Deep-Learning Based Semantic Labeling for 2D Mammography & Comparison of Complexity for Machine Learning Tasks

Size: px
Start display at page:

Download "Deep-Learning Based Semantic Labeling for 2D Mammography & Comparison of Complexity for Machine Learning Tasks"

Transcription

1 Deep-Learning Based Semantic Labeling for 2D Mammography & Comparison of Complexity for Machine Learning Tasks Paul H. Yi, MD, Abigail Lin, BSE, Jinchi Wei, BSE, Haris I. Sair, MD, Ferdinand K. Hui, MD, Gregory D Hager, PhD, & Susan C. Harvey, MD Radiology Artificial Intelligence Lab (RAIL), Johns Hopkins University School of Medicine & Malone Center for Engineering in Healthcare, Johns Hopkins University Whiting School of Engineering

2 Introduction

3 Introduction

4 Introduction arxiv ,000 frontal CXRs!

5 Introduction

6 Introduction Radiologist PACS workflow depends on accurate semantic labeling. Although DICOM stores metadata, its inclusion is inconsistent, can vary between equipment manufacturers, & can be inaccurate. Automated method for semantic labeling could: 1) Improve radiologist workflow 2) Facilitate curation of medical imaging datasets for machine learning purposes.

7 How Many Images Do You Need? arxiv ~5000 images per class J Digit Imaging this number may depend on the difficulty of the training set.

8 Mammography as a Model? Mammography is recommended annually for all women over age 40 by the ACR. Due to strict national regulations for DICOM labeling, mammography serves as a potential model to explore the nuances of developing semantic labeling algorithms. Lessons learned can be applied towards other modalities and more complex, but analogous problems!

9 Purpose 1. Develop deep convolutional neural networks (DCNNs) for automated classification of 2D-mammography: 1. View 2. Laterality 3. Breast density 4. Normal/Benign vs. Malignant masses 2. Compare the performance of DCNNs on these tasks of varying complexity.

10 Methods- Dataset Digital Database for Screening Mammography*: D mammography images (2620 patients) 4 USA Hospitals (MGH, Wake Forest, Sacred Heart, WUSTL) Normal & Benign or malignant masses (pathology groundtruth) Labels: Mammographic view (craniocaudal [CC] vs. mediolateral oblique [MLO]) Breast laterality (right vs. left) Breast density (4 BI-RADS categories) Normal/benign mass vs. malignant mass. *Updated CBIS-DDSM. Rebecca Sawyer Lee, Francisco Gimenez, Assaf Hoogi, Daniel Rubin (2016). Curated Breast Imaging Subset of DDSM. The Cancer Imaging Archive.

11 Methods- Dataset Data split into training (70%), validation (10%), & testing (20%) sets. Mammographi c View Total Label #s (3034) CC: 1429 (47%) MLO: 1605 (53%) Laterality Left: 1560 (51%) Right: 1474 (49%) Breast Density (BI-RADS) Benign vs. Malignant A: 416 (14%) B: 1182 (39%) C: 928 (31%) D: 508 (16%) Benign: 1704 (56%) Malignant: 1330 (44%) Training (70%) Validation (10%) Testing (20%) CC: 1000 MLO: 1123 Left: 1092 Right: 1032 A: 291 B: 827 C:649 D: 355 Benign: 1193 Malignant: 931 A = Fatty; B = Scattered fibroglandular; C = Heterogeneously dense; D = Dense CC: 143 MLO: 161 Left: 156 Right: 148 A: 42 B: 119 C: 93 D: 51 Benign: 171 Malignant: 1331 CC: 288 MLO: 323 Left: 314 Right: 296 A: 85 B: 238 C: 188 D: 104 Benign: 342 Malignant: 268

12 Methods- DCNN Transfer learning to train, validate, and test the ResNet-50 DCNN pretrained on ImageNet on these mammography datasets. Last fully connected layer fine-tuned using these datasets. During each training epoch, images augmented via rotations, cropping, and horizontal flipping.

13 Methods Receiver operating characteristic (ROC) curves with area under the curve (AUC) were generated. AUCs compared between DCNNs using the DeLong parametric method (significance set at p<0.05).

14 Methods Heatmaps created through class activation mapping:

15 Results: Simplest Task The DCNN trained to classify mammographic view achieved AUC of 1.

16 Results: Slightly More Difficult Task The DCNN trained to classify breast laterality initially mis-classified right and left breasts not infrequently (AUC 0.89, 77% accuracy) However, after discontinuing horizontal flips, AUC significantly improved to 1 (p<0.0001)!

17 Results: Laterality

18 Results: Most Difficult Tasks Classification of normal/benign vs. malignant masses proved more difficult: AUC of 0.75 (p<0.0001, compared to both view and laterality DCNNs) Similarly, breast density classification was not as successful with 68% accuracy.

19 Discussion Semantic labeling DCNNs achieved AUC of 1 for mammographic view and laterality ( obvious differences) using 2427 training/validation images. J Digit Imaging Deep convolutional neural networks perform rather well in distinguishing images that have many obvious differences, such as chest vs. abdominal radiographs (AUC = 1.00), and require only a small amount of training data. 45 chest and 45 abdominal XRs were sufficient!

20 Discussion They were less successful at more complex tasks, likely owing to increased subtleties in these categories. Datasets to train high-performing DCNNs for more complex tasks need to be larger than those used for simple tasks, e.g., semantic labeling.

21 Discussion More augmentation did not not always improve performance! Laterality DCNNs demonstrated significantly improved performance by omitting horizontal flips. ARRS 2018 Interestingly, the network initially miscategorized large right for large left effusions; however, 100% accuracy was achieved for correct laterality identification after discontinuing horizontal flipping during data augmentation.

