Automated Identification of Neoplasia in Diagnostic Imaging text reports

Similar documents
Application of Automated Pathology Reporting Concepts to Radiology Reports

HEAD AND NECK IMAGING. James Chen (MS IV)

NEURORADIOLOGY DIL part 5

Pathologic Analysis of CNS Surgical Specimens

Structural and functional imaging for the characterization of CNS lymphomas

Enhancement of Cranial US: Utility of Supplementary Acoustic Windows and Doppler Harriet J. Paltiel, MD

SWI including phase and magnitude images

The central nervous system

Cerebro-vascular stroke

CT & MRI Evaluation of Brain Tumour & Tumour like Conditions

Detection of Leptomeningeal CNS Metastases in Children

Masses of the Corpus Callosum

Head CT Scan Interpretation: A Five-Step Approach to Seeing Inside the Head Lawrence B. Stack, MD

CT - Brain Examination

1 MS Lesions in T2-Weighted Images

NEURO IMAGING 2. Dr. Said Huwaijah Chairman of radiology Dep, Damascus Univercity

NEURO IMAGING OF ACUTE STROKE

Benign brain lesions

Case 7391 Intraventricular Lesion

Diffusion-weighted imaging and ADC mapping in the differentiation of intraventricular brain tumors

MRI XR, CT, NM. Principal Modality (2): Case Report # 2. Date accepted: 15 March 2013

Improved Detection of Clinically Significant Prostate Cancer Using a Structured Prostate Imaging Reporting Data System (PI-RADS) Template

Keep Imaging Simple: An Introduction To Neuroimaging

Posterior fossa tumors: clues to differential diagnosis with case-based review

EEG IN FOCAL ENCEPHALOPATHIES: CEREBROVASCULAR DISEASE, NEOPLASMS, AND INFECTIONS

How to read the report

brain MRI for neuropsychiatrists: what do you need to know

For Emergency Doctors. Dr Suzanne Smallbane November 2011

Cerebral malaria: MR imaging spectrum

Index. aneurysm, 92 carotid occlusion, 94 ICA stenosis, 95 intracranial, 92 MCA, 94

RINGS N THINGS: Imaging Patterns in Differential Diagnosis. Anne G. Osborn, M.D.

Pearls and Pitfalls in Neuroradiology of Cerebrovascular Disease The Essentials with MR and CT

MRI Findings Of An Atypical Cystic Meningioma A Rare Case

41 year old female with headache. Elena G. Violari MD and Leo Wolansky MD

Joana Ramalho, MD C. Ryan Miller, MD, PhD

Case 9511 Hypertensive microangiopathy

Semiotics in Radiology

1 Uniform hyperintense signal intensity (normal). 2 Linear (arrow), wedge-shaped, or diffuse mild hypointensity, usually indistinct margin.

SURGICAL MANAGEMENT OF BRAIN TUMORS

Pediatric CNS Tumors. Disclosures. Acknowledgements. Introduction. Introduction. Posterior Fossa Tumors. Whitney Finke, MD

MRI OF THE THALAMUS. Mohammed J. Zafar, MD, FAAN Kalamazoo, MI

Role of Diffusion weighted Imaging in the Evaluation of Intracranial Tumors

Essentials of Clinical MR, 2 nd edition. 73. Urinary Bladder and Male Pelvis

Supratentorial Gangliocytoma Mimicking Extra-axial Tumor: A Report of Two Cases

Neurosonography: State of the art

CT and MR findings of systemic lupus erythematosus involving the brain: Differential diagnosis based on lesion distribution

Intracranial Lesions: MRI Signs for Localization

Disclosures. Posterior Fossa Masses. I m from the Government. and I here to help! Differential Diagnosis

NEURORADIOLOGY Part I

ISCHEMIC STROKE IMAGING

CNS Imaging. Dr Amir Monir, MD. Lecturer of radiodiagnosis.

Helpful Information for evaluation of new neurological symptoms in patients receiving TYSABRI

Astroblastoma: Radiologic-Pathologic Correlation and Distinction from Ependymoma

Hypoxic ischemic brain injury in neonates - early MR imaging findings

Oligodendroglioma: imaging findings, radio-pathological correlation and evolution

Disclosure. + Outline. Case-based approach to neurological emergencies that might present to the ED

Prostate MRI: Not So Difficult. Neil M. Rofsky, MD, FACR, FSCBTMR, FISMRM Dallas, TX

FINALIZED SEER SINQ QUESTIONS

Student Lab #: Date. Lab: Gross Anatomy of Brain Sheep Brain Dissection Organ System: Nervous Subdivision: CNS (Central Nervous System)

PRESERVE: How intensively should we treat blood pressure in established cerebral small vessel disease? Guide to assessing MRI scans

CASE OF THE WEEK PROFESSOR YASSER METWALLY

11/10/2015. Prostate cancer in the U.S. Multi-parametric MRI of Prostate Diagnosis and Treatment Planning. NIH estimates for 2015.

