Improving Network Accuracy with Augmented Imagery Training Data

Size: px
Start display at page:

Download "Improving Network Accuracy with Augmented Imagery Training Data"

Transcription

1 Improving Network Accuracy with Augmented Imagery Training Data Ted Hromadka 1, LCDR Niels Olson 2 MD 1, 2 US Navy NMCSD Presented at GTC 2017

2 Goals Determine effectiveness of various affine transforms for augmenting medical imagery training data

3 Background prostate cancer is a significant problem for DoD US military s hospitals care for disproportionately more male patients Prostate cancer is second-leading cause of cancer death in American men Approximately 220,000 new cases per year Early screening involves a blood test for prostate-specific antigen (PSA) or a digital rectal exam (DRE) If those tests generate abnormal results, then a prostate biopsy may be required

4 Each biopsy procedure creates around 12 samples Prostate biopsy is conducted by taking core samples using a hollow needle After processing, 5 micron sections of these samples are placed on glass slides, stained, and manually interpreted by a pathologist under a microscope.

5 Analysis is very labor-intensive Digital scans are opened with custom viewing software from the microscope vendor Multiple zoom levels available up to 40x. This dataset was scanned at 20x. Pathologist will annotate cancerous regions with polygons drawn by hand with a mouse Process requires careful judgment and is susceptible to fatigue and stress factors. Polygons cannot be edited once drawn (e.g., at higher magnification).

6 Augmented data Necessary when training data set is too small to generalize Some data is more expensive to source Medical, copyrighted, classified, etc Also necessary when doing object detection, not just image classification Sensitivity and accuracy Generally supplementing original training data set with significant transforms Also synthesizing new training data from models or GANs

7 Using MNIST to demonstrate effect of rotation on CNN 70.0% 60.0% 50.0% 40.0% 30.0% 20.0% 10.0% 0.0%

8 DetectNet Released by NVIDIA with DIGITS4, last summer Based on KITTI - self-driving car computer vision project Incorporates some affine transformations as a training option detectnet_augmentation_param { crop_prob: 1.0 shift_x: 32 shift_y: 32 scale_prob: 0.4 scale_min: 0.8 scale_max: 1.2 flip_prob: 0.5 rotation_prob: 0.0 max_rotate_degree: 5.0 hue_rotation_prob: 0.8 hue_rotation: 30.0 desaturation_prob: 0.8 desaturation_max: 0.8 }

9 Test Procedure Goal controlling all other variables, determine the effect of each augmented data approach First evaluate DetectNet-supported parameters Stride (shift) Scale We have two variations on this: image zoom vs microscope zoom Flip (horizontal, vertical) Rotation, Hue, Desaturation Not relevant: Crop

10 Test Procedure Also evaluate factors beyond DetectNet Oversaturation Noise (random speckle) Artifacts Ink Scanning stripes Not evaluated: skew/shear, warping, squeeze mapping, non-affine transforms All tests use the same learning parameters and stock GoogLeNet on top of Caffe1 Cross-validation (25%) to reduce overfitting Each factor test run five times Once for each of 5 training/testing permutations (staggered 80%/20% cohorts) Accuracy results were averaged together at the end

11 Specifications System NVIDIA DevBox 1 4x NVIDIA TITAN X GPU 12GB memory per GPU 6-core Intel i7-5930k at 3.5 GHz with 64GB DDR4 Ubuntu 14.04, DIGITS 4, CUDA/cuDNN/NVCaffe DIGITS 5 rumored to support new image segmentation features

12 Specifications Imagery Source: NMCSD samples Data later shared with Cancer Moonshot, Joint Pathology Center, and commercial partners Collected, scanned, and annotated by NMCSD pathologists 202 annotated full-size color SVS images over 100K image 256px Average full size image ~ 845 MB

13 MATLAB image chipper prepared the images Split SVS into image chips of size 256x256 pixels at the 4:1 zoom level Chipper labels each image chip based on XML annotation polygons (50% inclusion rule for Caffe; more refined segmentation for TF) Chipper 2.0 also used pixel averaging and histograms to determine if chip was a blank. This could also be applied to ink smears. Original set of image chips were then augmented with a supplemental set of processed chips XML parser built on work by Andrew Janowczyk (

14 Need to handle pragmatic labeling, real-world data Training data suffers from some inaccuracies Annotation was not meant for training neural networks Not pixel-perfect Artifacts due to the scanner or tissue preparation Striping Ink

15 Side note: how accurate is the measure of accuracy? Elmore et al Breast Biopsy Concordance study found only 75% agreement between expert pathologists JAMA, 2015: If an image chip is 50% cancer and 50% other tissue, how should it be labeled? This issue already addressed in frameworks like TensorFlow (regions exactly specified in JSON), Caffe+DetectNet (regions specified in labels.txt up to 400px), other frameworks Need protocol for the confidence levels What threshold to use when network gives it a substantial but minority chance of cancer?

