Development of a Decision Support System for the automatic diagnosis of medical images from brain MRI studies. Christian Salvatore

Size: px
Start display at page:

Download "Development of a Decision Support System for the automatic diagnosis of medical images from brain MRI studies. Christian Salvatore"

Transcription

1 Development of a Decision Support System for the automatic diagnosis of medical images from brain MRI studies Christian Salvatore Dottorato di Ricerca in Fisica, Scuola di Dottorato di Scienze Università degli Studi di Milano - Bicocca - XXVIII ciclo - Supervisor: Prof. Marco Paganoni External supervisor: Dott.ssa Isabella Castiglioni (IBFM-CNR; HSR) September, 28 th 2015

2 Overview Introduction Decision Support Systems Magnetic Resonance Imaging Machine Learning > Support Vector Machine The Machine Learning method Image preprocessing Feature extraction and selection Classification Computation of activation patterns for biomarkers extraction Application I > Parkinson s Disease Application II > Alzheimer s Disease Application III > Eating Disorders Conclusions

3 Introduction

4 Introduction > Decision Support Systems in medicine Role of Physics in Medicine R&D of medical devices (diagnosis, therapy ) Definition of protocols for the acquisition of medical images Implementation and development of algorithms for the analysis and processing of medical images Decision Support Systems in Clinical Medicine Assisted Diagnosis Objective clinical assessments Increasing in Diagnostic Accuracy Early and Differential Diagnosis

5 Introduction > Magnetic Resonance Imaging Nuclear imaging technique which produces 3D structural images Vertical magnetic field Precession motion of nuclei Magnetic momentum Radiofrequency pulses aimed to rotate the global magnetization (Larmor frequency for Hydrogen at 1.5T = 63.9MhZ) Spin-spin and spin-lattice interactions -> relaxation of magnetization vectors

6 Introduction > Magnetic Resonance Imaging T1 weight Cerebrospinal fluid (CSF) White and grey matter Fat

7 Introduction > Image Processing in Medicine Univariate analysis MultiVariate Pattern Analysis (MVPA) Correlation-based one-nearest neighbor classifier Neural network classifier Linear Discriminant Analysis Support Vector Machine (SVM) MACHINE LEARNING PREDICTIVE MODELS

8 Introduction > MVPA from Machine Learning Machine learning predictive models to predict a variable of interest (e.g. mental state 1 vs. mental state 2, or patients vs controls) from a voxel-based pattern (activation/anatomy)

9 Introduction > MVPA from Machine Learning The variable to be predicted when the variable comprises a set of discrete classes, the problem is referred to as Classification Variable = LABEL

10 Aim why SVM in brain imaging studies?

11 The machine learning method

12 The Machine Learning method > Schematic flowchart

13 The Machine Learning method > Image preprocessing MRI images Spatial Normalization Standard Template

14 The Machine Learning method > Feature extraction Principal Components Analysis (PCA) Extraction of the most significant features from a dataset X of (possibly) correlated variables : 1) application of an orthogonal transformation to the dataset X, which results in a set of orthogonal (uncorrelated) variables called principal components (eigenvectors) of the original dataset principal components = eigenvectors of C X X T 1) The space spanned by principal components is called PCA-space 2) PCA coefficients or scores are obtained by projection of the data onto the PCA-space PCA provides a measure of the variance explained by each component

15 The Machine Learning method > Feature selection Fisher s Discriminant Ratio (FDR) FDR can be obtained for each component applying the following formula to the PCA coefficients FDR k and 2 represent the two classes involved FDR provides a measure of the class discriminatory power of each component Feature selection is made by ranking PCA coefficients according to the FDR criterion (higher FDR = higher discriminatory power) Ranked PCA coefficients and associated labels can then be used for classification

16 The Machine Learning method > Classification Support Vector Machine (SVM) A set of known data (the training set) is used to estimate (to learn) the parameters of a model relating particular data attributes (the features ) to variables (the labels ) Once the parameters are learned (trained SVM), the model is applied to predict the label of new data (the testing set) AD subjects TRAINING SET Controls new subject Trained SVM Predicted label

17 The Machine Learning method > Classification Support Vector Machine (SVM) Image space N subj Feature space Data (Features, N sbj) 2 1 w d d d = distance from the hyper-plane 1 TRAINING SET New sbj pl x Predicted label = pl(x) N x w l k x, x i 1 i i i b l 1,2 TESTING SET

18 The Machine Learning method > Classification Support Vector Machine (SVM) pl N x w l k x, x i 1 i i i b Predictive model or decision function 1 Minimization of the empirical classification error Maximization of the separation distance between the two training classes (that is why the decision function is often called maximum margin hyper-plane) 2

19 Introduction > Classification Support Vector Machine (SVM) 1. Health Subject 1 2. Health Subject 2 3. Health Subject 3 Group CONDITIONS M. Health Subject M 1. Pathological 1 2. Pathological 2?? Single-subject classification Test +1 class 3. Pathological 3 M. Pathological M

20 The Machine Learning method > Weight maps Image space Feature space N subj 2 pl Data (Features, N sbj) N x w l k x, x i 1 i i i b 1 d 1 w d d = distance from the hyper-plane TRAINING SET Image maps of the most important voxels for the classification of 1 vs. 2 N sbj i=1 i x w = i Weight Maps Back projected image (eigenbrain)

21 The Machine Learning method > Weight maps Issues Predicted label = pl(x) pl N x w l k x, x i 1 x l 1,2 i i i b The combination of all weights defines the model Weights at each voxel are dependent on one another No voxel-wise statistical tests can be performed

22 The Machine Learning method > Activation patterns Image space Feature space N subj 2 y Data (Features, N sbj) N x w t k x, x i 1 i i i b 1 d 1 w d d = distance from the hyper-plane TRAINING SET Activation Maps w f N sbj = i=1 Features f,i x w i Image maps of voxel-based pattern distribution of brain structural differences between 1 and 2 COV [Data(Features, N sbj)] x w f = transformed weighted features

23 Application I Parkinson s Disease

24 Application I > Parkinson s Disease Parkinson s Disease (PD) Diagnosis Critical issue: to achieve an individual differential diagnosis Poor accuracy, specificity and sensitivity at visual inspection PD is difficult to be differentiated from other parkinsonian conditions such as Progressive Supranuclear Palsy (PSP) To date, the only validated MRI-based measurement employed in clinical practice of PD derives from conventional MRI using manual morphometric quantification

25 Application I > Parkinson s Disease Cohort 28 Healthy Control (HC) subjects 56 patients 28 Parkinson s Disease (PD) 28 Progressive Supranuclear Palsy (PSP) Healthy control subjects of similar age as both patients groups Patients recruited and data acquired at the Institute of Neurology, University Magna Graecia, Catanzaro MR images MRI system (1.5 T) Signa NV/I GE Medical Systems, USA FOV = 24cm Slice thickness = 1.2mm TR = 15.2ms; TE = 6.7ms T1-weighted 3D dataset

26 Application I > Parkinson s Disease Performance evaluation 1 Leave-One-Out (LOO) Cross Validation: N-1 subjects for training The remaining (1) subject for testing Multiple (N) rounds 2 N/2 Validation: 50% randomly chosen subjects for training The remaining 50% subjects for testing

27 Application I > Parkinson s Disease Comparisons PSP vs. PD PSP vs. CN PD vs. CN

28 Application I > Parkinson s Disease Image pre-processing Axial view of a MR scan of a clinicaly diagnosed PD patient before (a) and after (b) normalization to the MNI space

29 Application I > Parkinson s Disease Feature extraction + selection PSP (28) vs. PD (28): PCA coefficients (1 st, 2 nd and 3 rd components that showed highest FDR)

