SlideShare a Scribd company logo
1 of 38
Download to read offline
Diagnosing heart
diseases
with deep neural networks
Introduction
• Julian de Wit
• Freelancer software / machine learning
• MSc. Software engineering
• Love biologically inspired computing
• Last few years neural net “revolution”
• Turn academic ideas into practical apps
• Documents, plant/fruit grading, Medical, radar
Agenda
1. Diagnose heart disease challenge
2. Deep learning
3. Solution discussion
4. Results
5. Some extra slides
6. Feel free to ask questions during talk !
Challenge
• Second national data science bowl
• Kaggle.com / Booz Allen Hamilton
• Automate manual 30min clinical procedure
• Ca. 500.000 cases/year in USA
• Estimate heart volume based on MRI’s
• Ratio systole/diastole is ‘health’ predictor
• 750 teams
• $200.000 prize money
Challenge
• Kaggle.com
• Competition platform for ‘data scientists’
• Challenges hosted for companies
• Prize money and exposure
• 400.000+ registered users
• Learn: Always someone smarter than you !
• Today’s state of the art is tomorrow’s baseline!
Challenge • Given: MRI’s, metadata, train-volumes
• Train 700, Test: 1000 patients, 300.000+ imgs
• Estimate volume of left ventricle
Deep learning
• Image data → Deep Learning (CNN)
• Neural networks 2.0
• Don’t believe ALL the hype
• Structured data → feature engineering + Tree/Lin
• Great when “perception” data is involved
• Spectacular results with image analysis
• My take: “Super human” with a twist
Solution • Step 1: Preprocessing
• Use DICOM info to make images uniform
• Crop around heart 180x180 (less distractions)
• For my solution less class imbalance
• Local contrast enhancement (CLAHE)
Solution
123ml
• Step 2: Train deep neural net
• Standard option: Regression with ‘Vanilla’ architecture.
• Approach used by most teams (ie. #2 Ghent university)
• Input slices, regress on provided volumes
Solution • Less publicized approach (mine): Segment images.
• Integrate estimated areas into volume using metadata.
• Problem: ‘No annotations provided.’ Sunnybrook/hand
Solution • Segmentation : Traditional architecture bad fit
• Every layer is higher level features less spatial info (BOW)
• Per pixel classification possible coarse due to spatial loss
• Cumbersome! H x W x 300.000 classifications.
Solution • Segmentation : Fully convolutional architecture + upscale
• Efficient. Classify all pixels at once
• Still problem spatial bottleneck at bottom : coarse
Solution • Segmentation : U-net architecture
• Skip connection give more detail in segmentation output
• Author works at Deepmind health now
• Resnet-like ?!?
Solution
• Segmentation results impressive.
• Machine did exactly what it was told.
• Confused with uncommon examples < 1%.
• Remedy : Active learning
• Nice property : brightness == (un)certainty
Solution • Last step: Integrate to volume.. should be simple
• Devil was in the details
PER PIXEL
SEGMENTATION
LEFT VENTRICLE
Y/N
SUM ALL PIXELS
AND USE
DICOM INFO TO
GET TO ML
100ML
...
...
...
...
n slices n overlays
Solution
• Devil in details: MUCH data cleaning
• Slice order
• Missing slices
• Out of bound slices
• Wrong orientation
• Missing frames
• BAD ground truth volumes
• Gradient boosting “calibration” procedure
• Not relevant in real setting. Just rescan MRI.
Results
• Result:
• 3rd place
• Only 1 model. No ensemble.
• Sub 10ml MAE → clinically significant
• Many improvements possible :
• More, cleaner train data
• Expert annotations
• Active learning
Appendix 1.
• Other approaches
• #1 Similar + 9 extra models
Segmentation, age, 4-chamber, regression on images etc.
• #2 Traditional, 250!! Models
Dynamic ensemble per patient
“Cool” end-to-end model
Appendix 2.
• U-nets and state of the art
• Potential successor dilated convolutions.
• No more bottleneck.
• Somewhat easier to use.
• Small improvements for personal project.
• Jury is still out.
• Kaggle: Ultrasound nerve segmentation
• U-nets was baseline and best solution.
• FCN also worked.
• No significant “discoveries”
• Dilated convolutions did not seem to work,
Appendix 3.
• Medical images challenges
• Deep learning => success
• Example: Kaggle retinopathy challenge
• As good as doctor (better in combination)
• Google deepmind (Jeffry De Fauw=Kaggler)
• Many other companies “copied” the solution
Summary
• Deep learning for medical imaging
EINDE....
Diagnosing heart diseases
with deep neural networks
Competition
• Kaggle.com
• Competition platform for ‘data scientists’
• Challenges hosted for companies
• Prize money and exposure
• 400.000+ registered competitors
• Learn. Always someone smarter than you !
• Today’s state of the art is tomorrow’s baseline!
My background
• Julian de Wit
• Freelancer software / machine learning
• Technical University Delft : SE
• Biologically inspired computing / AI
• Since 2006 heavily re-interested in neural nets
• Looking for opportunities to test and bring in
practice
Approach
n slices n overlays
PER PIXEL
SEGMENTATI
ON LEFT
VENTRICLE
Y/N
CLEAN DATA
& SUM
...
...
...
...
PROVIDED
VOLUMES
CALIBRATE 110ML
Calibration
• Use provided volumes to calibrate
• Remove systematic errors
• Use Gradient Booster on residuals
• Top 5 -> top 3
• Beware of overfitting
Approach
• Every pixel: Left ventricle Yes/No
• Use convolutional neural network
• Sunnybrook too simplistic
• Train with hand-labeled segmentations
• Reverse engineer how to label
• Fix systematic errors with calibration against
provided volumes.
Competition
Deep learning
Labeling
• Hand labeling with own tool
• Big performance limiting factor
• Could not find how to do it exactly
Cat!
Cat !
Grass
Submission
• CRPS
• Uncertainty based on stdev in error as a
function of size.
• Model provided uncertainty.
• However does not account for uncertainty in
labels
• Example: patient 429. Error of 89ml !!!
• Provided label was wrong…

