges Workshop Avancées récentes en analyse d images médicales multi-modales Radiomics for outcome modeling: state-of-the-art and challenges Mathieu Hatt, PhD, HDR CR INSERM mathieu.hatt@inserm.fr Laboratoire

More information

CaPTk: Cancer Imaging Phenomics Toolkit

CaPTk: Cancer Imaging Phenomics Toolkit CaPTk: Cancer Imaging Phenomics Toolkit Interaction Personalized Diagnostics CaPTk Quantitative Imaging Phenomic Features Radiogenomics Image Analysis Machine Learning What is CaPTk? A dynamically growing

More information

Reproducibility of radiomic features with GrowCut and GraphCut semiautomatic tumor segmentation in hepatocellular carcinoma

Reproducibility of radiomic features with GrowCut and GraphCut semiautomatic tumor segmentation in hepatocellular carcinoma Original Article Reproducibility of radiomic features with GrowCut and GraphCut semiautomatic tumor segmentation in hepatocellular carcinoma Qingtao Qiu 1,2 *, Jinghao Duan 2 *, Guanzhong Gong 2, Yukun

More information

for the TCGA Breast Phenotype Research Group

for the TCGA Breast Phenotype Research Group Decoding Breast Cancer with Quantitative Radiomics & Radiogenomics: Imaging Phenotypes in Breast Cancer Risk Assessment, Diagnosis, Prognosis, and Response to Therapy Maryellen Giger & Yuan Ji The University

More information

MR-Radiomics in Neuro-Oncology

MR-Radiomics in Neuro-Oncology Klinik für Stereotaxie und funktionelle Neurochirurgie Institut für Neurowissenschaften und Medizin MR-Radiomics in Neuro-Oncology M. Kocher Klinik für funktionelle Neurochirurgie und Stereotaxie Forschungszentrum

More information

arxiv: v1 [cs.cv] 24 Mar 2017

arxiv: v1 [cs.cv] 24 Mar 2017 arxiv:73.856v [cs.cv] 24 Mar 27 Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer MartinVallières,, Emily Kay-Rivest 2,Léo Jean Perrin 3, Xavier Liem 4, Christophe Furstoss

More information

Oncology - Evolution of imaging From helpful to essential

Oncology - Evolution of imaging From helpful to essential Oncology - Evolution of imaging From helpful to essential 1990s 2000 1980s 18 FDG PET/CT MRI/MRSI 2010 1970s MRI 1960s CT 2015 HP13C-MRSI Ultrasound Nuc Med X-Ray - IVU MRI/PET Imaging 2016: Essential

More information

SUPPLEMENTARY INFORMATION

SUPPLEMENTARY INFORMATION doi:10.1038/nature10866 a b 1 2 3 4 5 6 7 Match No Match 1 2 3 4 5 6 7 Turcan et al. Supplementary Fig.1 Concepts mapping H3K27 targets in EF CBX8 targets in EF H3K27 targets in ES SUZ12 targets in ES

More information

Repeatability and reproducibility of 18 F-NaF PET quantitative imaging biomarkers

Repeatability and reproducibility of 18 F-NaF PET quantitative imaging biomarkers Repeatability and reproducibility of 18 F-NaF PET quantitative imaging biomarkers Christie Lin, Tyler Bradshaw, Timothy Perk, Stephanie Harmon, Glenn Liu, Robert Jeraj University of Wisconsin Madison,

More information

Radiomics - research challenges identified by EURAMED

Radiomics - research challenges identified by EURAMED Radiomics - research challenges identified by EURAMED Prof. Christoph Hoeschen EURAMED Past-President, member of ExB, head of scientific committee www.euramed.eu Vision To lead the European research activities

More information

CT texture analysis of lung adenocarcinoma: can Radiomic features be surrogate biomarkers for EGFR mutation statuses

CT texture analysis of lung adenocarcinoma: can Radiomic features be surrogate biomarkers for EGFR mutation statuses Mei et al. Cancer Imaging (2018) 18:52 https://doi.org/10.1186/s40644-018-0184-2 REGULAR ARTICLE Open Access CT texture analysis of lung adenocarcinoma: can Radiomic features be surrogate biomarkers for

More information

MRI-Based Biomarkers of Therapeutic Response in Triple-Negative Breast Cancer

MRI-Based Biomarkers of Therapeutic Response in Triple-Negative Breast Cancer MRI-Based Biomarkers of Therapeutic Response in Triple-Negative Breast Cancer Daniel Golden Postdoctoral Scholar (Radiology) Stanford University Daniel Rubin Laboratory NCI Cancer Imaging Fellowship Seminar