16 Original Naïve Model baseline Chip count Cancer: 38,080 Benign: 34,095 MATLAB None Effect Control set Overall Accuracy Precision Recall Sensitivity Specificity

17 Stride-varied Model Chip count Cancer: 35,033 Benign: 32,731 MATLAB None Effect Surprisingly similar to the control set Overall Accuracy Precision Recall Sensitivity Specificity

18 Flip Models Chip count Cancer: 76,160 Benign: 68,190 MATLAB B fliplr(a); B flipud(a); Effect in FlipH Consistent 2 point improvement. FlipV was similar. Overall Accuracy Precision Recall Sensitivity Specificity

19 Rotate-90 Model Chip count Cancer: 76,160 Benign: 68,190 MATLAB B imrotate(a, 90); Effect Slightly improved from flipping, not sure why Overall Accuracy Precision Recall Sensitivity Specificity

20 Rotate-360 Model Chip count Cancer: 152,320 Benign: 136,380 MATLAB B imrotate(a, 90); B imrotate(a, 180); B imrotate(a, 270); Effect 3-point improvement, no overfitting indicated Training loss rate decreased with validation loss Overall Accuracy Precision Recall Sensitivity Specificity

21 Hue Model Chip count Cancer: 76,160 Benign: 68,190 MATLAB H rgb2hsv(a); Effect H(:,:,1) H(:,:,1) * (rand / 50.0); B hsv2rgb(h); Insignificant Overall Accuracy Precision Recall Sensitivity Specificity

22 Saturation Model Chip count Cancer: 76,160 Benign: 68,190 MATLAB B(:,:,:) A(:,:,:) * 2; Effect Better at benign tissue De-saturation insignificant effect Overall Accuracy Precision Recall Sensitivity Specificity

23 Poisson Noise Model Chip count Cancer: 76,160 Benign: 68,190 MATLAB B imnoise(a, poisson ); Effect Promising, needs more variations (salt & pepper, etc) Overall Accuracy Precision Recall Sensitivity Specificity

24 Inked Model Chip count Cancer: 76,160 Benign: 68,190 MATLAB B ink(a); % 100-line script Effect Insignificant probably only helped with edge cases Overall Accuracy Precision Recall Sensitivity Specificity

25 Streaked Model Chip count Cancer: 76,160 Benign: 68,190 Pseudo-MATLAB Choose random column Starting from that col, add ++i to each col Do for 80 cols Effect Similar to inked version edge cases? Overall Accuracy Precision Recall Sensitivity Specificity

26 Conclusions For medical imagery Didn t help: Varying chip stride (a.k.a. translation) Hue Adding ink Adding scanner streaks Not sure: Horizontal and vertical flips Helpful: Rotations (surprising implies quantifiable orientation?) Oversaturation helped with benign tissue true identification Adding random noise was the most help Only tried Poisson, will explore other options

27 Current incarnation uses TensorFlow Shapely, TensorFlow, GoogLeNet, TensorBox Augmented with rotations + noise only Struggles with arteries, seminal vesicles Correctly labels benign tissue regions that were incorrectly included in cancer annotations

28 Next steps No signs of overfitting but seeking more data Adaptive refinement low-magnification whole slide image initially high-magnification regions of interest Try 128px chips (or higher magnification 256px chips) to reduce chance of multiple tissue types per image Ensemble classifiers for the edge cases Evaluating possible R&D deployment via HPCMP Portal on Hokule a machine

29 Thank you Ted Hromadka

Tumor Cellularity Assessment. Rene Bidart

Tumor Cellularity Assessment. Rene Bidart Tumor Cellularity Assessment Rene Bidart 1 Goals Find location and class of all cell nuclei: Lymphocyte Cells Normal Epithelial Cells Malignant Epithelial Cells Why: Test effectiveness of pre-surgery treatment

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

Automatic Prostate Cancer Classification using Deep Learning. Ida Arvidsson Centre for Mathematical Sciences, Lund University, Sweden

Automatic Prostate Cancer Classification using Deep Learning. Ida Arvidsson Centre for Mathematical Sciences, Lund University, Sweden Automatic Prostate Cancer Classification using Deep Learning Ida Arvidsson Centre for Mathematical Sciences, Lund University, Sweden Outline Autoencoders, theory Motivation, background and goal for prostate

More information

Retinopathy Net. Alberto Benavides Robert Dadashi Neel Vadoothker

Retinopathy Net. Alberto Benavides Robert Dadashi Neel Vadoothker Retinopathy Net Alberto Benavides Robert Dadashi Neel Vadoothker Motivation We were interested in applying deep learning techniques to the field of medical imaging Field holds a lot of promise and can

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

Image Classification with TensorFlow: Radiomics 1p/19q Chromosome Status Classification Using Deep Learning

Image Classification with TensorFlow: Radiomics 1p/19q Chromosome Status Classification Using Deep Learning Image Classification with TensorFlow: Radiomics 1p/19q Chromosome Status Classification Using Deep Learning Charles Killam, LP.D. Certified Instructor, NVIDIA Deep Learning Institute NVIDIA Corporation

