Automatic Extraction of BI-RADS Features from Cross-Institution and Cross-Language Free-Text Mammography Reports Houssam Nassif, Terrie Kitchner, Filipe.

Slides:



Advertisements
Similar presentations
CILC2011 A framework for structured knowledge extraction and representation from natural language via deep sentence analysis Stefania Costantini Niva Florio.
Advertisements

View Learning: An extension to SRL An application in Mammography Jesse Davis, Beth Burnside, Inês Dutra Vítor Santos Costa, David Page, Jude Shavlik &
Learning Semantic Information Extraction Rules from News The Dutch-Belgian Database Day 2013 (DBDBD 2013) Frederik Hogenboom Erasmus.
Semiautomatic Generation of Data-Extraction Ontologies Master’s Thesis Proposal Yihong Ding.
Automatic Report Generation from Ontologies: the MIAKT Approach Kalina Bontcheva, Yorick Wilks Department of Computer Science University of Sheffield.
COMPUTATIONAL INTELLIGENCE FOR THE DETECTION AND CLASSIFICATION OF MALIGNANT LESIONS IN SCREENING MAMMOGRAPHY DATA E. Panourgias,
Breast Cancer - FACTS:  Breast carcinoma leading cause of cancer death in womean  Every 8-10 th woman affected during lifetime  About 4000 new cases/a.
· Information gathering · Data analysis · Decision making · “ Human life is too important to be left to a computer “ Patients receive the best treatment.
WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer.
Automating Breast Ultrasound Workflow DICOM Compatible Automated Segmentation Digital Work Sheet Documentation Point and Click Lesion Characteristics Previous.
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.
Volumetric Breast Density understandbreastdensity.or g.
Word Sense Disambiguation for Automatic Taxonomy Construction from Text-Based Web Corpora 12th International Conference on Web Information System Engineering.
Uncovering Age-Specific Invasive and DCIS Breast Cancer Rules Using Inductive Logic Programming Houssam Nassif, David Page, Mehmet Ayvaci, Jude Shavlik,
Bayesian Network for Predicting Invasive and In-situ Breast Cancer using Mammographic Findings Jagpreet Chhatwal1 O. Alagoz1, E.S. Burnside1, H. Nassif1,
ENDA MOLLOY, ELECTRONIC ENG. FINAL PRESENTATION, 31/03/09. Automated Image Analysis Techniques for Screening of Mammography Images.
Empirical Methods in Information Extraction Claire Cardie Appeared in AI Magazine, 18:4, Summarized by Seong-Bae Park.
Exploiting Ontologies for Automatic Image Annotation M. Srikanth, J. Varner, M. Bowden, D. Moldovan Language Computer Corporation
Age Stratified Risk Prediction of Invasive versus In-situ Breast Cancer: A Logistic Regression Model Mehmet Ayvaci 1,2 Oguzhan Alagoz 1,Jagpreet Chhatwal.
A Simple Unsupervised Query Categorizer for Web Search Engines Prashant Ullegaddi and Vasudeva Varma Search and Information Extraction Lab Language Technologies.
Scott Duvall, Brett South, Stéphane Meystre A Hands-on Introduction to Natural Language Processing in Healthcare Annotation as a Central Task for Development.
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.
Intelligent Database Systems Lab Presenter : WU, MIN-CONG Authors : Jorge Villalon and Rafael A. Calvo 2011, EST Concept Maps as Cognitive Visualizations.
Extracting BI-RADS Features from Portuguese Clinical Texts H. Nassif, F. Cunha, I.C. Moreira, R. Cruz- Correia, E. Sousa, D. Page, E. Burnside, and I.
Improvement in Screening Radiologists’ Performance in an Organized Screening Program Nancy A. T. Wadden, MD, FRCPC Gregory Doyle, BSc, MBA Breast Screening.
Kickoff Meeting Opinion profile construction from Social Media. A case study of restaurant reviews Funded By Cogito Foundation Hatem Ghorbel ISIC-HE-Arc.
A Semantic Approach to IE Pattern Induction Mark Stevenson and Mark A. Greenwood Natural Language Processing Group University of Sheffield, UK.
Chapter 1 Introduction. Chapter 1 - Introduction 2 The Goal of Chapter 1 Introduce different forms of language translators Give a high level overview.
Image Processing and Analysis I Materials extracted from Gonzalez & Wood and Castleman.
Semantic web Bootstrapping & Annotation Hassan Sayyadi Semantic web research laboratory Computer department Sharif university of.
Biometrics % Biostatistics
Intelligent Database Systems Lab N.Y.U.S.T. I. M. 1 Mining knowledge from natural language texts using fuzzy associated concept mapping Presenter : Wu,
Information Extraction for Clinical Data Mining: A Mammography Case Study H. Nassif, R. Woods, E. Burnside, M. Ayvaci, J. Shavlik and D. Page University.
Human-Assisted Machine Annotation Sergei Nirenburg, Marjorie McShane, Stephen Beale Institute for Language and Information Technologies University of Maryland.
The CALMA project A CAD tool in breast radiography A.Ceccopieri, Padova
Microsoft Access Prepared by the Academic Faculty Members of IT.
An Effective Hybridized Classifier for Breast Cancer Diagnosis DISHANT MITTAL, DEV GAURAV & SANJIBAN SEKHAR ROY VIT University, India.
Automatic extraction of BI-RADS breast tissue composition classes from mammography reports Bethany Percha (Stanford) Houssam Nassif (U. Wisconsin) Jafi.
MSM 2013 Challenge: Annotowatch Stefan Dlugolinsky, Peter Krammer, Marek Ciglan, Michal Laclavik Institute of Informatics, Slovak Academy of Sciences.
THIRD CLASSIFICATION OF MICROCALCIFICATION STAGES IN MAMMOGRAPHIC IMAGES THIRD REVIEW Supervisor: Mrs.P.Valarmathi HOD/CSE Project Members: M.HamsaPriya( )
國立雲林科技大學 National Yunlin University of Science and Technology Intelligent Database Systems Lab 1 Self-organizing map for cluster analysis of a breast cancer.
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.
1-1 TITLE PRESENTATION:HEALTHCARE GROUP MEMBER: CHUAH XUE LI(212176) ONG SEAT NEE(212133) STIN2063 MACHINE LEARNING.
CIS 375 Bruce R. Maxim UM-Dearborn
Application of the breast imaging reporting and data system final assessment system in sonography of palpable breast lesions and reconsideration of the.
Jonatas Wehrmann, Willian Becker, Henry E. L. Cagnini, and Rodrigo C
Encoding Extraction as Inferences
Approaches to Machine Translation
Grammar-based Specification and Parsing for Binary File Formats
Fig. 2. Triple negative type breast cancer of 37-year-old woman. A
Siemens Enables Digitalization: Data Analytics & Artificial Intelligence Dr. Mike Roshchin, CT RDA BAM.
Wei Wei, PhD, Zhanglong Ji, PhD, Lucila Ohno-Machado, MD, PhD
Rapid, automatic image comparison software to help doctors determine breast density category. Now with FDA 510(k) clearance for use with GE Senographe.
Deepak Kumar1, Chetan Kumar1, Ming Shao2
Population Information Integration, Analysis and Modeling
سرطان الثدي Breast Cancer
RAD-IT Tool Training June 2017 RAD-IT Tool Training
Regional Architecture Development for Intelligent Transportation
By: Behrouz Rostami, Zeyun Yu Electrical Engineering Department
Compilers B V Sai Aravind (11CS10008).
Approaches to Machine Translation
Low-Grade Adenosquamous Carcinoma of the Breast: Imaging and Histopathologic Characteristics of This Rare Disease  Elena P. Scali, MD, Rola H. Ali, MD,
Independent Project Natural Language to SQL
CSC 578 Neural Networks and Deep Learning
Social Practice of the language: Describe and share information
Predicting Breast Cancer by Applying Deep Learning to Linked Health Records and Mammograms The algorithm predicted future breast cancer based on the index.
Extracting Why Text Segment from Web Based on Grammar-gram
SIDE: The Summarization IDE
Presentation transcript:

Automatic Extraction of BI-RADS Features from Cross-Institution and Cross-Language Free-Text Mammography Reports Houssam Nassif, Terrie Kitchner, Filipe Cunha, Inês C. Moreira, and Elizabeth S. Burnside

Mammogram Radiologist Structured Database Impression (free text) Predictive Model Benign Malignant Breast cancer screening starts with a mammogram, which is read by a radiologist. The radiologist takes some measurements, checks for features, and records them in a database. Various successful predictive models have been built on top of these databases But the amount of tabulated information varies between institutions, since radiologists also record their impression as free-text. These free-text reports are not used in any predictive model, leading to loss of information. In this work, we extract information from free-text reports, in order to augment breast-cancer classification models. 2

BI-RADS Lexicon Concepts Radiologists use a particular lexicon to describe their findings It is the BI-RADS lexicon, which stands for Breast Imaging Reporting and Data System It depicts 43 distinct mammography concepts Our task is basically to map text to these concepts Concepts 3

Example In the right breast, an approximately 1.0 cm mass is identified in the right upper inner breast. This mass is noncalcified and partially obscured and lobulated in appearance. Lobular Shape Oval Shape Obscured Margin … Report 1 1 Report 2 As an example, the following free-text report contains both the “lobular shape” and the “obscured margin” concepts. We identify their underlying text and populate a database 4

Our approach consists of three modules, (a syntax analyzer, a semantic parser and a lexical scanner) and incorporates the BI-RADS lexicon and experts knowledge. Our first step is a preprocessing step 5

Materials & Methods Training on 146,972 mammograms Testing on same academic institution as training and on different private institution Replicate algorithm into Portuguese language, and test on Portuguese set All test sets manually annotated

Results Testing set Size Precision Recall Academic 100 99.1% 98.2% Private 71 97.9% 95.9% Portuguese 306 96.6% 92.6%

Conclusion Automated BI-RADS extractor: Performs no worse than manual extraction Generalizes across institutions Generalizes across languages Enables the incorporation of free-text data into breast cancer risk prediction tools