More information

Computer based delineation and follow-up multisite abdominal tumors in longitudinal CT studies

Computer based delineation and follow-up multisite abdominal tumors in longitudinal CT studies Research plan submitted for approval as a PhD thesis Submitted by: Refael Vivanti Supervisor: Professor Leo Joskowicz School of Engineering and Computer Science, The Hebrew University of Jerusalem Computer

More information

Improved Intelligent Classification Technique Based On Support Vector Machines

Improved Intelligent Classification Technique Based On Support Vector Machines Improved Intelligent Classification Technique Based On Support Vector Machines V.Vani Asst.Professor,Department of Computer Science,JJ College of Arts and Science,Pudukkottai. Abstract:An abnormal growth

More information

The 16th KJC Bioinformatics Symposium Integrative analysis identifies potential DNA methylation biomarkers for pan-cancer diagnosis and prognosis

The 16th KJC Bioinformatics Symposium Integrative analysis identifies potential DNA methylation biomarkers for pan-cancer diagnosis and prognosis The 16th KJC Bioinformatics Symposium Integrative analysis identifies potential DNA methylation biomarkers for pan-cancer diagnosis and prognosis Tieliu Shi tlshi@bio.ecnu.edu.cn The Center for bioinformatics

More information

An Introduction to Radiomics: Capturing Tumour Biology in Space and Time

An Introduction to Radiomics: Capturing Tumour Biology in Space and Time Oncologic Imaging Review An Introduction to Radiomics: Capturing Tumour Biology in Space and Time Nickolas Papanikolaou, Joao Santinha Computational Clinical Imaging Group, Champalimaud Foundation, Centre

More information

This copy is for personal use only. To order printed copies, contact

This copy is for personal use only. To order printed copies, contact This copy is for personal use only. To order printed copies, contact reprints@rsna.org Jia Wu, PhD Todd Aguilera, MD, PhD David Shultz, MD, PhD Madhu Gudur, PhD Daniel L. Rubin, MD, MS Billy W. Loo, Jr,

More information

Somatic Mutations Drive Distinct Imaging Phenotypes in Lung Cancer

Somatic Mutations Drive Distinct Imaging Phenotypes in Lung Cancer Integrated Systems and Technologies Cancer Research Somatic Mutations Drive Distinct Imaging Phenotypes in Lung Cancer Emmanuel Rios Velazquez 1, Chintan Parmar 1, Ying Liu 2,3, Thibaud P. Coroller 1,

More information

Assessing the prognostic impact of 3D CT image tumour rind texture features on lung cancer survival

Assessing the prognostic impact of 3D CT image tumour rind texture features on lung cancer survival University of Wollongong Research Online Faculty of Engineering and Information Sciences - Papers: Part B Faculty of Engineering and Information Sciences 27 Assessing the prognostic impact of 3D CT image

More information

Radiomics: Extracting more information from medical images using advanced feature analysis

Radiomics: Extracting more information from medical images using advanced feature analysis European Journal of Cancer (2012) 48, 441 446 Available at www.sciencedirect.com journal homepage: www.ejconline.com Radiomics: Extracting more information from medical images using advanced feature analysis

More information

Radiomics of pulmonary nodules and lung cancer

Radiomics of pulmonary nodules and lung cancer Mini-Review Radiomics of pulmonary nodules and lung cancer Ryan Wilson, Anand Devaraj Royal Brompton Hospital, London, SW3 6NP, UK Contributions: (I) Conception and design: All authors; (II) Administrative

More information

Characterization of lung metastasis based on radiomics features: issues related to acquisition parameters and to lesion segmentation

Characterization of lung metastasis based on radiomics features: issues related to acquisition parameters and to lesion segmentation Characterization of lung metastasis based on radiomics features: issues related to acquisition parameters and to lesion segmentation Authors: F. Ambrogi 2, P. E. Colombo 1-2, C. De Mattia 1-2, D. Lizio

More information

Expanded View Figures

Expanded View Figures EMO Molecular Medicine Proteomic map of squamous cell carcinomas Hanibal ohnenberger et al Expanded View Figures Figure EV1. Technical reproducibility. Pearson s correlation analysis of normalised SILC

More information

Breast cancer classification: beyond the intrinsic molecular subtypes

Breast cancer classification: beyond the intrinsic molecular subtypes Breast cancer classification: beyond the intrinsic molecular subtypes Britta Weigelt, PhD Signal Transduction Laboratory CRUK London Research Institute Summary Breast cancer heterogeneity Molecular classification