More information

arxiv: v2 [cs.cv] 8 Mar 2017

arxiv: v2 [cs.cv] 8 Mar 2017 Detecting Cancer Metastases on Gigapixel Pathology Images arxiv:1703.02442v2 [cs.cv] 8 Mar 2017 Yun Liu 1, Krishna Gadepalli 1, Mohammad Norouzi 1, George E. Dahl 1, Timo Kohlberger 1, Aleksey Boyko 1,

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

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

Should I get screened for prostate cancer? What you should know about the PSA test

Should I get screened for prostate cancer? What you should know about the PSA test Should I get screened for prostate cancer? What you should know about the PSA test Should I get screened for prostate cancer? What you should know about the PSA test > What is PSA? Prostate-specific antigen

More information

Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images

Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images Sachin Mehta 1, Ezgi Mercan 1, Jamen Bartlett 2, Donald Weaver 2, Joann G. Elmore 1, and Linda Shapiro 1 1 University

More information

1. Benign Prostate Hyperplexia (BPH) 2. Prostate Cancer (PCa)

1. Benign Prostate Hyperplexia (BPH) 2. Prostate Cancer (PCa) Objectives: Our first segment focused in the anatomy and functions of the prostate gland, to get a clear understanding of the male Genito-Urinary System. Now, we will explore two of the main problems associated

More information

Combination of life science entrepreneurs, software development and machine vision experts & recognized scientists.

Combination of life science entrepreneurs, software development and machine vision experts & recognized scientists. Combination of life science entrepreneurs, software development and machine vision experts & recognized scientists. Kaisa Helminen CEO Previously: Sartorius Thermo Scientific Finnzymes Johan Lundin MD,

More information

Flexible, High Performance Convolutional Neural Networks for Image Classification

Flexible, High Performance Convolutional Neural Networks for Image Classification Flexible, High Performance Convolutional Neural Networks for Image Classification Dan C. Cireşan, Ueli Meier, Jonathan Masci, Luca M. Gambardella, Jürgen Schmidhuber IDSIA, USI and SUPSI Manno-Lugano,

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

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

Introduction. Growths in the prostate can be benign (not cancer) or malignant (cancer).

Introduction. Growths in the prostate can be benign (not cancer) or malignant (cancer). This information was taken from urologyhealth.org. Feel free to explore their website to learn more. Another trusted website with good information is the national comprehensive cancer network (nccn.org).

More information

Computational Pathology

Computational Pathology Computational Pathology In the Midst of a Revolution: How Computational Pathology is Transforming Clinical Practice and Biomedical Research Thomas J. Fuchs Associate Member, Memorial Sloan Kettering Cancer

More information

Diagnostic TRUS Elastography of the Prostate

Diagnostic TRUS Elastography of the Prostate Diagnostic TRUS Elastography of the Prostate George Zacharopoulos Department of Diagnostic Ultrasound Hygeia Hospital Athens, Greece Prostate HI-RTE Why we need Elastography Better Detection of possible

More information

Chapter 2. Understanding My Diagnosis

Chapter 2. Understanding My Diagnosis Chapter 2. Understanding My Diagnosis With contributions from Nancy L. Brown, Ph.D.,Palo Alto Medical Foundation Research Institute; and Patrick Swift, M.D., Alta Bates Comprehensive Cancer Program o Facts

More information

TWO HANDED SIGN LANGUAGE RECOGNITION SYSTEM USING IMAGE PROCESSING

TWO HANDED SIGN LANGUAGE RECOGNITION SYSTEM USING IMAGE PROCESSING 134 TWO HANDED SIGN LANGUAGE RECOGNITION SYSTEM USING IMAGE PROCESSING H.F.S.M.Fonseka 1, J.T.Jonathan 2, P.Sabeshan 3 and M.B.Dissanayaka 4 1 Department of Electrical And Electronic Engineering, Faculty

More information

BLADDER PROSTATE PENIS TESTICLES BE YO ND YO UR CA NC ER

BLADDER PROSTATE PENIS TESTICLES BE YO ND YO UR CA NC ER BLADDER PROSTATE PENIS TESTICLES THE PROSTATE IS A SMALL, WALNUT-SIZED GLAND THAT IS PART OF THE MALE REPRODUCTIVE SYSTEM. IT RESTS BELOW THE BLADDER, IN FRONT OF THE RECTUM AND SURROUNDS PART OF THE URETHRA.