Attenuation value in HU From -500 To HU From -10 To HU From 60 To 90 HU. From 200 HU and above

Anoxic brain injury CT and MRI patterns - quick pictoral quide for junior radiologists.

NEURORADIOLOGY Angela Lignelli, MD

NEURORADIOLOGY Angela Lignelli, MD

Primary Central Nervous System Lymphoma with Lateral Ventricle Involvement

Role of imaging (images) in my practice. Dr P Senthur Nambi Consultant Infectious Diseases

MRI and differential diagnosis in patients suspected of having MS

Medical Neuroscience Tutorial Notes

How to interpret an unenhanced CT brain scan. Part 2: Clinical cases

Imaging The Turkish Saddle. Russell Goodman, HMS III Dr. Gillian Lieberman

Acute Ischaemic Stroke

Case Report Intracranial Capillary Hemangioma in the Posterior Fossa of an Adult Male

NEURO PROTOCOLS MRI NEURO PROTOCOLS (SIEMENS SCANNERS)

Clinics in diagnostic imaging (175)

CNS TUMORS. D r. Ali Eltayb ( U. of Omdurman. I ). M. Path (U. of Alexandria)

Vascular Malformations of the Brain: A Review of Imaging Features and Risks

2/20/2019 BRAIN DISSECTION CODING AND DOCUMENTATION OBJECTIVES INTRODUCTION

Thursday, January 24, 2019

Analysis between clinical and MRI findings of childhood and teenages with epilepsy after hypoxic-ischemic encephalopathy in neonates periods

Non-Traumatic Neuro Emergencies

A pictorial review of neurological complications of systemic lupus erythematosus and antiphospholipid syndrome

Neonatal hypoxic-ischemic brain injury imaging: A pictorial review

An Introduction to Imaging the Brain. Dr Amy Davis

CT and MRI Findings of Intracranial Lymphoma

Pediatric MS MRI Study Methodology

Imaging the Spinal Cord & Intradural Disease

A New Trend in Vascular Imaging: the Arterial Spin Labeling (ASL) Sequence

Cross sectional imaging of Intracranial cystic lesions Abdel Razek A

General Identification. Name: 江 X X Age: 29 y/o Gender: Male Height:172cm, Weight: 65kg Date of admission:95/09/27

Brain Tumors. Medulloblastoma. Pilocytic astrocytoma: Ahmed Koriesh, MD. Pathological finding

Acute stroke. Ischaemic stroke. Characteristics. Temporal classification. Clinical features. Interpretation of Emergency Head CT

Organization of The Nervous System PROF. MOUSAED ALFAYEZ & DR. SANAA ALSHAARAWY

[(PHY-3a) Initials of MD reviewing films] [(PHY-3b) Initials of 2 nd opinion MD]

Table of Contents: SKULL AND BRAIN. Scalp, Skull. Anatomically Based Differentials. Skull Normal Variants. Scalp Mass, Child.

Insults to the Term Brain

IMAGING OF HYPOXIC ISCHEMIC INJURY IN A NEONATE FN3 STATE MEETING NEMOURS CHILDREN'S HOSPITAL ORLANDO,FL 08/04/18

Meningeal thickening in MRI: from signs to etiologies

Essentials of Clinical MR, 2 nd edition. 14. Ischemia and Infarction II

Transcription:

Automated Identification of Neoplasia in Diagnostic Imaging text reports "This work has been funded in whole or in part with Federal funds from the National Cancer Institute, National Institutes of Health, Department of Health and Human Services, under Contract No. HHSN261200900040C George Cernile Artificial Intelligence in Medicine, Inc. Suzanne March QuantumMark LLC.

Objective To extend the use of natural language programming techniques to other sources of data beyond pathology reports.