More information

CHAPTER 9 SUMMARY AND CONCLUSION

CHAPTER 9 SUMMARY AND CONCLUSION CHAPTER 9 SUMMARY AND CONCLUSION 9.1 SUMMARY In this thesis, the CAD system for early detection and classification of ischemic stroke in CT image, hemorrhage and hematoma in brain CT image and brain tumor

More information

COMPARATIVE STUDY ON FEATURE EXTRACTION METHOD FOR BREAST CANCER CLASSIFICATION

COMPARATIVE STUDY ON FEATURE EXTRACTION METHOD FOR BREAST CANCER CLASSIFICATION COMPARATIVE STUDY ON FEATURE EXTRACTION METHOD FOR BREAST CANCER CLASSIFICATION 1 R.NITHYA, 2 B.SANTHI 1 Asstt Prof., School of Computing, SASTRA University, Thanjavur, Tamilnadu, India-613402 2 Prof.,

More information

TECHNICAL, SCIENTIFIC

TECHNICAL, SCIENTIFIC SPECIAL ISSUE TECHNICAL, SCIENTIFIC AND RESEARCH REPORTS VOL.9 (2017) Prostate cancer Radiomics using multiparametric MR imaging TSRR IFAC-TSRR vol. 9 (2017) 1-51 Prostate cancer Radiomics using multiparametric

More information

Interobserver variation in cervical cancer tumor delineation for image-based radiotherapy planning among and within different specialties

Interobserver variation in cervical cancer tumor delineation for image-based radiotherapy planning among and within different specialties JOURNAL OF APPLIED CLINICAL MEDICAL PHYSICS, VOLUME 6, NUMBER 4, FALL 2005 Interobserver variation in cervical cancer tumor delineation for image-based radiotherapy planning among and within different

More information

Institute of Oncology & Radiobiology. Havana, Cuba. INOR

Institute of Oncology & Radiobiology. Havana, Cuba. INOR Institute of Oncology & Radiobiology. Havana, Cuba. INOR 1 Transition from 2-D 2 D to 3-D 3 D conformal radiotherapy in high grade gliomas: : our experience in Cuba Chon. I, MD - Chi. D, MD - Alert.J,

More information

POC Brain Tumor Segmentation. vlife Use Case

POC Brain Tumor Segmentation. vlife Use Case Brain Tumor Segmentation vlife Use Case 1 Automatic Brain Tumor Segmentation using CNN Background Brain tumor segmentation seeks to separate healthy tissue from tumorous regions such as the advancing tumor,

More information

Early Detection of Lung Cancer

Early Detection of Lung Cancer Early Detection of Lung Cancer Aswathy N Iyer Dept Of Electronics And Communication Engineering Lymie Jose Dept Of Electronics And Communication Engineering Anumol Thomas Dept Of Electronics And Communication

More information

Confidence-based Ensemble for GBM brain tumor segmentation

Confidence-based Ensemble for GBM brain tumor segmentation Confidence-based Ensemble for GBM brain tumor segmentation Jing Huo 1, Eva M. van Rikxoort 1, Kazunori Okada 2, Hyun J. Kim 1, Whitney Pope 1, Jonathan Goldin 1, Matthew Brown 1 1 Center for Computer vision

More information

Outcomes in the NLST. Health system infrastructure needs to implement screening

Outcomes in the NLST. Health system infrastructure needs to implement screening Outcomes in the NLST Health system infrastructure needs to implement screening Denise R. Aberle, MD Professor of Radiology and Bioengineering David Geffen School of Medicine at UCLA 1 Disclosures I have

More information

Texture analysis in Medical Imaging: Applications in Cancer

Texture analysis in Medical Imaging: Applications in Cancer Texture analysis in Medical Imaging: in Cancer Angel Alberich-Bayarri, PhD alberich_ang@gva.es angel@quibim.com 1 Biomedical Imaging Research Group (GIBI230) La Fe Polytechnics and University Hospital

More information

Differentiating Tumor and Edema in Brain Magnetic Resonance Images Using a Convolutional Neural Network

Differentiating Tumor and Edema in Brain Magnetic Resonance Images Using a Convolutional Neural Network Original Article Differentiating Tumor and Edema in Brain Magnetic Resonance Images Using a Convolutional Neural Network Aida Allahverdi 1, Siavash Akbarzadeh 1, Alireza Khorrami Moghaddam 2, Armin Allahverdy

More information

Segmentation of Tumor Region from Brain Mri Images Using Fuzzy C-Means Clustering And Seeded Region Growing