30 Application I > Parkinson s Disease Classification (training) PSP (28) vs. PD (28): Optimal Separating Hyper-Plane (1 st, 2 nd and 3 rd components)

31 Application I > Parkinson s Disease LOO VALIDATION N/2 VALIDATION Performance evaluation > Accuracy, specificity and sensitivity rates of SVM Overall Mean Accuracy* (%) Overall Mean Specificity* (%) Overall Mean Sensitivity* (%) Accuracy >80 (%) Mean (Min/Max) Specificity >80 (%) Mean (Min/Max) Sensitivity >80 (%) Mean (Min/Max) PD vs. HC PSP vs. HC PSP vs. PD PD vs. HC PSP vs. HC PSP vs. PD (83.9/100.0) 92.3 (81.3/100.0) 93.4 (80.6/100.0) (92.9/100.0) 98.2 (92.9/100.0) 95.9 (90.0/100.0) (94.6/100.0) 98.8 (96.3/100.0) 97.8 (93.1/100.0) (89.3/100) 90.6 (82.4/100) 97.4 (92.3/100) (85.7/96.4) 92.5 (85.7/100) 92.4 (85.7/100) (89.3/96.4) 91.3 (82.4/100) 94.4 (86.7/100) * Obtained as mean values calculated over a number of PCA components ranging from 1 to the whole number of extracted PCA components Calculated over a range of PCA components for which Accuracy, Specificity and Sensitivity fell above 80%

32 Application I > Parkinson s Disease Accuracy, specificity and sensitivity rates (%) of SVM versus Number of PCA coefficients (PSP vs. PD, LOO validation)

33 Application I > Parkinson s Disease Diagnostic MR-related biomarkers Thalamus Midbrain (Substantia Nigra) Pons Corpus Callosum Corpus Callosum Thalamus Midbrain Pons C Salvatore et al. Journal of Neuroscience Methods (2015) Midbrain Pons Corpus Callosum Thalamus

34 Application I > Parkinson s Disease Diagnostic MR-related biomarkers PD versus Healthy Controls: medial part of the midbrain (encompassing the substantia nigra) and caudal part of the pons. These findings are consistent with the Braak s neuroanatomical model of the PD. PSP versus Healthy Controls: midbrain, pons, corpus callosum and thalamus, four critical regions known to be strongly involved in the pathophysiological mechanisms of PSP. PSP versus PD: midbrain, pons, corpus callosum and thalamus. These features are highly consistent with typical neuropathological and imaging findings described in patients with PSP, where a key role is played by the volumetric atrophy of the brainstem, which represents a hallmark of PSP.

35 Application II Alzheimer s Disease

36 Application II > Alzheimer s Disease Alzheimer s Disease (AD) Diagnosis Individual diagnosis of AD is predominantly based on the clinical examination and neuropsychological assessment Definite diagnosis can only be performed by post-mortem analysis Additional supportive features can be obtained by neuronal injury biomarkers as measured by neuroimaging studies, including MRI MR changes provide measurements of atrophic regions even before dementia is apparent Detecting the transitions asymptomatic phase -> symptomatic pre-dementia phase -> dementia onset in the clinical setting is a non-trivial issue This causes a diagnostic uncertainty for the early stage of disease Determination of sensitive and specific markers of very early AD progression

37 Application II > Alzheimer s Disease Cohort and images obtained from the Alzheimer s Disease Neuroimaging Initiative (ADNI) database Cohort 162 Healthy Control (CN) subjects 134 Mild Cognitive Impairment not converter to AD (MCInc) 076 Mild Cognitive Impairment converter to AD (MCIc) 137 Alzheimer s Disease (AD) Healthy control subjects of similar age and gender as both patients groups MR images T1-weighted structural MR images (1.5 T) A total of 509 scans from 41 different radioligical centers

38 Application II > Alzheimer s Disease Performance evaluation Nested k-fold cross validation: K-1 subsets for training + parameter estimation and optimization The remaining (1) subset for performance evaluation Multiple (N) rounds K = 20 N rounds PERFORMANCE EVALUATION TRAINING PARAMETER ESTIMATION AND OPTIMIZATION

39 Application II > Alzheimer s Disease Comparisons MCIc vs. MCInc MCIc vs. CN AD vs. CN

40 Application II > Alzheimer s Disease Normalization to MNI space by automatic elastic co-registration to the MNI template (MNI152_T1_1mm_brain)

41 Application II > Alzheimer s Disease PCA coefficients

42 Application II > Alzheimer s Disease Explained variance Before FDR ranking After FDR ranking

43 Application II > Alzheimer s Disease Optimal separating hyperplane

44 Application II > Alzheimer s Disease Parameter optimization AD vs. CN GM tissue probability map 10 mm 3 FWHM of isotropic Gaussian kernel (smoothing) 127 PCA coefficients Minimum error = 0.08 MCIc vs. CN GM tissue probability map 6 mm 3 FWHM of isotropic Gaussian kernel (smoothing) 67 PCA coefficients Minimum error = 0.14 MCIc vs. MCInc GM tissue probability map 2 mm 3 FWHM of isotropic Gaussian kernel (smoothing) 34 PCA coefficients Minimum error = 0.27

45 Application II > Alzheimer s Disease Performance evaluation Balanced accuracy AD vs. CN MCIc vs. CN MCIc vs. MCInc 0.76 ± ± ± 0.16

46 Application II > Alzheimer s Disease Temporal pole Medial temporal cortex (hippocampus and enthorinal cortex) AD vs CN Segmented GM 137 AD 162 CN Cerebellum (posterior lobule) Caudate, putamen Amygdala Thalamus Gyrus rectus Precuneus Anterior cingulate cortex Insular cortex C Salvatore et al. Frontiers in neuroscience (2015)

47 Application II > Alzheimer s Disease The major part of voxels influencing the classification of both MCIc vs. CN and MCIc vs. MCInc was similar to the one previously found in AD MCIc vs CN Segmented GM 76 MCIc 162 CN Is diagnosis of AD at very early stages by MRI a matter of sensitivity? C Salvatore et al. Frontiers in neuroscience (2015)

48 Application II > Alzheimer s Disease The major part of voxels influencing the classification of both MCIc vs. CN and MCIc vs. MCInc was similar to the one previously found in AD MCIc vs MCInc Segmented GM 76 MCIc 134 MCInc Is diagnosis of AD at very early stages by MRI a matter of sensitivity? C Salvatore et al. Frontiers in neuroscience (2015)

49 Application III Eating Disorders

50 Application III > Eating Disorders Eating Disorders (ED) Diagnosis To date, individual diagnosis of ED is based only on a clinical interview complemented by physical, psychopathological and behavioural examinations ED diagnosis is unstable, with clinical features changing over time, often switching from Anorexia (AN) to Bulimia (BN) However, there is little interest in a technique for the automatic diagnosis of ED because clinical examinations are able to diagnose it No valid biomarkers of ED are known

51 Application III > Eating Disorders Cohort 17 Healthy Control (HC) subjects 17 Eating Disorders (ED)patients 11 Bulimia Nervosa (BN) 06 Anorexia Nervosa (AN) Healthy control subjects of similar age, education and BMI as patients group Patients recruited and data acquired at the Institute of Neurology, University Magna Graecia, Catanzaro MR images MRI system (3 T) Discovery MR-750 GE Medical Systems, USA FOV = 48cm Slice thickness = 1mm TR = 13.7ms; TE = 9.2ms T1-weighted 3D dataset