More information

EARLY STAGE DIAGNOSIS OF LUNG CANCER USING CT-SCAN IMAGES BASED ON CELLULAR LEARNING AUTOMATE

EARLY STAGE DIAGNOSIS OF LUNG CANCER USING CT-SCAN IMAGES BASED ON CELLULAR LEARNING AUTOMATE EARLY STAGE DIAGNOSIS OF LUNG CANCER USING CT-SCAN IMAGES BASED ON CELLULAR LEARNING AUTOMATE SAKTHI NEELA.P.K Department of M.E (Medical electronics) Sengunthar College of engineering Namakkal, Tamilnadu,

More information

Digital Pathology and CAP Guidelines

Digital Pathology and CAP Guidelines Digital Pathology and CAP Guidelines Frequently asked questions The VENTANA family of digital pathology products empowers you with the convenience of a comprehensive image and workflow solution. When used

More information

COMPUTER-AIDED HER-2/neu EVALUATION IN EXTERNAL QUALITY ASSURANCE (EQA) OF BREAST CANCER SCREENING PROGRAMME

COMPUTER-AIDED HER-2/neu EVALUATION IN EXTERNAL QUALITY ASSURANCE (EQA) OF BREAST CANCER SCREENING PROGRAMME COMPUTER-AIDED HER-2/neu EVALUATION IN EXTERNAL QUALITY ASSURANCE (EQA) OF BREAST CANCER SCREENING PROGRAMME Maria Lunardi MD Anatomic Pathology Fracastoro Hospital San Bonifacio, Verona -Italy HER2-neu

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

Identification of Sickle Cells using Digital Image Processing. Academic Year Annexure I

Identification of Sickle Cells using Digital Image Processing. Academic Year Annexure I Academic Year 2014-15 Annexure I 1. Project Title: Identification of Sickle Cells using Digital Image Processing TABLE OF CONTENTS 1.1 Abstract 1-1 1.2 Motivation 1-1 1.3 Objective 2-2 2.1 Block Diagram

More information

Visual interpretation in pathology

Visual interpretation in pathology 13 Visual interpretation in pathology Tissue architecture (alteration) evaluation e.g., for grading prostate cancer Immunohistochemistry (IHC) staining scoring e.g., HER2 in breast cancer (companion diagnostic

More information

Algorithms in Nature. Pruning in neural networks

Algorithms in Nature. Pruning in neural networks Algorithms in Nature Pruning in neural networks Neural network development 1. Efficient signal propagation [e.g. information processing & integration] 2. Robust to noise and failures [e.g. cell or synapse

More information

Measuring cell density in prostate cancer imaging as an input for radiotherapy treatment planning

Measuring cell density in prostate cancer imaging as an input for radiotherapy treatment planning Measuring cell density in prostate cancer imaging as an input for radiotherapy treatment planning Poster No.: R-0262 Congress: 2014 CSM Type: Scientific Exhibit Authors: H. Reynolds, S. Williams, A. Zhang,

More information

Virtual Microscopy: Express Surgical Pathology Consultation. Mercè Jordà, University of Miami, Florida

Virtual Microscopy: Express Surgical Pathology Consultation. Mercè Jordà, University of Miami, Florida Virtual Microscopy: Express Surgical Pathology Consultation Mercè Jordà, University of Miami, Florida Telepathology versus Virtual microscopy (Digital Pathology) Telepathology Use of telecommunications

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

CC&S Session #4: Lesson Plan

CC&S Session #4: Lesson Plan CC&S Session #4: Lesson Plan Core Activities: Use parking lot to address questions/topics Complete Activity: Skin Cancer Flashcard Activity Supplies Needed: Session 4 handouts Flip Chart Markers Nametags

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

Supplemental Information

Supplemental Information Supplemental Information Prediction of Prostate Cancer Recurrence using Quantitative Phase Imaging Shamira Sridharan 1, Virgilia Macias 2, Krishnarao Tangella 3, André Kajdacsy-Balla 2 and Gabriel Popescu

More information

What Is Prostate Cancer? Prostate cancer is the development of cancer cells in the prostate gland (a gland that produces fluid for semen).

What Is Prostate Cancer? Prostate cancer is the development of cancer cells in the prostate gland (a gland that produces fluid for semen). What Is Prostate Cancer? Prostate cancer is the development of cancer cells in the prostate gland (a gland that produces fluid for semen). It is a very common cancer in men; some cancers grow very slowly,

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

Enter into the world of unprecedented accuracy! IScan D104 Series

Enter into the world of unprecedented accuracy! IScan D104 Series Enter into the world of unprecedented accuracy! IScan D104 Series 2 Three scanners, one goal: Precisely fitting restorations The D104 Series of 3D scanning systems is the 5th generation of dental scanners

More information

AJCC Cancer Staging 8 th Edition. Prostate Chapter 58. Executive Committee, AJCC. Professor and Director, Duke Prostate Center

AJCC Cancer Staging 8 th Edition. Prostate Chapter 58. Executive Committee, AJCC. Professor and Director, Duke Prostate Center AJCC Cancer Staging 8 th Edition Prostate Chapter 58 Judd W Moul, MD, FACS Executive Committee, AJCC Professor and Director, Duke Prostate Center Duke University Durham, North Carolina Validating science.

More information

Welcome to a better way for YOU and YOUR patient.