Segmentation of Tumor Region from Brain Mri Images Using Fuzzy C-Means Clustering And Seeded Region Growing IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 18, Issue 5, Ver. I (Sept - Oct. 2016), PP 20-24 www.iosrjournals.org Segmentation of Tumor Region from Brain

More information

ASU-Mayo Clinic Imaging Informatics Laboratory (AMIIL)

ASU-Mayo Clinic Imaging Informatics Laboratory (AMIIL) ASU-Mayo Clinic Imaging Informatics Laboratory (AMIIL) 1 ASU-Mayo Clinic Imaging Informatics Laboratory (AMIIL) http://amiil.engineering.asu.edu/ Focus Area I: Imaging-centered data analytics for better

More information

Brain Tumour Detection of MR Image Using Naïve Beyer classifier and Support Vector Machine

Brain Tumour Detection of MR Image Using Naïve Beyer classifier and Support Vector Machine International Journal of Scientific Research in Computer Science, Engineering and Information Technology 2018 IJSRCSEIT Volume 3 Issue 3 ISSN : 2456-3307 Brain Tumour Detection of MR Image Using Naïve

More information

Patient characteristics of training and validation set. Patient selection and inclusion overview can be found in Supp Data 9. Training set (103)

Patient characteristics of training and validation set. Patient selection and inclusion overview can be found in Supp Data 9. Training set (103) Roepman P, et al. An immune response enriched 72-gene prognostic profile for early stage Non-Small- Supplementary Data 1. Patient characteristics of training and validation set. Patient selection and inclusion

More information

MEM BASED BRAIN IMAGE SEGMENTATION AND CLASSIFICATION USING SVM

MEM BASED BRAIN IMAGE SEGMENTATION AND CLASSIFICATION USING SVM MEM BASED BRAIN IMAGE SEGMENTATION AND CLASSIFICATION USING SVM T. Deepa 1, R. Muthalagu 1 and K. Chitra 2 1 Department of Electronics and Communication Engineering, Prathyusha Institute of Technology

More information

Diagnosis of Liver Tumor Using 3D Segmentation Method for Selective Internal Radiation Therapy

Diagnosis of Liver Tumor Using 3D Segmentation Method for Selective Internal Radiation Therapy Diagnosis of Liver Tumor Using 3D Segmentation Method for Selective Internal Radiation Therapy K. Geetha & S. Poonguzhali Department of Electronics and Communication Engineering, Campus of CEG Anna University,

More information

Knowledge Discovery and Predictive Modeling from Brain Tumor MRIs

Knowledge Discovery and Predictive Modeling from Brain Tumor MRIs University of South Florida Scholar Commons Graduate Theses and Dissertations Graduate School September 2015 Knowledge Discovery and Predictive Modeling from Brain Tumor MRIs Mu Zhou University of South

More information

Applying Tissue Phenomics to Colorectal Clinical Questions

Applying Tissue Phenomics to Colorectal Clinical Questions Applying Tissue Phenomics to Colorectal Clinical Questions International Symposium for Tissue Phenomics San Francisco October 2014 Peter Caie Senior Research Fellow University of St Andrews Systems Pathology

More information

Predicting Non-Small Cell Lung Cancer Diagnosis and Prognosis by Fully Automated Microscopic Pathology Image Features

Predicting Non-Small Cell Lung Cancer Diagnosis and Prognosis by Fully Automated Microscopic Pathology Image Features Predicting Non-Small Cell Lung Cancer Diagnosis and Prognosis by Fully Automated Microscopic Pathology Image Features Kun-Hsing Yu, MD, PhD Department of Biomedical Informatics, Harvard Medical School

More information

From single studies to an EBM based assessment some central issues

From single studies to an EBM based assessment some central issues From single studies to an EBM based assessment some central issues Doug Altman Centre for Statistics in Medicine, Oxford, UK Prognosis Prognosis commonly relates to the probability or risk of an individual

More information

NGS in Cancer Pathology After the Microscope: From Nucleic Acid to Interpretation

NGS in Cancer Pathology After the Microscope: From Nucleic Acid to Interpretation NGS in Cancer Pathology After the Microscope: From Nucleic Acid to Interpretation Michael R. Rossi, PhD, FACMG Assistant Professor Division of Cancer Biology, Department of Radiation Oncology Department

More information

A New Approach For an Improved Multiple Brain Lesion Segmentation

A New Approach For an Improved Multiple Brain Lesion Segmentation A New Approach For an Improved Multiple Brain Lesion Segmentation Prof. Shanthi Mahesh 1, Karthik Bharadwaj N 2, Suhas A Bhyratae 3, Karthik Raju V 4, Karthik M N 5 Department of ISE, Atria Institute of