52 Application III > Eating Disorders Performance evaluation K-fold Cross Validation: K-1 subsets for training The remaining (1) subset for testing K = 10 K = 20 Multiple (K) rounds N rounds TESTING TRAINING

53 Application II > Parkinson s Disease Comparison ED vs. CN

54 Application III > Eating Disorders Feature extraction + selection PCA coefficient FDR (#)

55 Application III > Eating Disorders Classification (training) ED (17) vs. HC (17): Optimal Separating Hyper-Plane (1 st, 2 nd and 3 rd components)

56 Application III > Eating Disorders Performance evaluation > K-fold cross validation Accuracy Specificity Sensitivity k = k =

57 Application III > Eating Disorders MEDIAL ORBITOFRONTAL CORTEX (part of the ventral limbic circuit) Identification of emotional significance of appetizing stimuli and regulation of inhibitory and reward systems CEREBELLUM Motor, cognitive and emotional functions, feeding behaviour, appetite regulation PRIMARY VISUAL CORTEX Body image disturbance

58 Scalability

59 Scalability of the implemented method GHz AD vs. CN dataset (299 subjects) MCIc vs. CN dataset (238 sbjs) MCIc vs. MCInc dataset (210 sbjs) from Application II described above Operational time required: by the whole pre-processing and training of the classifier (including feature extraction and selection) by the testing phase (including preprocessing and classification of the new dataset) 31.7s (AD vs. CN) 21.7s (MCIc vs. CN) 21.2s (MCIc vs. MCInc) 1.5s / subject on average

60 Scalability of the implemented method GHz AD vs. CN dataset (299 subjects) MCIc vs. CN dataset (238 sbjss) MCIc vs. MCInc dataset (210 sbjs) from Application II described above Operational time required: by the whole pre-processing and training of the classifier (including feature extraction and selection) by the testing phase (including preprocessing and classification of the new dataset) 31.7s (AD vs. CN) 21.7s (MCIc vs. CN) 21.2s (MCIc vs. MCInc) 1.5s / subject on average What would be the operational costs using larger (big data) datasets? What would be the operational costs in the daily clinical practice?

61 From bench to bedside Web-based service

62 Conclusions

63 Conclusions During my PhD, I have developed a supervised machinelearning method able to perform individual differential diagnosis of neurological (PD, PSP, AD) and psychiatric (ED) diseases by means of structural MR images Validation of this method returned classification performance comparable to or higher than other published methods We also implemented the extraction of pattern distribution maps of brain structural differences, which allowed the identification of possible MRI-related biomarkers useful for the diagnosis of the considered diseases Our findings offer new avenues for encouraging the application of computer-based diagnosis in clinical practice

64 Publications ISI International Papers Gallivanone, F., Canevari, C., Gianolli, L., Salvatore, C., Della Rosa, P. A., Gilardi, M. C., & Castiglioni, I. (2013). A partial volume effect correction tailored for 18 F-FDG-PET oncological studies. BioMed research international, Salvatore, C., Cerasa, A., Castiglioni, I., Gallivanone, F., Augimeri, A., Lopez, M.,... & Quattrone, A. (2014). Machine learning on brain MRI data for differential diagnosis of Parkinson's disease and Progressive Supranuclear Palsy. Journal of neuroscience methods, 222, Canini, M., Battista, P., Della Rosa, P. A., Catricalà, E., Salvatore, C., Gilardi, M. C., & Castiglioni, I. (2014). Computerized Neuropsychological Assessment in Aging: Testing Efficacy and Clinical Ecology of Different Interfaces. Computational and mathematical methods in medicine, Crippa, A., Salvatore, C., Perego, P., Forti, S., Nobile, M., Molteni, M., & Castiglioni, I. (2015). Use of Machine Learning to Identify Children with Autism and Their Motor Abnormalities. Journal of autism and developmental disorders, 45(7), doi: /s Salvatore, C., Cerasa, A., Battista, P., Gilardi, M.C., Quattrone, A., & Castiglioni, I. (2015). Magnetic Resonance Imaging biomarkers for the early diagnosis of Alzheimer s Disease: a machine learning approach. Frontiers in Neuroscience. doi: /fnins Salvatore, C., Battista, P., & Castiglioni, I. (2015). Frontiers for the early diagnosis of AD by means of MRI brain imaging and Support Vector Machines. Current Alzheimer Research. [in press] Cerasa, A., Castiglioni, I., Salvatore, C., Funaro, A., Martino, I.,, Alfano, S., Donzuso, G., Perrotta, P., Gioia, M.C., Gilardi, M.C., & Quattrone, A. (2015). Individual detection of patients with eating disorders using support vector machine analysis of morphological imaging data: preliminary results. Behavioural Neurology. [minor revision] Battista, P., Salvatore, C., & Castiglioni, I. Neuropsychological testing coupled to machine learning algorithms allow the identification of a profile of markers for dementia. [submitted] Salvatore, C., Cerasa, A., Battista, P., Gilardi, M.C., & Castiglioni, I. A web-based service to support the diagnosis of Alzheimer s Disease. [submitted]

65 Publications Indexed International Papers Grosso, E., López, M., Salvatore, C., Gallivanone, F., Di Grigoli, G., Valtorta, S.,... & Castiglioni, I. (2012, August). A Decision Support System for the assisted diagnosis of brain tumors: A feasibility study for 18 F-FDG PET preclinical studies. In Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE (pp ). IEEE. Gallivanone, F., Di Grigoli, G., Salvatore, C., Valtorta, S., Gilardi, M. C., Moresco, R. M., & Castiglioni, I. (2012, October). Acute stress studies in rats by 18 FDG PET and SPM. In Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), 2012 IEEE (pp ). IEEE. Cava, C., Zoppis, I., Mauri, G., Ripamonti, M., Gallivanone, F., Salvatore, C.,... & Castiglioni, I. (2013, July). Combination of gene expression and genome copy number alteration has a prognostic value for breast cancer. In Engineering in Medicine and Biology Society (EMBC), th Annual International Conference of the IEEE (pp ). IEEE. International Book Chapters 13 Cava, C., Gallivanone, F., Salvatore, C., Della Rosa, P. and Castiglioni, I. (2014). Bioinformatics clouds for high-throughput technologies. Handbook of Research on Cloud Infrastructures for Big Data Anaytics. IGI Global: doi: / ch020.

66 Publications International Conference Proceedings Gallivanone, F., Di Grigoli, G., Salvatore, C., Valtorta, S., Grosso, E., Gilardi, M.C., Moresco, R.M. and Castiglioni, I. (2012). SPM for activation studies in rats on stress conditions. 6th Hot Topics in Molecular Imaging Conference (TOPIM): p.44. Gallivanone, F., Di Grigoli, G., Salvatore, C., Belloli, S., Valtorta, S., Raccagni, I., Gilardi, M.C., Castiglioni, I. and Moresco, R.M. (2013). Feasibility of supervised machine learning technique for assisted diagnosis of cancer: application to PET studies in small animals. European Molecular Imaging Meeting (EMIM), 8th annual meeting of the European Society for Molecular Imaging (ESMI), Turin, Italy. Castiglioni, I., Cerasa, A., Salvatore, C., Gallivanone, F., Augimeri, A., Lopez, M.,... & Quattrone, A. (2013, June). Machine learning performs differential individual diagnosis of PD and PSP by brain MRI studies. In MOVEMENT DISORDERS (Vol. 28, pp. S71-S72). 111 RIVER ST, HOBOKEN , NJ USA: WILEY-BLACKWELL. Salvatore, C., Cerasa, A., Battista, P., Gilardi, M.C., Quattrone, A., & Castiglioni, I. (2015). Neuroimaging biomarkers predicting conversion to AD. 2nd meeting of the Scientific Council of NeuroMI, Milan. Battista, P., Salvatore, C., Gilardi, M.C., & Castiglioni, I. (2015). Neuropsychological testing and artificial intelligence for early and differential diagnosis of dementia. 2nd meeting of the Scientific Council of NeuroMI, Milan. National Conference Proceedings 19 Gallivanone, F., Grosso, E., Di Grigoli, G., Salvatore, C., Valtorta, S., Gilardi, M.C., Moresco, R.M. and Castiglioni, I. (2012). Statistical Parametric Mapping for activation studies in rats. Atti del Congresso Nazionale di Bioingegneria: p.147; ISBN:

67 Thank you for your attention!

A WEB-BASED INFRASTRUCTURE FOR MRI- BASED COMPUTER CLASSIFICATION OF NEUROLOGICAL PATIENTS: NEURO-IMAGE

A WEB-BASED INFRASTRUCTURE FOR MRI- BASED COMPUTER CLASSIFICATION OF NEUROLOGICAL PATIENTS: NEURO-IMAGE A WEB-BASED INFRASTRUCTURE FOR MRI- BASED COMPUTER CLASSIFICATION OF NEUROLOGICAL PATIENTS: NEURO-IMAGE F. Chionna 1, A. Cerasa 2, M. Giacovazzo 3, A. Iannella 3, Martini 1, N. Savino 1, V.Giannini 3,

More information

Supplementary Online Content

Supplementary Online Content Supplementary Online Content Redlich R, Opel N, Grotegerd D, et al. Prediction of individual response to electroconvulsive therapy via machine learning on structural magnetic resonance imaging data. JAMA

More information

Supplementary Online Content

Supplementary Online Content Supplementary Online Content Van Laere K, Vanhee A, Verschueren J, et al. Value of 18 fluorodeoxyglucose positron-emission tomography in amyotrophic lateral sclerosis. JAMA Neurol. Published online March

More information

10/3/2016. T1 Anatomical structures are clearly identified, white matter (which has a high fat content) appears bright.

10/3/2016. T1 Anatomical structures are clearly identified, white matter (which has a high fat content) appears bright. H2O -2 atoms of Hydrogen, 1 of Oxygen Hydrogen just has one single proton and orbited by one single electron Proton has a magnetic moment similar to the earths magnetic pole Also similar to earth in that

More information

Detection of Mild Cognitive Impairment using Image Differences and Clinical Features

Detection of Mild Cognitive Impairment using Image Differences and Clinical Features Detection of Mild Cognitive Impairment using Image Differences and Clinical Features L I N L I S C H O O L O F C O M P U T I N G C L E M S O N U N I V E R S I T Y Copyright notice Many of the images in

More information

arxiv: v1 [stat.ml] 21 Sep 2017

arxiv: v1 [stat.ml] 21 Sep 2017 Yet Another ADNI Machine Learning Paper? Paving The Way Towards Fully-reproducible Research on Classification of Alzheimer s Disease Jorge Samper-González 1,2, Ninon Burgos 1,2, Sabrina Fontanella 1,2,

More information

Classification and Statistical Analysis of Auditory FMRI Data Using Linear Discriminative Analysis and Quadratic Discriminative Analysis

Classification and Statistical Analysis of Auditory FMRI Data Using Linear Discriminative Analysis and Quadratic Discriminative Analysis International Journal of Innovative Research in Computer Science & Technology (IJIRCST) ISSN: 2347-5552, Volume-2, Issue-6, November-2014 Classification and Statistical Analysis of Auditory FMRI Data Using

More information

Identification of Neuroimaging Biomarkers

Identification of Neuroimaging Biomarkers Identification of Neuroimaging Biomarkers Dan Goodwin, Tom Bleymaier, Shipra Bhal Advisor: Dr. Amit Etkin M.D./PhD, Stanford Psychiatry Department Abstract We present a supervised learning approach to

More information

Discriminative Analysis for Image-Based Population Comparisons

Discriminative Analysis for Image-Based Population Comparisons Discriminative Analysis for Image-Based Population Comparisons Polina Golland 1,BruceFischl 2, Mona Spiridon 3, Nancy Kanwisher 3, Randy L. Buckner 4, Martha E. Shenton 5, Ron Kikinis 6, and W. Eric L.

More information

FDG-PET e parkinsonismi

FDG-PET e parkinsonismi Parkinsonismi FDG-PET e parkinsonismi Valentina Berti Dipartimento di Scienze Biomediche, Sperimentali e Cliniche Sez. Medicina Nucleare Università degli Studi di Firenze History 140 PubMed: FDG AND parkinsonism

More information

QUANTIFYING CEREBRAL CONTRIBUTIONS TO PAIN 1

QUANTIFYING CEREBRAL CONTRIBUTIONS TO PAIN 1 QUANTIFYING CEREBRAL CONTRIBUTIONS TO PAIN 1 Supplementary Figure 1. Overview of the SIIPS1 development. The development of the SIIPS1 consisted of individual- and group-level analysis steps. 1) Individual-person

More information

Brain gray matter volume changes associated with motor symptoms in patients with Parkinson s disease

Brain gray matter volume changes associated with motor symptoms in patients with Parkinson s disease Kang et al. Chinese Neurosurgical Journal (2015) 1:9 DOI 10.1186/s41016-015-0003-6 RESEARCH Open Access Brain gray matter volume changes associated with motor symptoms in patients with Parkinson s disease

More information

Supplementary Online Content

Supplementary Online Content Supplementary Online Content Gregg NM, Kim AE, Gurol ME, et al. Incidental cerebral microbleeds and cerebral blood flow in elderly individuals. JAMA Neurol. Published online July 13, 2015. doi:10.1001/jamaneurol.2015.1359.

More information

Assessing Brain Volumes Using MorphoBox Prototype

Assessing Brain Volumes Using MorphoBox Prototype MAGNETOM Flash (68) 2/207 33 Assessing Brain Volumes Using MorphoBox Prototype Alexis Roche,2,3 ; Bénédicte Maréchal,2,3 ; Tobias Kober,2,3 ; Gunnar Krueger 4 ; Patric Hagmann ; Philippe Maeder ; Reto

More information

Supplementary Information Methods Subjects The study was comprised of 84 chronic pain patients with either chronic back pain (CBP) or osteoarthritis

Supplementary Information Methods Subjects The study was comprised of 84 chronic pain patients with either chronic back pain (CBP) or osteoarthritis Supplementary Information Methods Subjects The study was comprised of 84 chronic pain patients with either chronic back pain (CBP) or osteoarthritis (OA). All subjects provided informed consent to procedures

More information

Functional MRI Mapping Cognition

Functional MRI Mapping Cognition Outline Functional MRI Mapping Cognition Michael A. Yassa, B.A. Division of Psychiatric Neuro-imaging Psychiatry and Behavioral Sciences Johns Hopkins School of Medicine Why fmri? fmri - How it works Research

More information

Regional and Lobe Parcellation Rhesus Monkey Brain Atlas. Manual Tracing for Parcellation Template

Regional and Lobe Parcellation Rhesus Monkey Brain Atlas. Manual Tracing for Parcellation Template Regional and Lobe Parcellation Rhesus Monkey Brain Atlas Manual Tracing for Parcellation Template Overview of Tracing Guidelines A) Traces are performed in a systematic order they, allowing the more easily

More information

Discriminative Analysis for Image-Based Studies

Discriminative Analysis for Image-Based Studies Discriminative Analysis for Image-Based Studies Polina Golland 1, Bruce Fischl 2, Mona Spiridon 3, Nancy Kanwisher 3, Randy L. Buckner 4, Martha E. Shenton 5, Ron Kikinis 6, Anders Dale 2, and W. Eric

More information

SUPPLEMENTARY MATERIAL. Table. Neuroimaging studies on the premonitory urge and sensory function in patients with Tourette syndrome.