Welcome to a better way for YOU and YOUR patient. Welcome to a better way for YOU and YOUR patient. The Next Generation of Prostate Care from Invivo Current methods of prostate cancer screening, such as prostate-specifi c antigen (PSA) tests and digital

More information

Quality Assurance of Ultrasound Imaging in Radiation Therapy. Zuofeng Li, D.Sc. Murty S. Goddu, Ph.D. Washington University St.

Quality Assurance of Ultrasound Imaging in Radiation Therapy. Zuofeng Li, D.Sc. Murty S. Goddu, Ph.D. Washington University St. Quality Assurance of Ultrasound Imaging in Radiation Therapy Zuofeng Li, D.Sc. Murty S. Goddu, Ph.D. Washington University St. Louis, Missouri Typical Applications of Ultrasound Imaging in Radiation Therapy

More information

Convolutional Neural Networks (CNN)

Convolutional Neural Networks (CNN) Convolutional Neural Networks (CNN) Algorithm and Some Applications in Computer Vision Luo Hengliang Institute of Automation June 10, 2014 Luo Hengliang (Institute of Automation) Convolutional Neural Networks

More information

Digital Pathology - moving on after implementation. Catarina Eloy, MD, PhD

Digital Pathology - moving on after implementation. Catarina Eloy, MD, PhD Digital Pathology - moving on after implementation Catarina Eloy, MD, PhD Catarina Eloy, MD, PhD No conflict of interests to declare Pathology challenges today Maintaining high quality students interested

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

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

Experiment Presentation CS Chris Thomas Experiment: What is an Object? Alexe, Bogdan, et al. CVPR 2010

Experiment Presentation CS Chris Thomas Experiment: What is an Object? Alexe, Bogdan, et al. CVPR 2010 Experiment Presentation CS 3710 Chris Thomas Experiment: What is an Object? Alexe, Bogdan, et al. CVPR 2010 1 Preliminaries Code for What is An Object? available online Version 2.2 Achieves near 90% recall

More information

An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns

An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns 1. Introduction Vasily Morzhakov, Alexey Redozubov morzhakovva@gmail.com, galdrd@gmail.com Abstract Cortical

More information

Testing for. Prostate Cancer

Testing for. Prostate Cancer Testing for Prostate Cancer Who this booklet is for: This booklet is to help men who do not have any symptoms decide if they want to be tested. Prostate cancer affects many men. There are tests to find

More information

UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Midterm, 2016

UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Midterm, 2016 UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Midterm, 2016 Exam policy: This exam allows one one-page, two-sided cheat sheet; No other materials. Time: 80 minutes. Be sure to write your name and

More information

The Optical Biopsy. Douglas S. Scherr

The Optical Biopsy. Douglas S. Scherr Patricia Kuharic 66 The Optical Biopsy Douglas S. Scherr UROLOGY, WEILL CORNELL MEDICAL COLLEGE We want to create a better way to look inside the walls of a bladder for cancerous cells, eliminating the

More information

Keywords Fuzzy Logic, Fuzzy Rule, Fuzzy Membership Function, Fuzzy Inference System, Edge Detection, Regression Analysis.

Keywords Fuzzy Logic, Fuzzy Rule, Fuzzy Membership Function, Fuzzy Inference System, Edge Detection, Regression Analysis. Volume 6, Issue 3, March 2016 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Modified Fuzzy

More information

Automated Detection of Vascular Abnormalities in Diabetic Retinopathy using Morphological Entropic Thresholding with Preprocessing Median Fitter

Automated Detection of Vascular Abnormalities in Diabetic Retinopathy using Morphological Entropic Thresholding with Preprocessing Median Fitter IJSTE - International Journal of Science Technology & Engineering Volume 1 Issue 3 September 2014 ISSN(online) : 2349-784X Automated Detection of Vascular Abnormalities in Diabetic Retinopathy using Morphological

More information

Incorporation of Imaging-Based Functional Assessment Procedures into the DICOM Standard Draft version 0.1 7/27/2011

Incorporation of Imaging-Based Functional Assessment Procedures into the DICOM Standard Draft version 0.1 7/27/2011 Incorporation of Imaging-Based Functional Assessment Procedures into the DICOM Standard Draft version 0.1 7/27/2011 I. Purpose Drawing from the profile development of the QIBA-fMRI Technical Committee,

More information

arxiv: v2 [cs.cv] 7 Jun 2018

arxiv: v2 [cs.cv] 7 Jun 2018 Deep supervision with additional labels for retinal vessel segmentation task Yishuo Zhang and Albert C.S. Chung Lo Kwee-Seong Medical Image Analysis Laboratory, Department of Computer Science and Engineering,

More information

A re-audit of Prostate biopsies from January to December 2010 and 2013.