More information

GBM heterogeneity characterization by radiomic analysis of phenotype anatomical planes

GBM heterogeneity characterization by radiomic analysis of phenotype anatomical planes GBM heterogeneity characterization by radiomic analysis of phenotype anatomical planes Ahmad Chaddad *, Christian Desrosiers, Matthew Toews Laboratory for Imagery, Vision and Artificial Intelligence, Ecole

More information

Clinical Trials for Adult Brain Tumors - the Imaging Perspective

Clinical Trials for Adult Brain Tumors - the Imaging Perspective Clinical Trials for Adult Brain Tumors - the Imaging Perspective Whitney B. Pope, M.D., Ph.D. Department of Radiology David Geffen School of Medicine at UCLA August 22, 2015 1 Disclosure of Financial Relationships

More information

Cancer Cells Detection using OTSU Threshold Algorithm

Cancer Cells Detection using OTSU Threshold Algorithm Cancer Cells Detection using OTSU Threshold Algorithm Nalluri Sunny 1 Velagapudi Ramakrishna Siddhartha Engineering College Mithinti Srikanth 2 Velagapudi Ramakrishna Siddhartha Engineering College Kodali

More information

Classification of Benign and Malignant Vertebral Compression Fractures in Magnetic Resonance Images

Classification of Benign and Malignant Vertebral Compression Fractures in Magnetic Resonance Images Classification of Benign and Malignant Vertebral Compression Fractures in Magnetic Resonance Images Lucas Frighetto-Pereira, Guilherme Augusto Metzner, Paulo Mazzoncini de Azevedo-Marques, Rangaraj Mandayam

More information

Brain Tumor segmentation and classification using Fcm and support vector machine

Brain Tumor segmentation and classification using Fcm and support vector machine Brain Tumor segmentation and classification using Fcm and support vector machine Gaurav Gupta 1, Vinay singh 2 1 PG student,m.tech Electronics and Communication,Department of Electronics, Galgotia College

More information

Precision of pre-sirt predictive dosimetry

Precision of pre-sirt predictive dosimetry International Course on THERANOSTICS AND MOLECULAR RADIOTHERAPY Precision of pre-sirt predictive dosimetry Hugo Levillain Department of Nuclear Medicine Medical Physics Jules Bordet Institute, Université

More information

Cover Page. The handle holds various files of this Leiden University dissertation

Cover Page. The handle   holds various files of this Leiden University dissertation Cover Page The handle http://hdl.handle.net/1887/26921 holds various files of this Leiden University dissertation Author: Doan, Nhat Trung Title: Quantitative analysis of human brain MR images at ultrahigh

More information

Nature Methods: doi: /nmeth.3115

Nature Methods: doi: /nmeth.3115 Supplementary Figure 1 Analysis of DNA methylation in a cancer cohort based on Infinium 450K data. RnBeads was used to rediscover a clinically distinct subgroup of glioblastoma patients characterized by

More information

ABSTRACT. Identifying and Predicting Molecular Signatures in Glioblastoma Using Imaging-Derived. Phenotypic Traits. Dalu Yang

ABSTRACT. Identifying and Predicting Molecular Signatures in Glioblastoma Using Imaging-Derived. Phenotypic Traits. Dalu Yang ABSTRACT Identifying and Predicting Molecular Signatures in Glioblastoma Using Imaging-Derived Phenotypic Traits by Dalu Yang This thesis addresses the relationship between molecular status of glioblastoma

More information

HEALTHCARE AI DEVELOPMENT CYCLE

HEALTHCARE AI DEVELOPMENT CYCLE Dr. Keith Dreyer Chief Science Officer, ACR Data Science Institute ACR Board of Chancellors, Chairman Informatics Commission Chief Data Science Officer, MGH, BWH, Partners Healthcare Associate Professor

More information

Identification and Verification of Translational Biomarkers for Patient Stratification and Precision Medicine

Identification and Verification of Translational Biomarkers for Patient Stratification and Precision Medicine Biomarkers for Patients Stratification and Precision Medicine -- Cancer and Beyond AAPS National Biotechnology Conference, Boston on May 16-18, 2016 Identification and Verification of Translational Biomarkers

More information

High-fidelity Imaging Response Detection in Multiple Sclerosis

High-fidelity Imaging Response Detection in Multiple Sclerosis High-fidelity Imaging Response Detection in Multiple Sclerosis Dr Baris Kanber, Translational Imaging Group, Centre for Medical Image Computing, Department of Medical Physics and Biomedical Engineering,