SUPPLEMENTARY MATERIAL. Table. Neuroimaging studies on the premonitory urge and sensory function in patients with Tourette syndrome. SUPPLEMENTARY MATERIAL Table. Neuroimaging studies on the premonitory urge and sensory function in patients with Tourette syndrome. Authors Year Patients Male gender (%) Mean age (range) Adults/ Children

More information

Contributions to Brain MRI Processing and Analysis

Contributions to Brain MRI Processing and Analysis Contributions to Brain MRI Processing and Analysis Dissertation presented to the Department of Computer Science and Artificial Intelligence By María Teresa García Sebastián PhD Advisor: Prof. Manuel Graña

More information

AUTOMATING NEUROLOGICAL DISEASE DIAGNOSIS USING STRUCTURAL MR BRAIN SCAN FEATURES

AUTOMATING NEUROLOGICAL DISEASE DIAGNOSIS USING STRUCTURAL MR BRAIN SCAN FEATURES AUTOMATING NEUROLOGICAL DISEASE DIAGNOSIS USING STRUCTURAL MR BRAIN SCAN FEATURES ALLAN RAVENTÓS AND MOOSA ZAIDI Stanford University I. INTRODUCTION Nine percent of those aged 65 or older and about one

More information

Development of Soft-Computing techniques capable of diagnosing Alzheimer s Disease in its pre-clinical stage combining MRI and FDG-PET images.

Development of Soft-Computing techniques capable of diagnosing Alzheimer s Disease in its pre-clinical stage combining MRI and FDG-PET images. Development of Soft-Computing techniques capable of diagnosing Alzheimer s Disease in its pre-clinical stage combining MRI and FDG-PET images. Olga Valenzuela, Francisco Ortuño, Belen San-Roman, Victor

More information

SUPPLEMENT: DYNAMIC FUNCTIONAL CONNECTIVITY IN DEPRESSION. Supplemental Information. Dynamic Resting-State Functional Connectivity in Major Depression

SUPPLEMENT: DYNAMIC FUNCTIONAL CONNECTIVITY IN DEPRESSION. Supplemental Information. Dynamic Resting-State Functional Connectivity in Major Depression Supplemental Information Dynamic Resting-State Functional Connectivity in Major Depression Roselinde H. Kaiser, Ph.D., Susan Whitfield-Gabrieli, Ph.D., Daniel G. Dillon, Ph.D., Franziska Goer, B.S., Miranda

More information

Investigating the impact of midlife obesity on Alzheimer s disease (AD) pathology in a mouse model of AD

Investigating the impact of midlife obesity on Alzheimer s disease (AD) pathology in a mouse model of AD Brain@McGill Prize for Neuroscience Undergraduate Research Colleen Rollins Supervisor: Dr. Mallar Chakravarty Revised: August 8, 2017 Investigating the impact of midlife obesity on Alzheimer s disease

More information

Hallucinations and conscious access to visual inputs in Parkinson s disease

Hallucinations and conscious access to visual inputs in Parkinson s disease Supplemental informations Hallucinations and conscious access to visual inputs in Parkinson s disease Stéphanie Lefebvre, PhD^1,2, Guillaume Baille, MD^4, Renaud Jardri MD, PhD 1,2 Lucie Plomhause, PhD

More information

Visual Rating Scale Reference Material. Lorna Harper Dementia Research Centre University College London

Visual Rating Scale Reference Material. Lorna Harper Dementia Research Centre University College London Visual Rating Scale Reference Material Lorna Harper Dementia Research Centre University College London Background The reference materials included in this document were compiled and used in relation to

More information

MRI-Based Classification Techniques of Autistic vs. Typically Developing Brain

MRI-Based Classification Techniques of Autistic vs. Typically Developing Brain MRI-Based Classification Techniques of Autistic vs. Typically Developing Brain Presented by: Rachid Fahmi 1 2 Collaborators: Ayman Elbaz, Aly A. Farag 1, Hossam Hassan 1, and Manuel F. Casanova3 1Computer

More information

Use of Multimodal Neuroimaging Techniques to Examine Age, Sex, and Alcohol-Related Changes in Brain Structure Through Adolescence and Young Adulthood

Use of Multimodal Neuroimaging Techniques to Examine Age, Sex, and Alcohol-Related Changes in Brain Structure Through Adolescence and Young Adulthood American Psychiatric Association San Diego, CA 24 May 2017 Use of Multimodal Neuroimaging Techniques to Examine Age, Sex, and Alcohol-Related Changes in Brain Structure Through Adolescence and Young Adulthood

More information

Voxel-based morphometry in clinical neurosciences

Voxel-based morphometry in clinical neurosciences Voxel-based morphometry in clinical neurosciences Ph.D. Thesis Ádám Feldmann Department of Behavioural Sciences Leader of Doctoral School: Prof. Dr.Sámuel Komoly, D.Sc. Program leader: Prof. Dr.Sámuel

More information

Course Booklet. We have felt the pain that Neuroscience is giving you.

Course Booklet. We have felt the pain that Neuroscience is giving you. Exams Stressing You Out? Take Action! Course Booklet NEUR 1202 Carleton University* *TranscendFinals is not affiliated with the university We have felt the pain that Neuroscience is giving you. Our mission

More information

Early Diagnosis of Alzheimer s Disease and MCI via Imaging and Pattern Analysis Methods. Christos Davatzikos, Ph.D.

Early Diagnosis of Alzheimer s Disease and MCI via Imaging and Pattern Analysis Methods. Christos Davatzikos, Ph.D. Early Diagnosis of Alzheimer s Disease and MCI via Imaging and Pattern Analysis Methods Christos Davatzikos, Ph.D. Director, Section of Biomedical Image Analysis Professor of Radiology http://www.rad.upenn.edu/sbia

More information

Automated morphometry in adolescents with OCD and controls, using MR images with incomplete brain coverage

Automated morphometry in adolescents with OCD and controls, using MR images with incomplete brain coverage Automated morphometry in adolescents with OCD and controls, using MR images with incomplete brain coverage M.Sc. Thesis Oscar Gustafsson gusgustaos@student.gu.se Supervisors: Göran Starck Maria Ljungberg

More information

Chapter 3. Structure and Function of the Nervous System. Copyright (c) Allyn and Bacon 2004

Chapter 3. Structure and Function of the Nervous System. Copyright (c) Allyn and Bacon 2004 Chapter 3 Structure and Function of the Nervous System 1 Basic Features of the Nervous System Neuraxis: An imaginary line drawn through the center of the length of the central nervous system, from the

More information

Investigations in Resting State Connectivity. Overview

Investigations in Resting State Connectivity. Overview Investigations in Resting State Connectivity Scott FMRI Laboratory Overview Introduction Functional connectivity explorations Dynamic change (motor fatigue) Neurological change (Asperger s Disorder, depression)

More information

Supplementary materials. Appendix A;

Supplementary materials. Appendix A; Supplementary materials Appendix A; To determine ADHD diagnoses, a combination of Conners' ADHD questionnaires and a semi-structured diagnostic interview was used(1-4). Each participant was assessed with

More information

Supporting Information

Supporting Information Revisiting default mode network function in major depression: evidence for disrupted subsystem connectivity Fabio Sambataro 1,*, Nadine Wolf 2, Maria Pennuto 3, Nenad Vasic 4, Robert Christian Wolf 5,*

More information

Text to brain: predicting the spatial distribution of neuroimaging observations from text reports (submitted to MICCAI 2018)

Text to brain: predicting the spatial distribution of neuroimaging observations from text reports (submitted to MICCAI 2018) 1 / 22 Text to brain: predicting the spatial distribution of neuroimaging observations from text reports (submitted to MICCAI 2018) Jérôme Dockès, ussel Poldrack, Demian Wassermann, Fabian Suchanek, Bertrand

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

Funding: NIDCF UL1 DE019583, NIA RL1 AG032119, NINDS RL1 NS062412, NIDA TL1 DA

Funding: NIDCF UL1 DE019583, NIA RL1 AG032119, NINDS RL1 NS062412, NIDA TL1 DA The Effect of Cognitive Functioning, Age, and Molecular Variables on Brain Structure Among Carriers of the Fragile X Premutation: Deformation Based Morphometry Study Naomi J. Goodrich-Hunsaker*, Ling M.