Introduction The Team QuantumMark PI & Project Management AIM - Knowledge Engineering & Development April Fritz & Associates Domain Expertise, Cancer Registrar Participating Institutions 12 data providers including registries, labs and hospitals

Radiology Reports HMR 0013 - MRI BRAIN W/WO CONTRAST - Aug 1 2007 FINDINGS: MRI of the brain with contrast. Clinical Indication: 82-year-old female with history of meningioma. Technique: MRI of the brain was obtained using the following sequences:sagittal T1, axial T1, axial FLAIR, axial T2, axial diffusion, axial ADC, axial postcontrast T1, and coronal postcontrast T1 weighted sequences. Comparison: comparison is made to an MRI of the brain from an outside institution (Downey Regional Med Ctr) dated 12/5/2006. There are no extra-axial fluid collections. A right frontal extra-axial parasagittal mass demonstrating isointense T1 signal to gray matter and intermediate to high signal intensity on T2 images with marked homogeneous enhancement postcontrast is noted to measure 2.6 cm transverse x 3.4 cm AP x 3.5 cm craniocaudal. Marrow signal changes in the calvarium abutting the mass are suspicious for interosseous involvement. When compared to the prior study of 12/5/2006, the size and appearance of the mass demonstrates no significant change. There is a minimal to mild mass effect on the adjacent right frontal lobe without evidence of edema. The cerebellum demonstrates mild atrophy. The brainstem appears normal. There are no parenchymal masses or midline shift. The are no restricted diffusion abnormalities. Mild right anterior ethmoid sinus mucosal disease is noted. A minimal amount of fluid is noted in the right mastoid air cells. The orbits, remaining paranasal sinuses, and calvarium are unremarkable. IMPRESSION: 1. Right frontal parasagittal meningioma, relatively unchanged in size and appearance when compared to the prior outside study dated 12/5/2006, including marrow signal changes in the calvarium adjacent to the lesion suggestive of intraosseous involvement. 2. Nonspecific white matter disease as described above, likely reflecting chronic ischemic changes. 3. Mild right anterior ethmoid sinus mucosal disease. Minimal amount of fluid noted in the right mastoid air cells.. The ventricles and cortical sulci are prominent consistent with mild to moderate cerebral atrophy. There is no hydrocephalus. The supratentorial brain parenchyma demonstrates scattered foci of T2 and FLAIR hyperintensities noted throughout the periventricular, subcortical, and deep white matter of both cerebral hemispheres, which are nonspecific, and likely represents chronic ischemic changes. The bilateral basal ganglia demonstrate T2 and FLAIR hypointensity.

Imaging terms 1 st pass Term Select Term Select hyperintensity FLAIR hyperintensity T2-weighted white matter change STIR hyperintensity T2 hyperintensity leukomalacic changes abnormal density white matter Yes choroid plexus cyst mass effect Maybe demyelinating disease. abnormal enhancement Maybe brain tumor Yes high density lesions heterogeneous enhancement Yes low density lesions Yes infarction / infarct abnormalities Maybe white matter signal abnormality abnormal enhancement chiari malformation small vessel disease chronic ischemic change extraaxial mass lesions Yes low attenuation changes Maybe increased signal intensity Maybe Edema / Oedema abnormal signal intensity Yes vasogenic Edema/Eodema Yes enhancement Yes BBB (Blood Brain Barrier) Yes pathologic mass Yes Infiltrative lesion Yes increased density Yes tumor Maybe retention cyst. Selection Rate > 30%

Imaging terms 2 nd pass Term Select Term Select hyperintensity FLAIR hyperintensity T2-weighted white matter change STIR hyperintensity T2 hyperintensity leukomalacic changes abnormal density white matter choroid plexus cyst mass effect Maybe demyelinating disease. abnormal enhancement brain tumor Yes high density lesions heterogeneous enhancement low density lesions infarction / infarct abnormalities white matter signal abnormality abnormal enhancement chiari malformation small vessel disease chronic ischemic change extraaxial mass lesions Yes low attenuation changes increased signal intensity Edema / Oedema abnormal signal intensity vasogenci Edema/Eodema enhancement BBB (Blood Brain Barrier) pathologic mass Yes Infiltrative lesion Yes increased density tumor Maybe retention cyst. Selection Rate ~ 10% 6

Process Clinical Indication Section % Selected with and without section filter 30 25 24 20 15 14 15 16 No Clin Indication With Clin Indication 10 7 9 5 0 Reno USC Desert

Phase I Results 12000 Selected 853 (8.7%) 10000 Selected 656 (7.3%) 8000 6000 Selected TOTAL 4000 TOTAL, 9796 TOTAL, 9023 2000 Selected, 144 (14.6%) 0 TOTAL, 983 Desert Radiology RENO Diagnostics USC

Phase II Installed into 3 registries and an initial run was done to determine performance and receive feedback. Different requirements One registry was very sensitive to false positives, and in fact wanted only tumors that were new to the registry. Another registry wanted all cancers for follow-up with existing registry data.