22 Discussion: Is More Better? Canonical ML wisdom is to always perform data augmentation during training to decrease overfitting. However, this should be performed thoughtfully! N.B. We don t know why certain techniques may help or hurt GREY

23 Discussion: How low can we go? We know that DCNNs for simpler tasks require less data! But how low can we go? Work Imaging Views Total # Training & Validation Images AUC Rajkomar et al. J Digit Imaging Yi et al. (Current work) Lakhani et al. J Digit Imaging *Augmented Future work? Frontal vs. Lateral Chest X-Ray 150,000* 1 CC vs. MLO Mammography Chest vs. Abdomen X-Ray 90 1

24 Conclusions DCNN semantic labeling of 2D-mammography is feasible using relatively small image datasets. However, automated classification of more difficult tasks will likely require larger datasets. Risks of image augmentation?

25 Thank you!

Mammographic Breast Density Classification by a Deep Learning Approach

Mammographic Breast Density Classification by a Deep Learning Approach Mammographic Breast Density Classification by a Deep Learning Approach Aly Mohamed, PhD Robert Nishikawa, PhD Wendie A. Berg, MD, PhD David Gur, ScD Shandong Wu, PhD Department of Radiology, University

More information

Automatic classification of mammographic breast density

Automatic classification of mammographic breast density Deep Learning Day 2018 Automatic classification of mammographic breast density PD Dr. Cristina Rossi cristina.rossi@usz.ch Institute of Diagnostic and Interventional Radiology, University Hospital Zurich

More information

Artificial Intelligence in Breast Imaging

Artificial Intelligence in Breast Imaging Artificial Intelligence in Breast Imaging Manisha Bahl, MD, MPH Director of Breast Imaging Fellowship Program, Massachusetts General Hospital Assistant Professor of Radiology, Harvard Medical School Outline

More information

Investigating the performance of a CAD x scheme for mammography in specific BIRADS categories

Investigating the performance of a CAD x scheme for mammography in specific BIRADS categories Investigating the performance of a CAD x scheme for mammography in specific BIRADS categories Andreadis I., Nikita K. Department of Electrical and Computer Engineering National Technical University of

More information

arxiv: v1 [cs.cv] 21 Jul 2017

arxiv: v1 [cs.cv] 21 Jul 2017 A Multi-Scale CNN and Curriculum Learning Strategy for Mammogram Classification William Lotter 1,2, Greg Sorensen 2, and David Cox 1,2 1 Harvard University, Cambridge MA, USA 2 DeepHealth Inc., Cambridge

More information

The Radiology Aspects

The Radiology Aspects REQUIREMENTS FOR INTERNATIONAL ACCREDITATION OF BREAST CENTERS/UNITS The Radiology Aspects Miri Sklair-Levy, Israel RADIOLOGY GUIDELINES FOR QUALITY ASSURANCE IN BREAST CANCER SCREENING AND DIAGNOSIS Radiologists

More information

arxiv: v2 [cs.cv] 8 Mar 2018

arxiv: v2 [cs.cv] 8 Mar 2018 Automated soft tissue lesion detection and segmentation in digital mammography using a u-net deep learning network Timothy de Moor a, Alejandro Rodriguez-Ruiz a, Albert Gubern Mérida a, Ritse Mann a, and

More information

High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks

High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks Krzysztof J. Geras Joint work with Kyunghyun Cho, Linda Moy, Gene Kim, Stacey Wolfson and Artie Shen. GTC 2017

More information

HEALTHCARE AI DEVELOPMENT CYCLE

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

More information

Since its introduction in 2000, digital mammography has become

Since its introduction in 2000, digital mammography has become Review Article Smith A, PhD email : Andrew.smith@hologic.com Since its introduction in 2000, digital mammography has become an accepted standard of care in breast cancer screening and has paved the way

More information

Automating Quality Assurance Metrics to Assess Adequate Breast Positioning in Mammography

Automating Quality Assurance Metrics to Assess Adequate Breast Positioning in Mammography Automating Quality Assurance Metrics to Assess Adequate Breast Positioning in Mammography Gerald R. Kolb, JD, The Breast Group, Sunriver, OR; Kaier Wang, PhD, VolparaSolutions, Wellington, NZ; Ariane Chan,

More information

Computerized image analysis: Estimation of breast density on mammograms

Computerized image analysis: Estimation of breast density on mammograms Computerized image analysis: Estimation of breast density on mammograms Chuan Zhou, Heang-Ping Chan, a) Nicholas Petrick, Mark A. Helvie, Mitchell M. Goodsitt, Berkman Sahiner, and Lubomir M. Hadjiiski

More information

DeepMiner: Discovering Interpretable Representations for Mammogram Classification and Explanation

DeepMiner: Discovering Interpretable Representations for Mammogram Classification and Explanation DeepMiner: Discovering Interpretable Representations for Mammogram Classification and Explanation Jimmy Wu 1, Bolei Zhou 1, Diondra Peck 2, Scott Hsieh 3, Vandana Dialani, MD 4 Lester Mackey 5, and Genevieve

More information

Using Deep Convolutional Neural Networks to Predict Semantic Features of Lesions in Mammograms

Using Deep Convolutional Neural Networks to Predict Semantic Features of Lesions in Mammograms Using Deep Convolutional Neural Networks to Predict Semantic Features of Lesions in Mammograms Vibhu Agarwal Stanford University vibhua@stanford.edu Clayton Carson Stanford University carsoncz@stanford.edu