More information

Assessment of Adipose Tissue from Whole Body 3T MRI Scans

Assessment of Adipose Tissue from Whole Body 3T MRI Scans Assessment of Adipose Tissue from Whole Body 3T MRI Scans Ting Song 1, Jing An 2, Qun Chen 2, Vivian Lee 2, Andrew Laine 1 1 Department of Biomedical Engineering, Columbia University, New York, NY, USA

More information

Digitizing the Proteomes From Big Tissue Biobanks

Digitizing the Proteomes From Big Tissue Biobanks Digitizing the Proteomes From Big Tissue Biobanks Analyzing 24 Proteomes Per Day by Microflow SWATH Acquisition and Spectronaut Pulsar Analysis Jan Muntel 1, Nick Morrice 2, Roland M. Bruderer 1, Lukas

More information

Combined Radiology and Pathology Classification of Brain Tumors

Combined Radiology and Pathology Classification of Brain Tumors Combined Radiology and Pathology Classification of Brain Tumors Rozpoznanie guza mózgu na podstawie obrazu radiologicznego i patologicznego Piotr Giedziun Supervisor: dr hab. inż. Henryk Maciejewski 4

More information

Optimization of Functional MRI Techniques for Tumor and Normal Tissue Response to RT

Optimization of Functional MRI Techniques for Tumor and Normal Tissue Response to RT Optimization of Functional MRI Techniques for Tumor and Normal Tissue Response to RT Yue Cao, Ph.D. Departments of Radiation Oncology, Radiology and Biomedical Engineering University of Michigan 1 Acknowledgments

More information

Computer-extracted MR imaging features are associated with survival in glioblastoma patients

Computer-extracted MR imaging features are associated with survival in glioblastoma patients Computer-extracted MR imaging features are associated with survival in glioblastoma patients Maciej A. Mazurowski, Ph.D. 1, Jing Zhang, Ph.D. 1, Katherine B. Peters, M.D., Ph.D. 2, Hasan Hobbs, M.D. 1

More information

ANALYSIS AND DETECTION OF BRAIN TUMOUR USING IMAGE PROCESSING TECHNIQUES

ANALYSIS AND DETECTION OF BRAIN TUMOUR USING IMAGE PROCESSING TECHNIQUES ANALYSIS AND DETECTION OF BRAIN TUMOUR USING IMAGE PROCESSING TECHNIQUES P.V.Rohini 1, Dr.M.Pushparani 2 1 M.Phil Scholar, Department of Computer Science, Mother Teresa women s university, (India) 2 Professor

More information

International Journal Of Advanced Research In ISSN: Engineering Technology & Sciences

International Journal Of Advanced Research In ISSN: Engineering Technology & Sciences International Journal Of Advanced Research In Engineering Technology & Sciences Email: editor@ijarets.org June- 2015 Volume 2, Issue-6 www.ijarets.org A Review Paper on Machine Learing Techniques And Anlaysis

More information

Data Sharing Consortiums and Large Datasets to Inform Cancer Diagnosis

Data Sharing Consortiums and Large Datasets to Inform Cancer Diagnosis February, 13th 2018 Data Sharing Consortiums and Large Datasets to Inform Cancer Diagnosis Improving Cancer Diagnosis and Care: Patient Access to Oncologic Imaging and Pathology Expertise and Technologies:

More information

Nature Getetics: doi: /ng.3471

Nature Getetics: doi: /ng.3471 Supplementary Figure 1 Summary of exome sequencing data. ( a ) Exome tumor normal sample sizes for bladder cancer (BLCA), breast cancer (BRCA), carcinoid (CARC), chronic lymphocytic leukemia (CLLX), colorectal

More information

EARLY STAGE DIAGNOSIS OF LUNG CANCER USING CT-SCAN IMAGES BASED ON CELLULAR LEARNING AUTOMATE

EARLY STAGE DIAGNOSIS OF LUNG CANCER USING CT-SCAN IMAGES BASED ON CELLULAR LEARNING AUTOMATE EARLY STAGE DIAGNOSIS OF LUNG CANCER USING CT-SCAN IMAGES BASED ON CELLULAR LEARNING AUTOMATE SAKTHI NEELA.P.K Department of M.E (Medical electronics) Sengunthar College of engineering Namakkal, Tamilnadu,

More information

Evaluation of AJCC, UICC, and Brigham and Women's Hospital Tumor Staging for Cutaneous Squamous Cell Carcinoma

