Managed by UT-Battelle for the Department of Energy Learning Cue Phrase Patterns from Radiology Reports Using a Genetic Algorithm Robert M. Patton, Ph.D.

Slides:



Advertisements
Similar presentations
Golan.O, Sperber.F, Shalmon.A, Weinstein.I, Gat.A
Advertisements

The role of ultrasound in breast imaging Dr Francien Malan Drs Van Wageningen & Vennote 31 October 2007.
1 FDA Radiological Devices Panel Meeting March 4-5, 2008 Mammography CAD Devices Robert C. Smith, MD, JD Medical Officer (Radiologist) Division of Reproductive,
COMPUTATIONAL INTELLIGENCE FOR THE DETECTION AND CLASSIFICATION OF MALIGNANT LESIONS IN SCREENING MAMMOGRAPHY DATA E. Panourgias,
Computer Aided Diagnosis: CAD overview
· Information gathering · Data analysis · Decision making · “ Human life is too important to be left to a computer “ Patients receive the best treatment.
MCQs On Breast Imaging:
A Computer Aided Detection System For Digital Mammograms Based on Radial Basis Functions and Feature Extraction Techniques By Mohammed Jirari Shanghai,
A Computer-Aided Diagnosis System For Digital Mammograms Based on Radial Basis Functions and Feature Extraction Techniques Dissertation written by Mohammed.
In The Nam of God.
A Computer Aided Detection System For Mammograms Based on Asymmetry and Feature Extraction Techniques By Mohammed Jirari Benidorm, Spain Sept 9th, 2005.
February 13, 1997CWU B.Kovalerchuk1 DESIGN OF CONSISTENT SYSTEM FOR RADIOLOGISTS TO SUPPORT BREAST CANCER DIAGNOSIS.
Automatic Detection And Classification Of Microcalcifications In Digital Mammograms Institute for Brain and Neural Systems Brown University Providence.
Breast Neoplasm In this section we will be discussing breast neoplasm.
What to Expect When a Lump Is Detected
BREAST IMAGING Claudia E. Galbo,M.D. USUHS Department of Radiology and Radiological Sciences.
Breast Imaging Made Brief and Simple
Normal Ultrasound Protocol Breast
Faculty of Medicine - Benha University
Tissue Sampling Options Lisa A. Newman, M.D., M.P.H., F.A.C.S. Professor of Surgery Director, Breast Care Center University of Michigan Ann Arbor, MI.
FINE - NEEDLE ASPIRATION BIOPSY By Dr. Tarek Atia.
In The Nam of God.
Background on: Breast Cancer, X-Ray and MRI Mammography
BI-RADS By Nina Zahedi MD.
Bayesian Network for Predicting Invasive and In-situ Breast Cancer using Mammographic Findings Jagpreet Chhatwal1 O. Alagoz1, E.S. Burnside1, H. Nassif1,
MAMOGRAPHY. Mammography is the process of using low- energy X-rays (usually around 30 kVp) to examine the human breast, which is used as a diagnostic.
Approach to a thyroid nodule
Marion C.W. Henry, MD Yale University
AJCC Staging Moments AJCC TNM Staging 7th Edition Breast Case #1 Contributors: Stephen B. Edge, MD Roswell Park Cancer Institute, Buffalo, New York David.
MedPix Medical Image Database COW - Case of the Week Case Contributor: Russell A. Patterson Affiliation: Uniformed Services University.
MAMMOGRAPHY - Pt 2 EQUIPMENT LECTURE & more….. RTEC 255 Week # 3 D. CHARMAN, M.Ed.,R.T.(R,M)
What’s Next After an Abnormal Screening Mammogram? James A Stewart M.D. Elizabeth Burnside M.D.
Imaging examinations of breasts
Introduction to Breast Imaging BREAST RAD LAB Directions: Please answer all the questions prior to interactive conference. 1.