More information

Mammography limitations. Clinical performance of digital breast tomosynthesis compared to digital mammography: blinded multi-reader study

Mammography limitations. Clinical performance of digital breast tomosynthesis compared to digital mammography: blinded multi-reader study Clinical performance of digital breast tomosynthesis compared to digital mammography: blinded multi-reader study G. Gennaro (1), A. Toledano (2), E. Baldan (1), E. Bezzon (1), C. di Maggio (1), M. La Grassa

More information

A Deep Learning Approach for Breast Cancer Mass Detection

A Deep Learning Approach for Breast Cancer Mass Detection A Deep Learning Approach for Breast Cancer Mass Detection Wael E.Fathy 1, Amr S. Ghoneim 2 Teaching Assistant 1, Assistant Professor 2 Department of Computer Science, Faculty of Computers and Information

More information

Ruud Pijnappel Professor of Radiology, UMC Utrecht. Chair Dutch Expert Centre for Screening Board EUSOBI

Ruud Pijnappel Professor of Radiology, UMC Utrecht. Chair Dutch Expert Centre for Screening Board EUSOBI Ruud Pijnappel Professor of Radiology, UMC Utrecht Best practice in Breast Imaging: what s new and what women need to know and Update on the Second Implementation Report of the 2003 Council Recommendation

More information

arxiv: v1 [stat.ml] 23 Jan 2017

arxiv: v1 [stat.ml] 23 Jan 2017 Learning what to look in chest X-rays with a recurrent visual attention model arxiv:1701.06452v1 [stat.ml] 23 Jan 2017 Petros-Pavlos Ypsilantis Department of Biomedical Engineering King s College London

More information

Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images

Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images Tae Joon Jun, Dohyeun Kim, and Daeyoung Kim School of Computing, KAIST,

More information

Expert identification of visual primitives used by CNNs during mammogram classification

Expert identification of visual primitives used by CNNs during mammogram classification Expert identification of visual primitives used by CNNs during mammogram classification Jimmy Wu a, Diondra Peck b, Scott Hsieh c, Vandana Dialani, MD d, Constance D. Lehman, MD e, Bolei Zhou a, Vasilis

More information

Breast asymmetries in mammography: Management

Breast asymmetries in mammography: Management Breast asymmetries in mammography: Management Poster No.: C-1026 Congress: ECR 2015 Type: Educational Exhibit Authors: V. de Lara Bendahan 1, F. J. Hidalgo Ramos 2, J. L. Ortega Garcia 3, Keywords: DOI:

More information

arxiv: v1 [cs.cv] 30 May 2018

arxiv: v1 [cs.cv] 30 May 2018 A Robust and Effective Approach Towards Accurate Metastasis Detection and pn-stage Classification in Breast Cancer Byungjae Lee and Kyunghyun Paeng Lunit inc., Seoul, South Korea {jaylee,khpaeng}@lunit.io

More information

ARTIFICIAL INTELLIGENCE FOR DIGITAL PATHOLOGY. Kyunghyun Paeng, Co-founder and Research Scientist, Lunit Inc.

ARTIFICIAL INTELLIGENCE FOR DIGITAL PATHOLOGY. Kyunghyun Paeng, Co-founder and Research Scientist, Lunit Inc. ARTIFICIAL INTELLIGENCE FOR DIGITAL PATHOLOGY Kyunghyun Paeng, Co-founder and Research Scientist, Lunit Inc. 1. BACKGROUND: DIGITAL PATHOLOGY 2. APPLICATIONS AGENDA BREAST CANCER PROSTATE CANCER 3. DEMONSTRATIONS

More information

How to Reduce Missed Diagnosis of Breast Cancer

How to Reduce Missed Diagnosis of Breast Cancer How to Reduce Missed Diagnosis of Breast Cancer Heeboong Park M.D., Ph.D. Park Surgical Clinic Medical Park Co., Ltd. Definition of Missed Diagnosis Misdiagnosis means that a doctor has diagnosed a person

More information

Healthcare Research You

Healthcare Research You DL for Healthcare Goals Healthcare Research You What are high impact problems in healthcare that deep learning can solve? What does research in AI applications to medical imaging look like? How can you

More information

MAMMOGRAM AND TOMOSYNTHESIS CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORKS

MAMMOGRAM AND TOMOSYNTHESIS CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORKS University of Kentucky UKnowledge Theses and Dissertations--Computer Science Computer Science 2017 MAMMOGRAM AND TOMOSYNTHESIS CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORKS Xiaofei Zhang University

More information

Financial Disclosures

Financial Disclosures Financial Disclosures 3D Mammography: The Latest Developments in the Breast Imaging Arena I have no financial disclosures Dr. Katharine Lampen-Sachar Breast and Body Radiologist Radiology Associates of

More information

CHAPTER 2 MAMMOGRAMS AND COMPUTER AIDED DETECTION

CHAPTER 2 MAMMOGRAMS AND COMPUTER AIDED DETECTION 9 CHAPTER 2 MAMMOGRAMS AND COMPUTER AIDED DETECTION 2.1 INTRODUCTION This chapter provides an introduction to mammogram and a description of the computer aided detection methods of mammography. This discussion

More information

Corporate Medical Policy

Corporate Medical Policy Corporate Medical Policy File Name: Origination: Last CAP Review: Next CAP Review: Last Review: digital_breast_tomosynthesis 3/2011 6/2016 6/2017 11/2016 Description of Procedure or Service Conventional

More information

Does the synthesised digital mammography (3D-DM) change the ACR density pattern?