Evaluation of AJCC, UICC, and Brigham and Women's Hospital Tumor Staging for Cutaneous Squamous Cell Carcinoma Evaluation of AJCC, UICC, and Brigham and Women's Hospital Tumor Staging for Cutaneous Squamous Cell Carcinoma Karia, et al Methods Details of data collectionfeatures of primary tumors including anatomic

More information

Introduction. Introduction

Introduction. Introduction Introduction We are leveraging genome sequencing data from The Cancer Genome Atlas (TCGA) to more accurately define mutated and stable genes and dysregulated metabolic pathways in solid tumors. These efforts

More information

Combining Data Science and Medical Imaging:

Combining Data Science and Medical Imaging: Combining Data Science and Medical Imaging: Advancing Cancer Precision Medicine with Radiomics Thibaud Coroller copyright Thibaud Coroller, Maastricht 2017 Printing: Datawyse Universitaire Pers Maastricht

More information

Multi-omics data integration colon cancer using proteogenomics approach

Multi-omics data integration colon cancer using proteogenomics approach Dept. of Medical Oncology Multi-omics data integration colon cancer using proteogenomics approach DTL Focus meeting, 29 August 2016 Thang Pham OncoProteomics Laboratory, Dept. of Medical Oncology VU University

More information

Test Retest Data for Radiomics Feature Stability Analysis: Generalizable or Study-Specific?

Test Retest Data for Radiomics Feature Stability Analysis: Generalizable or Study-Specific? RESEARCH ARTICLE Test Retest Data for Radiomics Feature Stability Analysis: Generalizable or Study-Specific? Janna E. van Timmeren 1, Ralph T.H. Leijenaar 1, Wouter van Elmpt 1, Jiazhou Wang 2,3, Zhen

More information

Cover Page. Author: Wang, Ancong Title: Automatic quantification of intravascular optical coherence tomography Issue Date:

Cover Page. Author: Wang, Ancong Title: Automatic quantification of intravascular optical coherence tomography Issue Date: Cover Page The handle http://hdl.handle.net/1887/29690 holds various files of this Leiden University dissertation Author: Wang, Ancong Title: Automatic quantification of intravascular optical coherence

More information

Molecular Markers. Marcie Riches, MD, MS Associate Professor University of North Carolina Scientific Director, Infection and Immune Reconstitution WC

Molecular Markers. Marcie Riches, MD, MS Associate Professor University of North Carolina Scientific Director, Infection and Immune Reconstitution WC Molecular Markers Marcie Riches, MD, MS Associate Professor University of North Carolina Scientific Director, Infection and Immune Reconstitution WC Overview Testing methods Rationale for molecular testing

More information

Volumetric Assessment of Hepatocellular Carcinoma Response to Treatment Using a Random. Forest-Based Automated Segmentation Protocol

Volumetric Assessment of Hepatocellular Carcinoma Response to Treatment Using a Random. Forest-Based Automated Segmentation Protocol Volumetric Assessment of Hepatocellular Carcinoma Response to Treatment Using a Random Forest-Based Automated Segmentation Protocol Kareem Ahmed, MD 1 David Fuentes, PhD 1 J.S. Lin, PhD 1 Reham Ali, MD

More information

Integrative Omics for The Systems Biology of Complex Phenotypes

Integrative Omics for The Systems Biology of Complex Phenotypes Integrative Omics for The Systems Biology of Complex Phenotypes Mehmet Koyutürk Case Western Reserve University (1) Electrical Engineering and Computer Science (2) Center for Proteomics and Bioinformatics

More information

Final Project Report Sean Fischer CS229 Introduction

Final Project Report Sean Fischer CS229 Introduction Introduction The field of pathology is concerned with identifying and understanding the biological causes and effects of disease through the study of morphological, cellular, and molecular features in

More information

Quantitative Imaging for Treatment Response Assessment. Thanks to 8/2/2017. Predicting response to RT or chemo can be based on:

Quantitative Imaging for Treatment Response Assessment. Thanks to 8/2/2017. Predicting response to RT or chemo can be based on: Quantitative Imaging for Treatment Response Assessment Amita Dave, Neelam Tyagi, Sang Ho Lee, Miria Crispin-Ortuzar, Jeho Jeong, John Humm, Milan Grkovski, Joe Deasy et al. Harini Veeraraghavan, PhD Jung

More information

Somatic mutations associated with MRI-derived volumetric features in glioblastoma