More information

Supplementary Information

Supplementary Information Supplementary Information The neural correlates of subjective value during intertemporal choice Joseph W. Kable and Paul W. Glimcher a 10 0 b 10 0 10 1 10 1 Discount rate k 10 2 Discount rate k 10 2 10

More information

A possible mechanism for impaired joint attention in autism

A possible mechanism for impaired joint attention in autism A possible mechanism for impaired joint attention in autism Justin H G Williams Morven McWhirr Gordon D Waiter Cambridge Sept 10 th 2010 Joint attention in autism Declarative and receptive aspects initiating

More information

Functional Elements and Networks in fmri

Functional Elements and Networks in fmri Functional Elements and Networks in fmri Jarkko Ylipaavalniemi 1, Eerika Savia 1,2, Ricardo Vigário 1 and Samuel Kaski 1,2 1- Helsinki University of Technology - Adaptive Informatics Research Centre 2-

More information

Group-Wise FMRI Activation Detection on Corresponding Cortical Landmarks

Group-Wise FMRI Activation Detection on Corresponding Cortical Landmarks Group-Wise FMRI Activation Detection on Corresponding Cortical Landmarks Jinglei Lv 1,2, Dajiang Zhu 2, Xintao Hu 1, Xin Zhang 1,2, Tuo Zhang 1,2, Junwei Han 1, Lei Guo 1,2, and Tianming Liu 2 1 School

More information

CISC 3250 Systems Neuroscience

CISC 3250 Systems Neuroscience CISC 3250 Systems Neuroscience Levels of organization Central Nervous System 1m 10 11 neurons Neural systems and neuroanatomy Systems 10cm Networks 1mm Neurons 100μm 10 8 neurons Professor Daniel Leeds

More information

Visualization strategies for major white matter tracts identified by diffusion tensor imaging for intraoperative use

Visualization strategies for major white matter tracts identified by diffusion tensor imaging for intraoperative use International Congress Series 1281 (2005) 793 797 www.ics-elsevier.com Visualization strategies for major white matter tracts identified by diffusion tensor imaging for intraoperative use Ch. Nimsky a,b,

More information

Brain tissue and white matter lesion volume analysis in diabetes mellitus type 2

Brain tissue and white matter lesion volume analysis in diabetes mellitus type 2 Brain tissue and white matter lesion volume analysis in diabetes mellitus type 2 C. Jongen J. van der Grond L.J. Kappelle G.J. Biessels M.A. Viergever J.P.W. Pluim On behalf of the Utrecht Diabetic Encephalopathy

More information

Supplementary Online Content

Supplementary Online Content Supplementary Online Content Green SA, Hernandez L, Tottenham N, Krasileva K, Bookheimer SY, Dapretto M. The neurobiology of sensory overresponsivity in youth with autism spectrum disorders. Published

More information

Supplementary Material S3 Further Seed Regions

Supplementary Material S3 Further Seed Regions Supplementary Material S3 Further Seed Regions Figure I. Changes in connectivity with the right anterior insular cortex. (A) wake > mild sedation, showing a reduction in connectivity between the anterior

More information

Shape Modeling of the Corpus Callosum for Neuroimaging Studies of the Brain (Part I) Dongqing Chen, Ph.D.

Shape Modeling of the Corpus Callosum for Neuroimaging Studies of the Brain (Part I) Dongqing Chen, Ph.D. The University of Louisville CVIP Lab Shape Modeling of the Corpus Callosum for Neuroimaging Studies of the Brain (Part I) Dongqing Chen, Ph.D. Computer Vision & Image Processing (CVIP) Laboratory Department

More information

Procedia - Social and Behavioral Sciences 159 ( 2014 ) WCPCG 2014

Procedia - Social and Behavioral Sciences 159 ( 2014 ) WCPCG 2014 Available online at www.sciencedirect.com ScienceDirect Procedia - Social and Behavioral Sciences 159 ( 2014 ) 743 748 WCPCG 2014 Differences in Visuospatial Cognition Performance and Regional Brain Activation

More information

Prediction of Successful Memory Encoding from fmri Data

Prediction of Successful Memory Encoding from fmri Data Prediction of Successful Memory Encoding from fmri Data S.K. Balci 1, M.R. Sabuncu 1, J. Yoo 2, S.S. Ghosh 3, S. Whitfield-Gabrieli 2, J.D.E. Gabrieli 2 and P. Golland 1 1 CSAIL, MIT, Cambridge, MA, USA

More information

Network-based pattern recognition models for neuroimaging

Network-based pattern recognition models for neuroimaging Network-based pattern recognition models for neuroimaging Maria J. Rosa Centre for Neuroimaging Sciences, Institute of Psychiatry King s College London, UK Outline Introduction Pattern recognition Network-based

More information

Supporting online material. Materials and Methods. We scanned participants in two groups of 12 each. Group 1 was composed largely of

Supporting online material. Materials and Methods. We scanned participants in two groups of 12 each. Group 1 was composed largely of Placebo effects in fmri Supporting online material 1 Supporting online material Materials and Methods Study 1 Procedure and behavioral data We scanned participants in two groups of 12 each. Group 1 was

More information

Neuroanatomical correlates of depressive symptoms in newly diagnosed Parkinson s disease patients

Neuroanatomical correlates of depressive symptoms in newly diagnosed Parkinson s disease patients Neurology Asia 2018; 23(3) : 239 244 Neuroanatomical correlates of depressive symptoms in newly diagnosed Parkinson s disease patients * 1,2 Seong-il Oh MD, * 1,2 Eun Joo Chung MD, 3 Song-I Chun PhD, 3

More information

Voxel-based Lesion-Symptom Mapping. Céline R. Gillebert

Voxel-based Lesion-Symptom Mapping. Céline R. Gillebert Voxel-based Lesion-Symptom Mapping Céline R. Gillebert Paul Broca (1861) Mr. Tan no productive speech single repetitive syllable tan Broca s area: speech production Broca s aphasia: problems with fluency,

More information

Emotion Detection Using Physiological Signals. M.A.Sc. Thesis Proposal Haiyan Xu Supervisor: Prof. K.N. Plataniotis

Emotion Detection Using Physiological Signals. M.A.Sc. Thesis Proposal Haiyan Xu Supervisor: Prof. K.N. Plataniotis Emotion Detection Using Physiological Signals M.A.Sc. Thesis Proposal Haiyan Xu Supervisor: Prof. K.N. Plataniotis May 10 th, 2011 Outline Emotion Detection Overview EEG for Emotion Detection Previous

More information

Inter-method Reliability of Brainstem Volume Segmentation Algorithms in Preschoolers with ASD

Inter-method Reliability of Brainstem Volume Segmentation Algorithms in Preschoolers with ASD Bosco, Paolo and Giuliano, Alessia and Delafield-Butt, Jonathan and Muratori, Filippo and Calderoni, Sara and Retico, Alessandra (2017) Inter-method reliability of brainstem volume segmentation algorithms

More information

Supplementary Online Content

Supplementary Online Content Supplementary Online Content Devenney E, Bartley L, Hoon C, et al. Progression in behavioral variant frontotemporal dementia: a longitudinal study. JAMA Neurol. Published online October 26, 2015. doi:10.1001/jamaneurol.2015.2061.