Does the synthesised digital mammography (3D-DM) change the ACR density pattern? Does the synthesised digital mammography (3D-DM) change the ACR density pattern? Poster No.: B-0211 Congress: ECR 2015 Type: Scientific Paper Authors: P. MARTÍNEZ MIRAVETE, M. Millor Muruzábal, P. García-

More information

Classification of breast cancer histology images using transfer learning

Classification of breast cancer histology images using transfer learning Classification of breast cancer histology images using transfer learning Sulaiman Vesal 1 ( ), Nishant Ravikumar 1, AmirAbbas Davari 1, Stephan Ellmann 2, Andreas Maier 1 1 Pattern Recognition Lab, Friedrich-Alexander-Universität

More information

Look differently. Invenia ABUS. Automated Breast Ultrasound

Look differently. Invenia ABUS. Automated Breast Ultrasound Look differently. Invenia ABUS Automated Breast Ultrasound InveniaTM ABUS from GE Healthcare offers a view beyond mammography, with breast screening technology that looks differently. 40 % The unseen risk.

More information

DIAGNOSTIC CLASSIFICATION OF LUNG NODULES USING 3D NEURAL NETWORKS

DIAGNOSTIC CLASSIFICATION OF LUNG NODULES USING 3D NEURAL NETWORKS DIAGNOSTIC CLASSIFICATION OF LUNG NODULES USING 3D NEURAL NETWORKS Raunak Dey Zhongjie Lu Yi Hong Department of Computer Science, University of Georgia, Athens, GA, USA First Affiliated Hospital, School

More information

Deep learning and non-negative matrix factorization in recognition of mammograms

Deep learning and non-negative matrix factorization in recognition of mammograms Deep learning and non-negative matrix factorization in recognition of mammograms Bartosz Swiderski Faculty of Applied Informatics and Mathematics Warsaw University of Life Sciences, Warsaw, Poland bartosz_swiderski@sggw.pl

More information

ACCREDITATION DOCUMENT THE RADIOGRAPHER

ACCREDITATION DOCUMENT THE RADIOGRAPHER ACCREDITATION DOCUMENT THE RADIOGRAPHER Nijmegen, October 2012 1. Introduction An optimal quality of mammography is one of the fundamental requirements for successful breast cancer screening programmes.

More information

Predicting Malignancy from Mammography Findings and Image Guided Core Biopsies

Predicting Malignancy from Mammography Findings and Image Guided Core Biopsies Predicting Malignancy from Mammography Findings and Image Guided Core Biopsies 2 nd Breast Cancer Workshop 2015 April 7 th 2015 Porto, Portugal Pedro Ferreira Nuno A. Fonseca Inês Dutra Ryan Woods Elizabeth

More information

A deep learning method for classifying mammographic breast density categories

A deep learning method for classifying mammographic breast density categories A deep learning method for classifying mammographic breast density categories Aly A. Mohamed Department of Radiology, University of Pittsburgh School of Medicine, 4200 Fifth Ave, Pittsburgh, PA 15260,

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

S. Murgo, MD. Chr St-Joseph, Mons Erasme Hospital, Brussels

S. Murgo, MD. Chr St-Joseph, Mons Erasme Hospital, Brussels S. Murgo, MD Chr St-Joseph, Mons Erasme Hospital, Brussels? Introduction Mammography reports are sometimes ambiguous and indecisive. ACR has developped the BIRADS. BIRADS consists of a lexicon in order

More information

MAMMO: A Deep Learning Solution for Facilitating Radiologist-Machine Collaboration in Breast Cancer Diagnosis

MAMMO: A Deep Learning Solution for Facilitating Radiologist-Machine Collaboration in Breast Cancer Diagnosis 1 MAMMO: A Deep Learning Solution for Facilitating Radiologist-Machine Collaboration in Breast Cancer Diagnosis Trent Kyono, Fiona J. Gilbert, Mihaela van der Schaar, Fellow, IEEE arxiv:1811.02661v1 [cs.cv]

More information

Assessment of extent of disease: digital breast tomosynthesis (DBT) versus full-field digital mammography (FFDM)

Assessment of extent of disease: digital breast tomosynthesis (DBT) versus full-field digital mammography (FFDM) Assessment of extent of disease: digital breast tomosynthesis (DBT) versus full-field digital mammography (FFDM) Poster No.: C-1237 Congress: ECR 2012 Type: Scientific Paper Authors: N. Seo 1, H. H. Kim

More information

Research Article A Selective Ensemble Classification Method Combining Mammography Images with Ultrasound Images for Breast Cancer Diagnosis

Research Article A Selective Ensemble Classification Method Combining Mammography Images with Ultrasound Images for Breast Cancer Diagnosis Hindawi Computational and Mathematical Methods in Medicine Volume 27, Article ID 4896386, 7 pages https://doi.org/5/27/4896386 Research Article A Selective Ensemble Classification Method Combining Mammography

More information

The value of the craniocaudal mammographic view in breast cancer detection: A preliminary study

The value of the craniocaudal mammographic view in breast cancer detection: A preliminary study The value of the craniocaudal mammographic view in breast cancer detection: A preliminary study P D Trieu 1, Prof. P C Brennan 1, Dr. W Lee 2, Dr. E Ryan 1, Dr. W Reed 1, Dr. M Pietrzyk 1 1. Medical Image