Somatic mutations associated with MRI-derived volumetric features in glioblastoma DOI 10.1007/s00234-015-1576-7 DIAGNOSTIC NEURORADIOLOGY Somatic mutations associated with MRI-derived volumetric features in glioblastoma David A. Gutman 1,2 & William D. Dunn Jr 1,2 & Patrick Grossmann

More information

Computer-based 3d Puzzle Solving For Pre-operative Planning Of Articular Fracture Reductions In The Ankle, Knee, And Hip

Computer-based 3d Puzzle Solving For Pre-operative Planning Of Articular Fracture Reductions In The Ankle, Knee, And Hip Computer-based 3d Puzzle Solving For Pre-operative Planning Of Articular Fracture Reductions In The Ankle, Knee, And Hip Andrew M. Kern, MS, Donald Anderson. University of Iowa, Iowa City, IA, USA. Disclosures:

More information

Ratio of maximum standardized uptake value to primary tumor size is a prognostic factor in patients with advanced non-small cell lung cancer

Ratio of maximum standardized uptake value to primary tumor size is a prognostic factor in patients with advanced non-small cell lung cancer Original Article Ratio of maximum standardized uptake value to primary tumor size is a prognostic factor in patients with advanced non-small cell lung cancer Fangfang Chen 1 *, Yanwen Yao 2 *, Chunyan

More information

Endobronchial Ultrasound in the Diagnosis & Staging of Lung Cancer

Endobronchial Ultrasound in the Diagnosis & Staging of Lung Cancer Endobronchial Ultrasound in the Diagnosis & Staging of Lung Cancer Dr Richard Booton PhD FRCP Lead Lung Cancer Clinician, Consultant Respiratory Physician & Speciality Director Manchester University NHS

More information

ANALYTISCHE STRATEGIE Tissue Imaging. Bernd Bodenmiller Institute of Molecular Life Sciences University of Zurich

ANALYTISCHE STRATEGIE Tissue Imaging. Bernd Bodenmiller Institute of Molecular Life Sciences University of Zurich ANALYTISCHE STRATEGIE Tissue Imaging Bernd Bodenmiller Institute of Molecular Life Sciences University of Zurich Quantitative Breast single cancer cell analysis Switzerland Brain Breast Lung Colon-rectum

More information

Metabolomics: quantifying the phenotype

Metabolomics: quantifying the phenotype Metabolomics: quantifying the phenotype Metabolomics Promises Quantitative Phenotyping What can happen GENOME What appears to be happening Bioinformatics TRANSCRIPTOME What makes it happen PROTEOME Systems

More information

Radiomics: Images Are More than Pictures, They Are Data 1

Radiomics: Images Are More than Pictures, They Are Data 1 This copy is for personal use only. To order printed copies, contact reprints@rsna.org Robert J. Gillies, PhD Paul E. Kinahan, PhD Hedvig Hricak, MD, PhD, Dr(hc) Radiomics: Images Are More than Pictures,

More information

LUNG NODULE SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGE. Hemahashiny, Ketheesan Department of Physical Science, Vavuniya Campus

LUNG NODULE SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGE. Hemahashiny, Ketheesan Department of Physical Science, Vavuniya Campus LUNG NODULE SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGE Hemahashiny, Ketheesan Department of Physical Science, Vavuniya Campus tketheesan@vau.jfn.ac.lk ABSTRACT: The key process to detect the Lung cancer

More information

Strengthening the weakest link: improving tumour definition

Strengthening the weakest link: improving tumour definition Strengthening the weakest link: improving tumour definition Marianne C Aznar marianne.aznar@manchester.ac.uk University of Manchester / The Christie NHS Clinical Trial Service Unit, University of Oxford

More information

Chapter 6. Hester Gietema Cornelia Schaefer-Prokop Willem Mali Gerard Groenewegen Mathias Prokop. Accepted for publication in Radiology

Chapter 6. Hester Gietema Cornelia Schaefer-Prokop Willem Mali Gerard Groenewegen Mathias Prokop. Accepted for publication in Radiology Chapter 6 Interscan variability of semiautomated volume measurements in intraparenchymal pulmonary nodules using multidetector-row computed tomography: Influence of inspirational level, nodule size and

More information

Beyond RECIST Volumetric and Functional Tumor Analysis in Oncology Clinical Trials

Beyond RECIST Volumetric and Functional Tumor Analysis in Oncology Clinical Trials Beyond RECIST Volumetric and Functional Tumor Analysis in Oncology Clinical Trials Presented by Median Technologies, The Imaging Phenomics Company Contents 01 Introduction 02 Routine Versus Advanced Endpoints

More information