A re-audit of Prostate biopsies from January to December 2010 and 2013. A re-audit of Prostate biopsies from January to December 2010 and 2013. Dr. M S Siddiqui Consultant Histopathologist University Hospital of North Tees Stockton on Tees. Objectives To assess and compare

More information

Behavioral Data Mining. Lecture 4 Measurement

Behavioral Data Mining. Lecture 4 Measurement Behavioral Data Mining Lecture 4 Measurement Outline Hypothesis testing Parametric statistical tests Non-parametric tests Precision-Recall plots ROC plots Hardware update Icluster machines are ready for

More information

Patients EEG Data Analysis via Spectrogram Image with a Convolution Neural Network

Patients EEG Data Analysis via Spectrogram Image with a Convolution Neural Network Patients EEG Data Analysis via Spectrogram Image with a Convolution Neural Network Longhao Yuan and Jianting Cao ( ) Graduate School of Engineering, Saitama Institute of Technology, Fusaiji 1690, Fukaya-shi,

More information

Observership Program Anatomical Pathology

Observership Program Anatomical Pathology Observership Program Anatomical Pathology Pathology is the study and diagnosis of diseases through examination of organs, tissues, cells and bodily fluids. Pathology is a unique medical specialty in that

More information

Automated Brain Tumor Segmentation Using Region Growing Algorithm by Extracting Feature

Automated Brain Tumor Segmentation Using Region Growing Algorithm by Extracting Feature Automated Brain Tumor Segmentation Using Region Growing Algorithm by Extracting Feature Shraddha P. Dhumal 1, Ashwini S Gaikwad 2 1 Shraddha P. Dhumal 2 Ashwini S. Gaikwad ABSTRACT In this paper, we propose

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

Image analysis in IHC overview, considerations and applications

Image analysis in IHC overview, considerations and applications Image analysis in IHC overview, considerations and applications Rasmus Røge, MD, Institute of Pathology, Aalborg University Hospital NordiQC workshop September 2016 Aalborg, Denmark Outline Theory Image

More information

A DEEP LEARNING METHOD FOR DETECTING AND CLASSIFYING BREAST CANCER METASTASES IN LYMPH NODES ON HISTOPATHOLOGICAL IMAGES

A DEEP LEARNING METHOD FOR DETECTING AND CLASSIFYING BREAST CANCER METASTASES IN LYMPH NODES ON HISTOPATHOLOGICAL IMAGES A DEEP LEARNING METHOD FOR DETECTING AND CLASSIFYING BREAST CANCER METASTASES IN LYMPH NODES ON HISTOPATHOLOGICAL IMAGES Kaiwen Xiao 1, Zichen Wang 1, Tong Xu 1, Tao Wan 1,2 1 DeepCare Inc., Beijing, China

More information

Your Guide to Prostate Cancer

Your Guide to Prostate Cancer Your Guide to Prostate Cancer If you face a diagnosis of prostate cancer, what s next? We can help. A prostate cancer diagnosis can be overwhelming. The good news is that while prostate cancer can be serious,

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

Prostate Cancer CALIFORNIA COALITION. Fighting Prostate Cancer in California since 1997.

Prostate Cancer CALIFORNIA COALITION. Fighting Prostate Cancer in California since 1997. CALIFORNIA Prostate Cancer COALITION Fighting Prostate Cancer in California since 1997. A Proud Participant in the National Alliance of State Prostate Cancer Coalitions WHAT IS CANCER? According to the

More information

Visualize. Analyze. Personalize. OCT + OCTA

Visualize. Analyze. Personalize. OCT + OCTA Visualize. Analyze. Personalize. OCT + OCTA A New Approach to Protecting Vision AngioVue OCT Angiography brings valuable new information to clinical practice. Non-invasive visualization of retinal vasculature.

More information

Prostate cancer staging and datasets: The Nitty-Gritty. What determines our pathological reports? 06/07/2018. Dan Berney Maastricht 2018

Prostate cancer staging and datasets: The Nitty-Gritty. What determines our pathological reports? 06/07/2018. Dan Berney Maastricht 2018 Prostate cancer staging and datasets: The Nitty-Gritty What determines our pathological reports? Dan Berney Maastricht 2018 Biopsy reporting. How not to do it. The TNM 8 th edition. Changes good and bad

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

Questions and Answers About the Prostate-Specific Antigen (PSA) Test

Questions and Answers About the Prostate-Specific Antigen (PSA) Test CANCER FACTS N a t i o n a l C a n c e r I n s t i t u t e N a t i o n a l I n s t i t u t e s o f H e a l t h D e p a r t m e n t o f H e a l t h a n d H u m a n S e r v i c e s Questions and Answers

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

LUNG NODULE SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGE. Hemahashiny, Ketheesan Department of Physical Science, Vavuniya Campus

LUNG NODULE SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGE. Hemahashiny, Ketheesan Department of Physical Science, Vavuniya Campus LUNG NODULE SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGE Hemahashiny, Ketheesan Department of Physical Science, Vavuniya Campus tketheesan@vau.jfn.ac.lk ABSTRACT: The key process to detect the Lung cancer

More information

Central Pathology Review and Tissue MicroArrays. Dr Lisa Storer Children s Brain Tumour Research Centre Nottingham