More information

BREAST CANCER EARLY DETECTION USING X RAY IMAGES

BREAST CANCER EARLY DETECTION USING X RAY IMAGES Volume 119 No. 15 2018, 399-405 ISSN: 1314-3395 (on-line version) url: http://www.acadpubl.eu/hub/ http://www.acadpubl.eu/hub/ BREAST CANCER EARLY DETECTION USING X RAY IMAGES Kalaichelvi.K 1,Aarthi.R

More information

CSE Introduction to High-Perfomance Deep Learning ImageNet & VGG. Jihyung Kil

CSE Introduction to High-Perfomance Deep Learning ImageNet & VGG. Jihyung Kil CSE 5194.01 - Introduction to High-Perfomance Deep Learning ImageNet & VGG Jihyung Kil ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton,

More information

Imaging Collaboration: From Pen and Ink to Artificial Intelligence June 2, 2018

Imaging Collaboration: From Pen and Ink to Artificial Intelligence June 2, 2018 Imaging Collaboration: From Pen and Ink to Artificial Intelligence June 2, 2018 Curtis P. Langlotz, MD, PhD Professor of Radiology and Biomedical Informatics Director, Center for Artificial Intelligence

More information

CLASSIFICATION OF ABNORMALITY IN B -MASS BY ARCHITECTURAL DISTORTION

CLASSIFICATION OF ABNORMALITY IN B -MASS BY ARCHITECTURAL DISTORTION CLASSIFICATION OF ABNORMALITY IN B -MASS BY ARCHITECTURAL DISTORTION #1 Venmathi.A.R., * 2 D.C.Jullie Josphine #1.Dept of ECE, Kings Engineering College * 2. Dept of CSE,Kings Engineering college Abstract-The

More information

FDA Executive Summary

FDA Executive Summary Meeting of the Radiological Devices Advisory Panel On October 24, 22, the panel will discuss, make recommendations, and vote on a premarket approval application supplement (P83/S) to expand the indications

More information

Intracystic papillary carcinoma of the breast

Intracystic papillary carcinoma of the breast Intracystic papillary carcinoma of the breast Poster No.: C-1932 Congress: ECR 2011 Type: Educational Exhibit Authors: V. Dimarelos, F. TZIKOS, N. Kotziamani, G. Rodokalakis, 1 2 3 1 1 1 2 T. MALKOTSI

More information

ImageCLEF2018: Transfer Learning for Deep Learning with CNN for Tuberculosis Classification

ImageCLEF2018: Transfer Learning for Deep Learning with CNN for Tuberculosis Classification ImageCLEF2018: Transfer Learning for Deep Learning with CNN for Tuberculosis Classification Amilcare Gentili 1-2[0000-0002-5623-7512] 1 San Diego VA Health Care System, San Diego, CA USA 2 University of

More information

Computer Aided Diagnosis for Breast Cancer Screening

Computer Aided Diagnosis for Breast Cancer Screening Proceedings of the 4th IIAE International Conference on Industrial Application Engineering 2016 Computer Aided Diagnosis for Breast Cancer Screening Piyamas Suapang a,*, Chadaporn Naruephai b, Sorawat

More information

GE Healthcare. Look differently. Invenia ABUS. Automated Breast Ultrasound

GE Healthcare. Look differently. Invenia ABUS. Automated Breast Ultrasound GE Healthcare Look differently Invenia ABUS Automated Breast Ultrasound Invenia TM ABUS from GE Healthcare offers a view beyond mammography, with breast screening technology that looks differently. 40%

More information

Epworth Healthcare Benign Breast Disease Symposium. Sat Nov 12 th 2016

Epworth Healthcare Benign Breast Disease Symposium. Sat Nov 12 th 2016 Epworth Healthcare Benign Breast Disease Symposium Breast cancer is common Sat Nov 12 th 2016 Benign breast disease is commoner, and anxiety about breast disease commoner still Breast Care Campaign UK

More information

Estimation of Breast Density and Feature Extraction of Mammographic Images

Estimation of Breast Density and Feature Extraction of Mammographic Images IJIRST International Journal for Innovative Research in Science & Technology Volume 2 Issue 11 April 2016 ISSN (online): 2349-6010 Estimation of Breast Density and Feature Extraction of Mammographic Images

More information

Mammogram Analysis: Tumor Classification

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

More information

8/31/2016 HIDING IN PLAIN SITE, ARCHITECTURAL DISTORTIONS AND BREAST ASYMMETRIES ARCHITECTURAL DISTORTIONS ARCHITECTURAL DISTORTIONS

8/31/2016 HIDING IN PLAIN SITE, ARCHITECTURAL DISTORTIONS AND BREAST ASYMMETRIES ARCHITECTURAL DISTORTIONS ARCHITECTURAL DISTORTIONS HIDING IN PLAIN SITE, ARCHITECTURAL DISTORTIONS AND BREAST ASYMMETRIES DEBORAH THAMES R.T. (R)(M)(QM) ARCHITECTURAL DISTORTIONS Definition is disruption of the natural flow of breast pattern towards the

More information

COMPARATIVE STUDY ON FEATURE EXTRACTION METHOD FOR BREAST CANCER CLASSIFICATION

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

More information

Challenges to Delivery of High Quality Mammography

Challenges to Delivery of High Quality Mammography Challenges to Delivery of High Quality Mammography Overview of Current Challenges Barbara Monsees, Washington University Geographic Access, Equity and Impact on Quality Tracy Onega, Dartmouth Medical School

More information

Diagnostic benefits of ultrasound-guided. CNB) versus mammograph-guided biopsy for suspicious microcalcifications. without definite breast mass