Integrating Machine Learning and Physician Knowledge to Improve the Accuracy of Breast Biopsy Inês Dutra University of Porto, CRACS & INESC-Porto LA Houssam.
Introduction to Clinical Radiology: The Breast
How will you approach the 35-year old, with a 2x2x2cm, firm, mobile, well-circumscribed non-tender mass on her R breast?
3D Mammography Ernesto Coto Sören Grimm Stefan Bruckner M. Eduard Gröller Institute of Computer Graphics and Algorithms Vienna University of Technology.
BREAST CANCER: Half a million women later… Amy Miglani M.D September 3, 2004.
Biometrics % Biostatistics
Information Extraction for Clinical Data Mining: A Mammography Case Study H. Nassif, R. Woods, E. Burnside, M. Ayvaci, J. Shavlik and D. Page University.
Examination of Pathology Demonstration of Thyroid Nodules And the Post Thyroidectomy Neck.
Automatic extraction of BI-RADS breast tissue composition classes from mammography reports Bethany Percha (Stanford) Houssam Nassif (U. Wisconsin) Jafi.
THIRD CLASSIFICATION OF MICROCALCIFICATION STAGES IN MAMMOGRAPHIC IMAGES THIRD REVIEW Supervisor: Mrs.P.Valarmathi HOD/CSE Project Members: M.HamsaPriya( )
MAMMOGRAM COLLAGE OF MEDICINE /RADIOLOGY DEPARTMENT.
BREAST: anatomy, imaging techniques & clinical/radiological cases
Thursday Case of the Day History: The hypothetical results from a clinical trial of computer-aided detection (CADe) used in mammographic screening of 5,000,000.
Figure 1: a 32-year-old woman presented with RT breast mass, MRI showed false positive diagnosis of cancer. Dynamic contrast enhanced MRI, axial subtraction.
Case D Karmi Margaret G. Marcial. How will you approach the 35-year old, with a 2 x 2 x 2cm, firm, mobile, well-circumscribed non-tender mass on her R.
MAMMOGRAPHY Positioning & Anatomy
Kanjanaporn Mahatthanaphak
Indications for Breast MR Imaging
BREAST IMAGING.
Volume 39, Issue 4, Pages (July 2015)
Contrast-enhanced Dedicated Breast CT: Initial Clinical Experience
Example 4: (A,B) Standard CC and MLO views of the right breast in this screening mammogram for a 60-year-old woman who never had any prior mammograms.
Is Ductal Carcinoma In Situ With “Possible Invasion” More Predictive of Invasive Carcinoma Than Pure Ductal Carcinoma In Situ?  Tal Arazi-Kleinman, MD,
Variable Appearances of Ductal Carcinoma In Situ Calcifications on Digital Mammography, Synthesized Mammography, and Tomosynthesis: A Pictorial Essay 
Pathologic Upgrade Rates of High-Risk Breast Lesions on Digital Two-Dimensional vs Tomosynthesis Mammography  Leslie R. Lamb, MD, MSc, Manisha Bahl, MD,
Beyond Mammography: New Frontiers in Breast Cancer Screening
Imaging Approaches and Findings in the Reconstructed Breast: A Pictorial Essay  Anabel M. Scaranelo, MD, PhD, Bridgette Lord, RN, NP, MN, Riham Eiada,
Mammography and Breast Localization for the Interventionalist
Current Status of Breast Ultrasound
Jeong Mi Park, MD, Limin Yang, MD, PhD, Archana Laroia, MD, Edmund A
Mammography and Breast Localization for the Interventionalist
Pathologic Upgrade Rates of High-Risk Breast Lesions on Digital Two-Dimensional vs Tomosynthesis Mammography  Leslie R. Lamb, MD, MSc, Manisha Bahl, MD,
Avoiding Pitfalls in Mammographic Interpretation
Jeong Mi Park, MD, Limin Yang, MD, PhD, Archana Laroia, MD, Edmund A
Marion C.W. Henry, MD Yale University
imaging modalities for Breast screening
Presentation transcript:

Managed by UT-Battelle for the Department of Energy Learning Cue Phrase Patterns from Radiology Reports Using a Genetic Algorithm Robert M. Patton, Ph.D. Applied Software Engineering Research

2Managed by UT-Battelle for the Department of Energy Current Status  Worldwide, more women than ever are getting mammograms: –Radiologists cannot keep up with the growing number of readings they are facing –Growing shortage of radiologists –Human error in reading the images –Exams may do not necessarily take into consideration the patient’s prior exams –Computer-aided Detection (CAD) systems still need improvement Images courtesy of Memorial Sloan-Kettering Cancer Center via

3Managed by UT-Battelle for the Department of Energy Challenges  What is “normal”? What is “abnormal”?  Reports vary widely in the words that are used regardless of Bi-RADS rating  Some radiologists “talk” a lot (i.e., very wordy reports), while other radiologists say very little  Longitudinal view: 1 patient may have N radiologists

4Managed by UT-Battelle for the Department of Energy Characteristics of Reports  Abnormal reports tend to have a wider variation in the language that is used  Normal reports use more negation phrases than abnormal reports –“no new focal masses” –“no radiographic lesions seen”  Multiple ways to say the same thing –“no radiographic evidence of malignancy” –“no mammographic findings of malignancy”

5Managed by UT-Battelle for the Department of Energy Example Reports Normal

6Managed by UT-Battelle for the Department of Energy Example Reports Abnormal

7Managed by UT-Battelle for the Department of Energy Multiple ways to say the same thing  Use skip grams (s-grams) to represent patterns of phrases that have similar meaning  S-grams are word pairs in their respective sentence order that allow for arbitrary gaps between the words  Example: –“no radiographic evidence of malignancy” –“no mammographic findings of malignancy” –S-gram: the words “no” & “malignancy”

8Managed by UT-Battelle for the Department of Energy Mammogram Classifier  Goal: Develop classifier based on s-grams that will distinguish between abnormal and normal reports using no labeled data or training set (unsupervised learning)  Classifier based on Maximum Variation Sampling implemented as a Genetic Algorithm (GA) –1 st Objective: Identify the most diverse reports (typically, abnormal reports), then extract the s-grams that they have in common –2 nd Objective: From the failed individuals in the GA (typically, normal reports), extract the negation s-grams that they have in common

9Managed by UT-Battelle for the Department of Energy Maximum Variation Sampling  Non-probabilistic sampling technique  Seeks to identify a sample that represents the largest diversity of data in the population  Abnormal reports are easily identified with this approach without any need for prior labeling or use of keywords –Abnormal reports tend to be longer and use diverse and unique language than normal reports  Implemented using a genetic algorithm

10Managed by UT-Battelle for the Department of Energy GA Implementation  Genetic Representation: Sample size of N –Each gene value is a unique, real-valued document ID  Fitness Function –Minimize the following fitness function Document 1Document 2….Document N Gene 1Gene 2….Gene N Individual i

11Managed by UT-Battelle for the Department of Energy Data Set  Primary data set consists of 9,000 patients studied over 5 year period  120,000 reports –Duplicate reports –Cancellation reports

12Managed by UT-Battelle for the Department of Energy Top Ten S-grams from MVS-GA best solution RankS-gramExample Observed Variants 1 left & breastleft breast demonstrating apparent distortion core & biopsy stereotactic guided core biopsy of microcalcification compression & views additional bilateral anterior compression mlo views spot & viewslaterally exaggerated craniocaudal spot views838 5 magnification & views magnification views requested648 6 spot & compression mediolateral oblique spot compression views needle & localization ultrasound-guided needle localization procedure nodular & density showing questionable increased nodular density lymph & nodeatypically located intramammary lymph node spot & magnification breasts requiring spot magnification imaging624

13Managed by UT-Battelle for the Department of Energy Top Ten S-grams with the word "no" RankS-gramExample Observed Variants 1 no & suspiciousno finding strongly suspicious no & massesno new focal masses365 3 no & focalno dominant focal lesion210 4 no & evidenceno evidence of cyst716 5 no & specificno specific palpable abnormality detected187 6 no & findingsno current physical findings308 7 no & massno development of abnormal dominant mass534 8 no & mammographic no persisting mammographic abnormalities390 9 no & radiographicno radiographic lesions seen no & calcificationsno clear cut clustered punctate calcifications138

14Managed by UT-Battelle for the Department of Energy Future Work  Additional work is needed to classify and identify more than two classes of reports  Fuse text features with image features to develop CAD training set  Longitudinal analysis: Develop methods to recognize precursors to abnormal conditions in patients

15Managed by UT-Battelle for the Department of Energy Longitudinal Patient Analysis spot magnificationsimple cyst nodular density 7 years successful aspiration

16Managed by UT-Battelle for the Department of Energy Longitudinal Patient Analysis “There is prominent nodular density posteriorly and inferiorly in both breasts on the mediolateral oblique views, left more than right.” … “Prominent nodular tissue bilaterally in the posterior inferior breasts is interpretated as normal breast tissue” May 1984 “A 9 mm nodule is present in the left breast at the 6 o'clock position. It was not definitely seen previously and may be a new finding.” … “New left inferior nodule and questionable new right superolateral microcalcifications. The patient should return for additional views with compression spot magnification and possible ultrasound for further evaluation.” Dec 1991 * Note: Emphasis added

17Managed by UT-Battelle for the Department of Energy Acknowledgements  Research sponsored by the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory, managed by UT-Battelle, LLC, for the U. S. Department of Energy.  Our thanks to Robert M. Nishikawa, Ph.D., Department of Radiology, University of Chicago for providing the large dataset of unstructured mammography reports.

18Managed by UT-Battelle for the Department of Energy Questions? Robert M. Patton, Ph.D. Applied Software Engineering Research Oak Ridge National Laboratory (865)