Central Pathology Review and Tissue MicroArrays. Dr Lisa Storer Children s Brain Tumour Research Centre Nottingham Central Pathology Review and Tissue MicroArrays Dr Lisa Storer Children s Brain Tumour Research Centre Nottingham What is a tissue microarray? Tissue microarrays (TMAs) consist of paraffin blocks in which

More information

Prostate MRI Hamidreza Abdi, MD,FEBU Post Doctoral Fellow Vancouver Prostate Centre UBC Department of Urologic Sciences May-20144

Prostate MRI Hamidreza Abdi, MD,FEBU Post Doctoral Fellow Vancouver Prostate Centre UBC Department of Urologic Sciences May-20144 Prostate MRI Hamidreza Abdi, MD,FEBU Post Doctoral Fellow Vancouver Prostate Centre UBC Department of Urologic Sciences May-20144 Objectives: Detection of prostate cancer the need for better imaging What

More information

Kofax VRS. Installation Guide

Kofax VRS. Installation Guide Kofax VRS Installation Guide 2013-06-27 1999-2013 Kofax, Inc., 15211 Laguna Canyon Road, Irvine, California 92618, U.S.A. All rights reserved. Use is subject to license terms. Third-party software is copyrighted

More information

Using Deep Convolutional Networks for Gesture Recognition in American Sign Language

Using Deep Convolutional Networks for Gesture Recognition in American Sign Language Using Deep Convolutional Networks for Gesture Recognition in American Sign Language Abstract In the realm of multimodal communication, sign language is, and continues to be, one of the most understudied

More information

MEDICAL POLICY Genetic and Protein Biomarkers for Diagnosis and Risk Assessment of

MEDICAL POLICY Genetic and Protein Biomarkers for Diagnosis and Risk Assessment of POLICY: PG0367 ORIGINAL EFFECTIVE: 08/26/16 LAST REVIEW: 09/27/18 MEDICAL POLICY Genetic and Protein Biomarkers for Diagnosis and Risk Assessment of Prostate Cancer GUIDELINES This policy does not certify

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

Dolphin 3D Imaging 11.7 beta

Dolphin 3D Imaging 11.7 beta Dolphin 3D Imaging 11.7 beta Dolphin 3D Surgery Dolphin s 3D Surgery has expanded to include even more features! This revolutionary treatment planning and presentation software module now includes a fully

More information

arxiv: v1 [cs.cv] 24 Jul 2018

arxiv: v1 [cs.cv] 24 Jul 2018 Multi-Class Lesion Diagnosis with Pixel-wise Classification Network Manu Goyal 1, Jiahua Ng 2, and Moi Hoon Yap 1 1 Visual Computing Lab, Manchester Metropolitan University, M1 5GD, UK 2 University of

More information

Utilizing machine learning techniques to rapidly identify. MUC2 expression in colon cancer tissues

Utilizing machine learning techniques to rapidly identify. MUC2 expression in colon cancer tissues 1 Utilizing machine learning techniques to rapidly identify MUC2 expression in colon cancer tissues Thesis by Preethi Periyakoil In partial fulfillment of the requirements for the degree of Bachelor of

More information

Routine Quality Assurance Cookbook

Routine Quality Assurance Cookbook This Cookbook is a companion guide to the AIUM Routine Quality Assurance (QA) for Diagnostic Ultrasound Equipment document, which outlines the basic QA requirements for AIUM-accredited practices. The Guide

More information

Large-scale Histopathology Image Analysis for Colon Cancer on Azure

Large-scale Histopathology Image Analysis for Colon Cancer on Azure Large-scale Histopathology Image Analysis for Colon Cancer on Azure Yan Xu 1, 2 Tao Mo 2 Teng Gao 2 Maode Lai 4 Zhuowen Tu 2,3 Eric I-Chao Chang 2 1 Beihang University; 2 Microsoft Research Asia; 3 UCSD;

More information

International Journal of Engineering Trends and Applications (IJETA) Volume 4 Issue 2, Mar-Apr 2017

International Journal of Engineering Trends and Applications (IJETA) Volume 4 Issue 2, Mar-Apr 2017 RESEARCH ARTICLE OPEN ACCESS Knowledge Based Brain Tumor Segmentation using Local Maxima and Local Minima T. Kalaiselvi [1], P. Sriramakrishnan [2] Department of Computer Science and Applications The Gandhigram

More information

Prostate Cancer. What Are the Risk Factors? Prostate cancer is the second leading cancer that causes death to men in the U.S.