Diagnostic benefits of ultrasound-guided. CNB) versus mammograph-guided biopsy for suspicious microcalcifications. without definite breast mass Volume 118 No. 19 2018, 531-543 ISSN: 1311-8080 (printed version); ISSN: 1314-3395 (on-line version) url: http://www.ijpam.eu ijpam.eu Diagnostic benefits of ultrasound-guided biopsy versus mammography-guided

More information

CURRENTLY FDA APPROVED ARE FULL FIELD DIGITAL MAMMOGRAPHY SYSTEMS AND FILM SCREEN STILL BEING USED AT SOME INSTITUTIONS

CURRENTLY FDA APPROVED ARE FULL FIELD DIGITAL MAMMOGRAPHY SYSTEMS AND FILM SCREEN STILL BEING USED AT SOME INSTITUTIONS ABBY DUROJAYE,M.D CURRENTLY FDA APPROVED ARE FULL FIELD DIGITAL MAMMOGRAPHY SYSTEMS AND FILM SCREEN STILL BEING USED AT SOME INSTITUTIONS BOTH HAVE BEEN SHOWN TO BE EFFECTIVE TOOLS EARLY DETECTION OF BREAST

More information

FULLY AUTOMATED CLASSIFICATION OF MAMMOGRAMS USING DEEP RESIDUAL NEURAL NETWORKS. Gustavo Carneiro

FULLY AUTOMATED CLASSIFICATION OF MAMMOGRAMS USING DEEP RESIDUAL NEURAL NETWORKS. Gustavo Carneiro FULLY AUTOMATED CLASSIFICATION OF MAMMOGRAMS USING DEEP RESIDUAL NEURAL NETWORKS Neeraj Dhungel Gustavo Carneiro Andrew P. Bradley? Electrical and Computer Engineering, The University of British Columbia,

More information

NMF-Density: NMF-Based Breast Density Classifier

NMF-Density: NMF-Based Breast Density Classifier NMF-Density: NMF-Based Breast Density Classifier Lahouari Ghouti and Abdullah H. Owaidh King Fahd University of Petroleum and Minerals - Department of Information and Computer Science. KFUPM Box 1128.

More information

Additional US or DBT after digital mammography: which one is the best combination?

Additional US or DBT after digital mammography: which one is the best combination? Additional US or DBT after digital mammography: which one is the best combination? Poster No.: B-0926 Congress: ECR 2015 Type: Authors: Keywords: DOI: Scientific Paper A. Elizalde, P. Garcia Barquin, M.

More information

Breast Imaging! Ravi Adhikary, MD!

Breast Imaging! Ravi Adhikary, MD! Breast Imaging! Ravi Adhikary, MD! ACS Estimated Cancers Statistics 2014! Breast! New Cases in Women! 232,670 (+67,570 in situ)! Deaths in Women! 40,000! Colon! 48,380! 24,040! Cervical! 12,360! 4,020!

More information

ORIGINAL ARTICLE EVALUATION OF BREAST LESIONS USING X-RAY MAMMOGRAM WITH HISTOPATHOLOGICAL CORRELATION

ORIGINAL ARTICLE EVALUATION OF BREAST LESIONS USING X-RAY MAMMOGRAM WITH HISTOPATHOLOGICAL CORRELATION Available online at www.journalijmrr.com INTERNATIONAL JOURNAL OF MODERN RESEARCH AND REVIEWS IJMRR ISSN: 2347-8314 Int. J. Modn. Res. Revs. Volume 3, Issue 10, pp 807-814, October, 2015 ORIGINAL ARTICLE

More information

Elad Hoffer*, Itay Hubara*, Daniel Soudry

Elad Hoffer*, Itay Hubara*, Daniel Soudry Train longer, generalize better: closing the generalization gap in large batch training of neural networks Elad Hoffer*, Itay Hubara*, Daniel Soudry *Equal contribution Better models - parallelization

More information

Computer aided detection of clusters of microcalcifications on full field digital mammograms

Computer aided detection of clusters of microcalcifications on full field digital mammograms Computer aided detection of clusters of microcalcifications on full field digital mammograms Jun Ge, a Berkman Sahiner, Lubomir M. Hadjiiski, Heang-Ping Chan, Jun Wei, Mark A. Helvie, and Chuan Zhou Department

More information

Breast Imaging & You

Breast Imaging & You Breast Imaging & You What s Inside: Breast Imaging... 2 Digital Breast Tomosynthesis (DBT) mammograms... 4 Breast cancer screening... 6 Dense breast tissue... 8 Automated Breast Ultrasound (ABUS)... 9

More information

Deep CNNs for Diabetic Retinopathy Detection

Deep CNNs for Diabetic Retinopathy Detection Deep CNNs for Diabetic Retinopathy Detection Alex Tamkin Stanford University atamkin@stanford.edu Iain Usiri Stanford University iusiri@stanford.edu Chala Fufa Stanford University cfufa@stanford.edu 1

More information

Background Information

Background Information Background Information Erlangen, November 26, 2017 RSNA 2017 in Chicago: South Building, Hall A, Booth 1937 Artificial intelligence: Transforming data into knowledge for better care Inspired by neural

More information

Breast Density. Update 2018: Implications for Clinical Practice

Breast Density. Update 2018: Implications for Clinical Practice Breast Density Update 2018: Implications for Clinical Practice Matthew A. Stein, MD Assistant professor Breast Imaging Department of Radiology and Imaging Sciences University of Utah Health Disclosures

More information

London Medical Imaging & Artificial Intelligence Centre for Value-Based Healthcare. Professor Reza Razavi Centre Director