More information

Classification of Alzheimer s disease subjects from MRI using the principle of consensus segmentation

Classification of Alzheimer s disease subjects from MRI using the principle of consensus segmentation Classification of Alzheimer s disease subjects from MRI using the principle of consensus segmentation Aymen Khlif and Max Mignotte 1 st September, Maynooth University, Ireland Plan Introduction Contributions

More information

THE nervous system has two major divisions: the central nervous system (CNS), which consists of the brain and the spinal

THE nervous system has two major divisions: the central nervous system (CNS), which consists of the brain and the spinal MASTER THESIS DISSERTATION, MASTER IN COMPUTER VISION, SEPTEMBER 2017-1 Identification of Parkinson s and Alzheimer s diseases through the analysis of FDG-PET images using machine learning techniques Lidia

More information

The motor regulator. 2) The cerebellum

The motor regulator. 2) The cerebellum The motor regulator 2) The cerebellum Motor control systems outside the cortex Cerebellum -controls neural programs for the executionl of skilled movements Feed-back and feed-forward control circuits By

More information

Quantitative Neuroimaging- Gray and white matter Alteration in Multiple Sclerosis. Lior Or-Bach Instructors: Prof. Anat Achiron Dr.

Quantitative Neuroimaging- Gray and white matter Alteration in Multiple Sclerosis. Lior Or-Bach Instructors: Prof. Anat Achiron Dr. Quantitative Neuroimaging- Gray and white matter Alteration in Multiple Sclerosis Lior Or-Bach Instructors: Prof. Anat Achiron Dr. Shmulik Miron INTRODUCTION Multiple Sclerosis general background Gray

More information

Four Tissue Segmentation in ADNI II

Four Tissue Segmentation in ADNI II Four Tissue Segmentation in ADNI II Charles DeCarli, MD, Pauline Maillard, PhD, Evan Fletcher, PhD Department of Neurology and Center for Neuroscience, University of California at Davis Summary Table of

More information

Pediatric MS MRI Study Methodology

Pediatric MS MRI Study Methodology General Pediatric MS MRI Study Methodology SCAN PREPARATION axial T2-weighted scans and/or axial FLAIR scans were obtained for all subjects when available, both T2 and FLAIR scans were scored. In order

More information

Supplemental Data. Inclusion/exclusion criteria for major depressive disorder group and healthy control group

Supplemental Data. Inclusion/exclusion criteria for major depressive disorder group and healthy control group 1 Supplemental Data Inclusion/exclusion criteria for major depressive disorder group and healthy control group Additional inclusion criteria for the major depressive disorder group were: age of onset of

More information

Supporting Online Material for

Supporting Online Material for www.sciencemag.org/cgi/content/full/324/5927/646/dc1 Supporting Online Material for Self-Control in Decision-Making Involves Modulation of the vmpfc Valuation System Todd A. Hare,* Colin F. Camerer, Antonio

More information

Mammogram Analysis: Tumor Classification

Mammogram Analysis: Tumor Classification Mammogram Analysis: Tumor Classification Term Project Report Geethapriya Raghavan geeragh@mail.utexas.edu EE 381K - Multidimensional Digital Signal Processing Spring 2005 Abstract Breast cancer is the

More information

Finding the Augmented Neural Pathways to Math Processing: fmri Pattern Classification of Turner Syndrome Brains

Finding the Augmented Neural Pathways to Math Processing: fmri Pattern Classification of Turner Syndrome Brains Finding the Augmented Neural Pathways to Math Processing: fmri Pattern Classification of Turner Syndrome Brains Gary Tang {garytang} @ {stanford} {edu} Abstract The use of statistical and machine learning

More information

Gender Based Emotion Recognition using Speech Signals: A Review

Gender Based Emotion Recognition using Speech Signals: A Review 50 Gender Based Emotion Recognition using Speech Signals: A Review Parvinder Kaur 1, Mandeep Kaur 2 1 Department of Electronics and Communication Engineering, Punjabi University, Patiala, India 2 Department

More information

IJESRT. Scientific Journal Impact Factor: (ISRA), Impact Factor: 1.852

IJESRT. Scientific Journal Impact Factor: (ISRA), Impact Factor: 1.852 IJESRT INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY Performance Analysis of Brain MRI Using Multiple Method Shroti Paliwal *, Prof. Sanjay Chouhan * Department of Electronics & Communication

More information

Cortical hypoperfusion in Parkinson's disease assessed with arterial spin labeling MRI

Cortical hypoperfusion in Parkinson's disease assessed with arterial spin labeling MRI Cortical hypoperfusion in Parkinson's disease assessed with arterial spin labeling MRI Poster No.: C-0609 Congress: ECR 2013 Type: Scientific Exhibit Authors: S. Aoki, K. Kamagata, Y. Motoi, K. Kamiya,

More information

9.14 Class 32 Review. Limbic system

9.14 Class 32 Review. Limbic system 9.14 Class 32 Review Limbic system 1 Lateral view Medial view Brainstem, sagittal section Sensory- Perceptual Motor Behavior Major functional modules of the CNS Motivation Courtesy of MIT Press. Used with

More information

Neuroimaging and Assessment Methods

Neuroimaging and Assessment Methods Psych 2200, Lecture 5 Experimental Design and Brain Imaging Methods Tues Sept 15, 2015 Revised TA office hours (Sam), today 4-5p, and wed 11:30-1:30. I will not have office hours this thurs but you should

More information

Clinical applications of real-time fmri neurofeedback in 6 steps

Clinical applications of real-time fmri neurofeedback in 6 steps Training course: Real-time fmri: Fundamental Principles for Clinical Applications Clinical applications of real-time fmri neurofeedback in 6 steps David Linden Cardiff University 1) What is your clinical

More information

Online appendices are unedited and posted as supplied by the authors. SUPPLEMENTARY MATERIAL

Online appendices are unedited and posted as supplied by the authors. SUPPLEMENTARY MATERIAL Appendix 1 to Sehmbi M, Rowley CD, Minuzzi L, et al. Age-related deficits in intracortical myelination in young adults with bipolar SUPPLEMENTARY MATERIAL Supplementary Methods Intracortical Myelin (ICM)

More information

Effective Diagnosis of Alzheimer s Disease by means of Association Rules

Effective Diagnosis of Alzheimer s Disease by means of Association Rules Effective Diagnosis of Alzheimer s Disease by means of Association Rules Rosa Chaves (rosach@ugr.es) J. Ramírez, J.M. Górriz, M. López, D. Salas-Gonzalez, I. Illán, F. Segovia, P. Padilla Dpt. Theory of

More information

Introduction to the Central Nervous System: Internal Structure

Introduction to the Central Nervous System: Internal Structure Introduction to the Central Nervous System: Internal Structure Objective To understand, in general terms, the internal organization of the brain and spinal cord. To understand the 3-dimensional organization

More information

Characterizing Anatomical Variability And Alzheimer s Disease Related Cortical Thinning in the Medial Temporal Lobe