Prostate Cancer. What Are the Risk Factors? Prostate cancer is the second leading cancer that causes death to men in the U.S. Prostate cancer is the second leading cancer that causes death to men in the U.S. What Are the Risk Factors? Prostate cancer is unusual because it does not behave the same way in all men. Sometimes the

More information

Name AP Statistics UNIT 1 Summer Work Section II: Notes Analyzing Categorical Data

Name AP Statistics UNIT 1 Summer Work Section II: Notes Analyzing Categorical Data Name AP Statistics UNIT 1 Summer Work Date Section II: Notes 1.1 - Analyzing Categorical Data Essential Understanding: How can I represent the data when it is treated as a categorical variable? I. Distribution

More information

Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks

Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks Yongshuai Liu, Jiyu Chen, and Hao Chen University of California, Davis {yshliu, jiych, chen}@ucdavis.edu Abstract. Deep

More information

Prostate Cancer. David Wilkinson MD Gulfshore Urology

Prostate Cancer. David Wilkinson MD Gulfshore Urology Prostate Cancer David Wilkinson MD Gulfshore Urology What is the Prostate? Male Sexual Gland Adds nutrients and fluids for sperm This fluid is added to sperm during ejaculation Urethra (urine channel)

More information

Real Time Sign Language Processing System

Real Time Sign Language Processing System Real Time Sign Language Processing System Dibyabiva Seth (&), Anindita Ghosh, Ariruna Dasgupta, and Asoke Nath Department of Computer Science, St. Xavier s College (Autonomous), Kolkata, India meetdseth@gmail.com,

More information

Pushing the boundaries

Pushing the boundaries Samsung Medison is a global leading medical devices company. Founded in 1985, the company now sells cutting-edge medical devices including diagnostic ultrasound, digital X-ray and blood analyzer, around

More information

Patch-based Head and Neck Cancer Subtype Classification

Patch-based Head and Neck Cancer Subtype Classification Patch-based Head and Neck Cancer Subtype Classification Wanyi Qian, Guoli Yin, Frances Liu, Advisor: Olivier Gevaert, Mu Zhou, Kevin Brennan Stanford University wqian2@stanford.edu, guoliy@stanford.edu,

More information

AN ALGORITHM FOR EARLY BREAST CANCER DETECTION IN MAMMOGRAMS

AN ALGORITHM FOR EARLY BREAST CANCER DETECTION IN MAMMOGRAMS AN ALGORITHM FOR EARLY BREAST CANCER DETECTION IN MAMMOGRAMS Isaac N. Bankman', William A. Christens-Barryl, Irving N. Weinberg2, Dong W. Kim3, Ralph D. Semmell, and William R. Brody2 The Johns Hopkins

More information

Automatic Detection of Malaria Parasite from Blood Images

Automatic Detection of Malaria Parasite from Blood Images Volume 1, No. 3, May 2012 ISSN 2278-1080 The International Journal of Computer Science & Applications (TIJCSA) RESEARCH PAPER Available Online at http://www.journalofcomputerscience.com/ Automatic Detection

More information

Learning Convolutional Neural Networks for Graphs

Learning Convolutional Neural Networks for Graphs GA-65449 Learning Convolutional Neural Networks for Graphs Mathias Niepert Mohamed Ahmed Konstantin Kutzkov NEC Laboratories Europe Representation Learning for Graphs Telecom Safety Transportation Industry

More information

Diagnosis and Classification of Prostate Cancer

Diagnosis and Classification of Prostate Cancer Patient Information English 32 Diagnosis and Classification of Prostate Cancer The underlined terms are listed in the glossary. prostate biopsy is the only test that can confirm a prostate cancer diagnosis.

More information

Prostate Biopsy. Prostate Biopsy. We canʼt go backwards: Screening has helped!

Prostate Biopsy. Prostate Biopsy. We canʼt go backwards: Screening has helped! We canʼt go backwards: Screening has helped! Robert E. Donohue M.D. Denver V.A. Medical Center University of Colorado Prostate Biopsy Is cure necessary; when it is possible? Is cure possible; when it is

More information

A TREATMENT PLANNING STUDY COMPARING VMAT WITH 3D CONFORMAL RADIOTHERAPY FOR PROSTATE CANCER USING PINNACLE PLANNING SYSTEM *

A TREATMENT PLANNING STUDY COMPARING VMAT WITH 3D CONFORMAL RADIOTHERAPY FOR PROSTATE CANCER USING PINNACLE PLANNING SYSTEM * Romanian Reports in Physics, Vol. 66, No. 2, P. 394 400, 2014 A TREATMENT PLANNING STUDY COMPARING VMAT WITH 3D CONFORMAL RADIOTHERAPY FOR PROSTATE CANCER USING PINNACLE PLANNING SYSTEM * D. ADAM 1,2,

More information

Object Detectors Emerge in Deep Scene CNNs

Object Detectors Emerge in Deep Scene CNNs Object Detectors Emerge in Deep Scene CNNs Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba Presented By: Collin McCarthy Goal: Understand how objects are represented in CNNs Are

More information

Leukemia Blood Cell Image Classification Using Convolutional Neural Network

Leukemia Blood Cell Image Classification Using Convolutional Neural Network Leukemia Blood Cell Image Classification Using Convolutional Neural Network T. T. P. Thanh, Caleb Vununu, Sukhrob Atoev, Suk-Hwan Lee, and Ki-Ryong Kwon Abstract Acute myeloid leukemia is a type of malignant

More information