London Medical Imaging & Artificial Intelligence Centre for Value-Based Healthcare. Professor Reza Razavi Centre Director London Medical Imaging & Artificial Intelligence Centre for Value-Based Healthcare Professor Reza Razavi Centre Director The traditional healthcare business model is changing Fee-for-service Fee-for-outcome

More information

Min Jung Kim Department of Medicine The Graduate School, Yonsei University

Min Jung Kim Department of Medicine The Graduate School, Yonsei University Zoomed image of contact mammography versus magnification mammography in the diagnosis of microcalcifications with soft-copy full field digital mammography Min Jung Kim Department of Medicine The Graduate

More information

A comparison of the accuracy of film-screen mammography, full-field digital mammography, and digital breast tomosynthesis

A comparison of the accuracy of film-screen mammography, full-field digital mammography, and digital breast tomosynthesis Clinical Radiology xxx (2012) 1e6 Contents lists available at SciVerse ScienceDirect Clinical Radiology journal homepage: www.clinicalradiologyonline.net A comparison of the accuracy of film-screen mammography,

More information

Ana Sofia Preto 19/06/2013

Ana Sofia Preto 19/06/2013 Ana Sofia Preto 19/06/2013 Understanding the underlying pathophysiologic processes leading to the various types of calcifications Description and illustration of the several types of calcifications, according

More information

Automated Volumetric Breast Density Measurements in the Era of the BI-RADS Fifth Edition: A Comparison With Visual Assessment

Automated Volumetric Breast Density Measurements in the Era of the BI-RADS Fifth Edition: A Comparison With Visual Assessment Medical Physics and Informatics Original Research Youk et al. Automated Breast Density Measurement and BI-RADS Fifth Edition Medical Physics and Informatics Original Research Ji Hyun Youk 1 Hye Mi Gweon

More information

arxiv: v1 [cs.cv] 17 Oct 2018

arxiv: v1 [cs.cv] 17 Oct 2018 WHEN DOES BONE SUPPRESSION AND LUNG FIELD SEGMENTATION IMPROVE CHEST X-RAY DISEASE CLASSIFICATION? Ivo M. Baltruschat 1,2,3,4 Leonhard Steinmeister 1,3 Harald Ittrich 1 Gerhard Adam 1 Hannes Nickisch 4

More information

arxiv: v1 [cs.cv] 26 Feb 2018

arxiv: v1 [cs.cv] 26 Feb 2018 Classification of breast cancer histology images using transfer learning Sulaiman Vesal 1, Nishant Ravikumar 1, AmirAbbas Davari 1, Stephan Ellmann 2, Andreas Maier 1 arxiv:1802.09424v1 [cs.cv] 26 Feb

More information

9/3/2015. New Mammographic Modality Training. Mammographer. Qualified Radiologic Technologist. Tomosynthesis Training

9/3/2015. New Mammographic Modality Training. Mammographer. Qualified Radiologic Technologist. Tomosynthesis Training FDA Required Breast Tomosynthesis Training New Mammographic Modality Training On any new mammography technology, such as breast tomosynthesis, the Mammography Quality Standards Act (MQSA) (http:fda.gov/radiation-emitting

More information

Can Digital Breast Tomosynthesis(DBT) Perform Better than Standard Digital Mammography Workup in a Breast Cancer Assessment Clinic?

Can Digital Breast Tomosynthesis(DBT) Perform Better than Standard Digital Mammography Workup in a Breast Cancer Assessment Clinic? Can Digital Breast Tomosynthesis(DBT) Perform Better than Standard Digital Mammography Workup in a Breast Cancer Assessment Clinic? Accepted for publication in European Radiology Authors: S Mall, J Noakes,

More information

Final Report: Automated Semantic Segmentation of Volumetric Cardiovascular Features and Disease Assessment

Final Report: Automated Semantic Segmentation of Volumetric Cardiovascular Features and Disease Assessment Final Report: Automated Semantic Segmentation of Volumetric Cardiovascular Features and Disease Assessment Tony Lindsey 1,3, Xiao Lu 1 and Mojtaba Tefagh 2 1 Department of Biomedical Informatics, Stanford

More information

Lung Nodule Segmentation Using 3D Convolutional Neural Networks

Lung Nodule Segmentation Using 3D Convolutional Neural Networks Lung Nodule Segmentation Using 3D Convolutional Neural Networks Research paper Business Analytics Bernard Bronmans Master Business Analytics VU University, Amsterdam Evert Haasdijk Supervisor VU University,

More information

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

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

More information

Detection of suspicious lesion based on Multiresolution Analysis using windowing and adaptive thresholding method.

Detection of suspicious lesion based on Multiresolution Analysis using windowing and adaptive thresholding method. Detection of suspicious lesion based on Multiresolution Analysis using windowing and adaptive thresholding method. Ms. N. S. Pande Assistant Professor, Department of Computer Science and Engineering,MGM

More information

Breast density in quantifying breast cancer risk 9 December 2016

Breast density in quantifying breast cancer risk 9 December 2016 Breast density in quantifying breast cancer risk 9 December 2016 cancer risk factors is still being debated. University of Malaya researchers, Prof. Kwan Hoong NG and his team published two papers on this

More information

Mammography is a most effective imaging modality in early breast cancer detection. The radiographs are searched for signs of abnormality by expert

Mammography is a most effective imaging modality in early breast cancer detection. The radiographs are searched for signs of abnormality by expert Abstract Methodologies for early detection of breast cancer still remain an open problem in the Research community. Breast cancer continues to be a significant problem in the contemporary world. Nearly

More information

Machine Learning Powered Automatic Organ Classification for Patient Specific Organ Dose Estimation