Two different case-findings 1. Identify reports of the diagnosis, differential diagnosis, metastasis or history of primary CNS neoplasms or non CNS neoplasms of behavior greater than 2. 2. Identification of a diagnosis or differential diagnosis of a primary CNS neoplasm.

Bundle Sensitivity and Specificity Results for QC Study 1289 Reports True Positive True Negative False Positive False Negative Sensitivity Specificity B0096 4 90 2 0 100% 97.8% B0097 16 81 3 0 100% 96.4% B0098 13 78 4 0 100% 95.1% B0103 5 93 1 1 83.3% 98.9% B0108 15 83 2 0 100% 97.6% B0110 10 88 2 0 100% 97.8% B0111 1 92 6 0 100% 93.9% B0112 10 87 2 0 100% 97.8% B0113 7 90 3 0 100% 96.8% B0115 15 78 7 0 100% 91.8% B0116 13 86 1 0 100% 98.9% B0117 10 86 4 0 100% 95.6% B0118 5 91 3 1 83.3% 96.8% Total 124 1123 40 2 98.4% 96.6% 11

Extended Classifications Negative History of cancer Metastatic tumor Positive previously known Positive This information would allow increased decision making as well as provide information to registries.

Report classification Classification History of Metastatic CNS Non CNS 1 Negative - - - - 2 History yes - - yes 3 Metastatic implied Yes implied implied 4 Positive previously known yes - yes - 5 Positive - - yes -

What about Sensitivity and Specificity? Classification History of Metastatic CNS Non CNS 1 Negative - - - - 2 History yes - - yes 3 Metastatic implied Yes implied implied 4 Positive previously known yes - yes - 5 Positive - - yes -

What about Sensitivity and Specificity? Classification History of Metastatic CNS Non CNS 1 Negative - - - - 2 History yes - - yes 3 Metastatic implied Yes implied implied 4 Positive previously known yes - yes - 5 Positive - - yes -

What about Sensitivity and Specificity? Classification History of Metastatic CNS Non CNS 1 Negative - - - - 2 History yes - - yes 3 Metastatic implied Yes implied implied 4 Positive previously known yes - yes - 5 Positive - - yes -

What about Sensitivity and Specificity? Classification History of Metastatic CNS Non CNS 1 Negative - - - - 2 History yes - - yes 3 Metastatic implied Yes implied implied 4 Positive previously known yes - yes - 5 Positive - - yes -

Positive Previously Known Resection medulloblastoma Post surgical change

Positive Pituitary gland microadenoma and no other neoplasm

History of cancer History of prostate cancer No other neoplasm

Metastatic History of renal cancer with lesions on frontal lobe

Negative 1 History of Metastatic 2 4 3 Positive 5 CNS

Results Bundle True Positive True Negative False Positive False Negative Sensitivity Specificity B0076 12 82 5 1.923.942 B0077 13 83 2 1.929.976 B1011 113 78 9 0 1.897 B1012 78 22 0 0 1 1 B1022 84 8 6 2.977.571 B1023 86 8 6 0 1.571 Total Normal distribution 280 1134 67 15.949.944 Total Positive enriched 1981 202 94 25.988.682 Total Combined 2261 1336 161 40.982.892

Problem

What about sites beyond CNS? Attempted to process Pancreas and biliary reports. Not specific enough to isolate only to these organs Would have produced lots of reports that were already in registry, eg: liver biopsy, etc..

Tried to include Biliary, Pancreas reports problem!

Production system Standardized Format Standardized Format 1 2 3 5 6 Dx Imaging Identification & Sending Receipt & Review Ca Registry Data HL7/XML Integration Coding and Filtering Secure IP Network HL7/XML Integration Data Review (optional) Data Siemens GE Hitachi Phillips Toshiba Fonar Etc. AIM Interfaceware Orion Mitem etransx Etc. 4 Impac Oncolog ERS Seer DMS CDC C/Next Etc. CNS Neoplasm Lexicon

Conclusion System implemented at three pilot sites QC studies will commence to determine Sensitivity/Specificity for selectable reports Determine accuracy in supplementary classifications System can be used as E-path add-on, or as standalone