Characterizing Anatomical Variability And Alzheimer s Disease Related Cortical Thinning in the Medial Temporal Lobe Characterizing Anatomical Variability And Alzheimer s Disease Related Cortical Thinning in the Medial Temporal Lobe Long Xie, Laura Wisse, Sandhitsu Das, Ranjit Ittyerah, Jiancong Wang, David Wolk, Paul

More information

The Human Brain. I Think Therefore I am

The Human Brain. I Think Therefore I am The Human Brain I Think Therefore I am The Beginning The simplest creatures have very simple nervous systems made up of nothing but a bunch of nerve cells They have neural nets, individual neurons linked

More information

Neuropathology of Neurodegenerative Disorders Prof. Jillian Kril

Neuropathology of Neurodegenerative Disorders Prof. Jillian Kril Neurodegenerative disorders to be discussed Alzheimer s disease Lewy body diseases Frontotemporal dementia and other tauopathies Huntington s disease Motor Neuron Disease 2 Neuropathology of neurodegeneration

More information

Myers Psychology for AP*

Myers Psychology for AP* Myers Psychology for AP* David G. Myers PowerPoint Presentation Slides by Kent Korek Germantown High School Worth Publishers, 2010 *AP is a trademark registered and/or owned by the College Board, which

More information

Unit 3: The Biological Bases of Behaviour

Unit 3: The Biological Bases of Behaviour Unit 3: The Biological Bases of Behaviour Section 1: Communication in the Nervous System Section 2: Organization in the Nervous System Section 3: Researching the Brain Section 4: The Brain Section 5: Cerebral

More information

biological psychology, p. 40 The study of the nervous system, especially the brain. neuroscience, p. 40

biological psychology, p. 40 The study of the nervous system, especially the brain. neuroscience, p. 40 biological psychology, p. 40 The specialized branch of psychology that studies the relationship between behavior and bodily processes and system; also called biopsychology or psychobiology. neuroscience,

More information

Cerebral Cortex 1. Sarah Heilbronner

Cerebral Cortex 1. Sarah Heilbronner Cerebral Cortex 1 Sarah Heilbronner heilb028@umn.edu Want to meet? Coffee hour 10-11am Tuesday 11/27 Surdyk s Overview and organization of the cerebral cortex What is the cerebral cortex? Where is each

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

Methods to examine brain activity associated with emotional states and traits

Methods to examine brain activity associated with emotional states and traits Methods to examine brain activity associated with emotional states and traits Brain electrical activity methods description and explanation of method state effects trait effects Positron emission tomography

More information

Early Diagnosis of Autism Disease by Multi-channel CNNs

Early Diagnosis of Autism Disease by Multi-channel CNNs Early Diagnosis of Autism Disease by Multi-channel CNNs Guannan Li 1,2, Mingxia Liu 2, Quansen Sun 1(&), Dinggang Shen 2(&), and Li Wang 2(&) 1 School of Computer Science and Engineering, Nanjing University

More information

Update on functional brain imaging in Movement Disorders

Update on functional brain imaging in Movement Disorders Update on functional brain imaging in Movement Disorders Mario Masellis, MSc, MD, FRCPC, PhD Assistant Professor & Clinician-Scientist Sunnybrook Health Sciences Centre University of Toronto 53 rd CNSF

More information

DIADEM Instructions for Use

DIADEM Instructions for Use Software Version: 1.0.0 Document Version: 3.0 July 2017 Contents 1 Intended Use... 4 2 Scanning... 5 2.1 Automatic Operation... 5 2.2 Suitable Scans... 5 2.2.1 Protocols... 5 2.2.2 Brain Coverage... 5

More information

An Improved Algorithm To Predict Recurrence Of Breast Cancer

An Improved Algorithm To Predict Recurrence Of Breast Cancer An Improved Algorithm To Predict Recurrence Of Breast Cancer Umang Agrawal 1, Ass. Prof. Ishan K Rajani 2 1 M.E Computer Engineer, Silver Oak College of Engineering & Technology, Gujarat, India. 2 Assistant

More information

Segmentation of Normal and Pathological Tissues in MRI Brain Images Using Dual Classifier

Segmentation of Normal and Pathological Tissues in MRI Brain Images Using Dual Classifier 011 International Conference on Advancements in Information Technology With workshop of ICBMG 011 IPCSIT vol.0 (011) (011) IACSIT Press, Singapore Segmentation of Normal and Pathological Tissues in MRI

More information

WHAT DOES THE BRAIN TELL US ABOUT TRUST AND DISTRUST? EVIDENCE FROM A FUNCTIONAL NEUROIMAGING STUDY 1

WHAT DOES THE BRAIN TELL US ABOUT TRUST AND DISTRUST? EVIDENCE FROM A FUNCTIONAL NEUROIMAGING STUDY 1 SPECIAL ISSUE WHAT DOES THE BRAIN TE US ABOUT AND DIS? EVIDENCE FROM A FUNCTIONAL NEUROIMAGING STUDY 1 By: Angelika Dimoka Fox School of Business Temple University 1801 Liacouras Walk Philadelphia, PA

More information

Medical Neuroscience Tutorial

Medical Neuroscience Tutorial Pain Pathways Medical Neuroscience Tutorial Pain Pathways MAP TO NEUROSCIENCE CORE CONCEPTS 1 NCC1. The brain is the body's most complex organ. NCC3. Genetically determined circuits are the foundation

More information

Validation of basal ganglia segmentation on a 3T MRI template

Validation of basal ganglia segmentation on a 3T MRI template Validation of basal ganglia segmentation on a 3T MRI template Claire Haegelen, Nicolas Guizard, Pierrick Coupé, Florent Lalys, Pierre Jannin, Xavier Morandi, D. Louis Collins To cite this version: Claire

More information

MRI Image Processing Operations for Brain Tumor Detection

MRI Image Processing Operations for Brain Tumor Detection MRI Image Processing Operations for Brain Tumor Detection Prof. M.M. Bulhe 1, Shubhashini Pathak 2, Karan Parekh 3, Abhishek Jha 4 1Assistant Professor, Dept. of Electronics and Telecommunications Engineering,

More information

Supplementary information Detailed Materials and Methods

Supplementary information Detailed Materials and Methods Supplementary information Detailed Materials and Methods Subjects The experiment included twelve subjects: ten sighted subjects and two blind. Five of the ten sighted subjects were expert users of a visual-to-auditory

More information

Automated detection of abnormal changes in cortical thickness: A tool to help diagnosis in neocortical focal epilepsy

Automated detection of abnormal changes in cortical thickness: A tool to help diagnosis in neocortical focal epilepsy Automated detection of abnormal changes in cortical thickness: A tool to help diagnosis in neocortical focal epilepsy 1. Introduction Epilepsy is a common neurological disorder, which affects about 1 %

More information

fmri and Voxel-based Morphometry in Detection of Early Stages of Alzheimer's Disease

fmri and Voxel-based Morphometry in Detection of Early Stages of Alzheimer's Disease fmri and Voxel-based Morphometry in Detection of Early Stages of Alzheimer's Disease Andrey V. Sokolov 1,3, Sergey V. Vorobyev 2, Aleksandr Yu. Efimtcev 1,3, Viacheslav S. Dekan 1,3, Gennadiy E. Trufanov

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/1887/32078 holds various files of this Leiden University dissertation Author: Pannekoek, Nienke Title: Using novel imaging approaches in affective disorders

More information

Twelve right-handed subjects between the ages of 22 and 30 were recruited from the

Twelve right-handed subjects between the ages of 22 and 30 were recruited from the Supplementary Methods Materials & Methods Subjects Twelve right-handed subjects between the ages of 22 and 30 were recruited from the Dartmouth community. All subjects were native speakers of English,

More information