Machine Learning Powered Automatic Organ Classification for Patient Specific Organ Dose Estimation Machine Learning Powered Automatic Organ Classification for Patient Specific Organ Dose Estimation Junghwan Cho, Eunmi Lee, Hyunkwang Lee, Bob Liu, Xinhua Li, Shahein Tajmir, Dushyant Sahani, and Synho

More information

CLASSIFICATION OF DIGITAL MAMMOGRAM BASED ON NEAREST- NEIGHBOR METHOD FOR BREAST CANCER DETECTION

CLASSIFICATION OF DIGITAL MAMMOGRAM BASED ON NEAREST- NEIGHBOR METHOD FOR BREAST CANCER DETECTION International Journal of Technology (2016) 1: 71-77 ISSN 2086-9614 IJTech 2016 CLASSIFICATION OF DIGITAL MAMMOGRAM BASED ON NEAREST- NEIGHBOR METHOD FOR BREAST CANCER DETECTION Anggrek Citra Nusantara

More information

Amammography report is a key component of the breast

Amammography report is a key component of the breast Review Article Writing a Mammography Report Amammography report is a key component of the breast cancer diagnostic process. Although mammographic findings were not clearly differentiated between benign

More information

arxiv: v2 [cs.cv] 29 Jan 2019

arxiv: v2 [cs.cv] 29 Jan 2019 Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification Ivo M. Baltruschat 1,2,, Hannes Nickisch 3, Michael Grass 3, Tobias Knopp 1,2, and Axel Saalbach 3 arxiv:1803.02315v2 [cs.cv]

More information

Digital Breast Tomosynthesis from a first idea to clinical routine

Digital Breast Tomosynthesis from a first idea to clinical routine International Master Programm Biomedical Engineering Digital Breast Tomosynthesis from a first idea to clinical routine Historical background 2D imaging of 3D objects has important limitations Jörg Barkhausen

More information

Skin cancer reorganization and classification with deep neural network

Skin cancer reorganization and classification with deep neural network Skin cancer reorganization and classification with deep neural network Hao Chang 1 1. Department of Genetics, Yale University School of Medicine 2. Email: changhao86@gmail.com Abstract As one kind of skin

More information

'Automated dermatologist' detects skin cancer with expert accuracy - CNN.com

'Automated dermatologist' detects skin cancer with expert accuracy - CNN.com 'Automated dermatologist' detects skin cancer with expert accuracy (CNN)Even though the phrase "image recognition technologies" conjures visions of high-tech surveillance, these tools may soon be used

More information

Digital Breast Tomosynthesis in the Diagnostic Environment: A Subjective Side-by-Side Review

Digital Breast Tomosynthesis in the Diagnostic Environment: A Subjective Side-by-Side Review Women s Imaging Original Research Hakim et al. Digital Breast Tomosynthesis Women s Imaging Original Research Christiane M. Hakim 1 Denise M. Chough 1 Marie A. Ganott 1 Jules H. Sumkin 1 Margarita L. Zuley

More information

Highly Accurate Brain Stroke Diagnostic System and Generative Lesion Model. Junghwan Cho, Ph.D. CAIDE Systems, Inc. Deep Learning R&D Team

Highly Accurate Brain Stroke Diagnostic System and Generative Lesion Model. Junghwan Cho, Ph.D. CAIDE Systems, Inc. Deep Learning R&D Team Highly Accurate Brain Stroke Diagnostic System and Generative Lesion Model Junghwan Cho, Ph.D. CAIDE Systems, Inc. Deep Learning R&D Team Established in September, 2016 at 110 Canal st. Lowell, MA 01852,

More information

Classification of benign and malignant masses in breast mammograms

Classification of benign and malignant masses in breast mammograms Classification of benign and malignant masses in breast mammograms A. Šerifović-Trbalić*, A. Trbalić**, D. Demirović*, N. Prljača* and P.C. Cattin*** * Faculty of Electrical Engineering, University of

More information

Improving the breast cancer diagnosis using digital repositories

Improving the breast cancer diagnosis using digital repositories Improving the breast cancer diagnosis using digital repositories Cesar Suarez Ortega 1 cesar.suarez@ciemat.es, Jose M. Franco Valiente 1, Manuel Rubio del Solar 1, Guillermo Daz Herrero 1, Raul Ramos Pollan

More information

Disclosures. Breast Cancer. Breast Imaging Modalities. Breast Cancer Screening. Breast Cancer 6/4/2014

Disclosures. Breast Cancer. Breast Imaging Modalities. Breast Cancer Screening. Breast Cancer 6/4/2014 : Information for the Primary Care Physician Disclosures No financial relationships with commercial entities producing health care products/services. Roxsann Roberts, MD Section Chief, MRI Erlanger/EmCare

More information

GE Healthcare. Look differently. Invenia ABUS Automated Breast Ultrasound

GE Healthcare. Look differently. Invenia ABUS Automated Breast Ultrasound GE Healthcare Look differently. Invenia ABUS Automated Breast Ultrasound The unseen risk. Too many tumors are missed. 40% >1/3 Having dense breasts increases a women s likelihood to develop cancer four

More information

SD-CNN: a Shallow-Deep CNN for Improved Breast Cancer Diagnosis

SD-CNN: a Shallow-Deep CNN for Improved Breast Cancer Diagnosis 1 SD-CNN: a Shallow-Deep CNN for Improved Breast Cancer Diagnosis Fei Gao, Teresa Wu, Jing Li, Member, IEEE, Bin Zheng, Lingxiang Ruan, Desheng Shang and Bhavika Patel Abstract Breast cancer is the second

More information