More Related Content

Viewers also liked

Scikit-Learn: Machine Learning in Python
Scikit-Learn: Machine Learning in PythonScikit-Learn: Machine Learning in Python
Scikit-Learn: Machine Learning in PythonMicrosoft
 
Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?Manuel Martín
 
Automatic Machine Learning, AutoML
Automatic Machine Learning, AutoMLAutomatic Machine Learning, AutoML
Automatic Machine Learning, AutoMLHimadri Mishra
 
Data Science and Machine Learning Using Python and Scikit-learn
Data Science and Machine Learning Using Python and Scikit-learnData Science and Machine Learning Using Python and Scikit-learn
Data Science and Machine Learning Using Python and Scikit-learnAsim Jalis
 
A Beginner's Guide to Machine Learning with Scikit-Learn
A Beginner's Guide to Machine Learning with Scikit-LearnA Beginner's Guide to Machine Learning with Scikit-Learn
A Beginner's Guide to Machine Learning with Scikit-LearnSarah Guido
 
Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnBenjamin Bengfort
 
Introduction to Machine Learning with Python and scikit-learn
Introduction to Machine Learning with Python and scikit-learnIntroduction to Machine Learning with Python and scikit-learn
Introduction to Machine Learning with Python and scikit-learnMatt Hagy
 
New Developments in Spark
New Developments in SparkNew Developments in Spark
New Developments in SparkDatabricks
 
Practical Machine Learning in Python
Practical Machine Learning in PythonPractical Machine Learning in Python
Practical Machine Learning in PythonMatt Spitz
 
Insights Without Tradeoffs: Using Structured Streaming
Insights Without Tradeoffs: Using Structured StreamingInsights Without Tradeoffs: Using Structured Streaming
Insights Without Tradeoffs: Using Structured StreamingDatabricks
 
"Deep Learning" Chap.6 Convolutional Neural Net
"Deep Learning" Chap.6 Convolutional Neural Net"Deep Learning" Chap.6 Convolutional Neural Net
"Deep Learning" Chap.6 Convolutional Neural NetKen'ichi Matsui
 
Machine learning with scikitlearn
Machine learning with scikitlearnMachine learning with scikitlearn
Machine learning with scikitlearnPratap Dangeti
 
Realtime Analytical Query Processing and Predictive Model Building on High Di...
Realtime Analytical Query Processing and Predictive Model Building on High Di...Realtime Analytical Query Processing and Predictive Model Building on High Di...
Realtime Analytical Query Processing and Predictive Model Building on High Di...Spark Summit
 
Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningSujit Pal
 
Making Structured Streaming Ready for Production
Making Structured Streaming Ready for ProductionMaking Structured Streaming Ready for Production
Making Structured Streaming Ready for ProductionDatabricks
 
Introduce Deep learning & A.I. Applications
Introduce Deep learning & A.I. ApplicationsIntroduce Deep learning & A.I. Applications
Introduce Deep learning & A.I. ApplicationsMario Cho
 
Artificial Intelligence: Predictions for 2017
Artificial Intelligence: Predictions for 2017Artificial Intelligence: Predictions for 2017
Artificial Intelligence: Predictions for 2017NVIDIA
 

Viewers also liked (18)

Scikit-Learn: Machine Learning in Python
Scikit-Learn: Machine Learning in PythonScikit-Learn: Machine Learning in Python
Scikit-Learn: Machine Learning in Python
 
Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?
 
Automatic Machine Learning, AutoML
Automatic Machine Learning, AutoMLAutomatic Machine Learning, AutoML
Automatic Machine Learning, AutoML
 
Data Science and Machine Learning Using Python and Scikit-learn
Data Science and Machine Learning Using Python and Scikit-learnData Science and Machine Learning Using Python and Scikit-learn
Data Science and Machine Learning Using Python and Scikit-learn
 
A Beginner's Guide to Machine Learning with Scikit-Learn
A Beginner's Guide to Machine Learning with Scikit-LearnA Beginner's Guide to Machine Learning with Scikit-Learn
A Beginner's Guide to Machine Learning with Scikit-Learn
 
Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-Learn
 
Introduction to Machine Learning with Python and scikit-learn
Introduction to Machine Learning with Python and scikit-learnIntroduction to Machine Learning with Python and scikit-learn
Introduction to Machine Learning with Python and scikit-learn
 
New Developments in Spark
New Developments in SparkNew Developments in Spark
New Developments in Spark
 
Practical Machine Learning in Python
Practical Machine Learning in PythonPractical Machine Learning in Python
Practical Machine Learning in Python
 
Insights Without Tradeoffs: Using Structured Streaming
Insights Without Tradeoffs: Using Structured StreamingInsights Without Tradeoffs: Using Structured Streaming
Insights Without Tradeoffs: Using Structured Streaming
 
"Deep Learning" Chap.6 Convolutional Neural Net
"Deep Learning" Chap.6 Convolutional Neural Net"Deep Learning" Chap.6 Convolutional Neural Net
"Deep Learning" Chap.6 Convolutional Neural Net
 
Machine learning with scikitlearn
Machine learning with scikitlearnMachine learning with scikitlearn
Machine learning with scikitlearn
 
Realtime Analytical Query Processing and Predictive Model Building on High Di...
Realtime Analytical Query Processing and Predictive Model Building on High Di...Realtime Analytical Query Processing and Predictive Model Building on High Di...
Realtime Analytical Query Processing and Predictive Model Building on High Di...
 
Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep Learning
 
Making Structured Streaming Ready for Production
Making Structured Streaming Ready for ProductionMaking Structured Streaming Ready for Production
Making Structured Streaming Ready for Production
 
Deep learning
Deep learningDeep learning
Deep learning
 
Introduce Deep learning & A.I. Applications
Introduce Deep learning & A.I. ApplicationsIntroduce Deep learning & A.I. Applications
Introduce Deep learning & A.I. Applications
 
Artificial Intelligence: Predictions for 2017
Artificial Intelligence: Predictions for 2017Artificial Intelligence: Predictions for 2017
Artificial Intelligence: Predictions for 2017
 

Similar to Julian - diagnosing heart disease using convolutional neural networks

NYC Open Data Meetup-- Thoughtworks chief data scientist talk
NYC Open Data Meetup-- Thoughtworks chief data scientist talkNYC Open Data Meetup-- Thoughtworks chief data scientist talk
NYC Open Data Meetup-- Thoughtworks chief data scientist talkVivian S. Zhang
 
Artificial Intelligence and the Data Center
Artificial Intelligence and the Data CenterArtificial Intelligence and the Data Center
Artificial Intelligence and the Data Centersflaig
 
(Em)Powering Science: High-Performance Infrastructure in Biomedical Science
(Em)Powering Science: High-Performance Infrastructure in Biomedical Science(Em)Powering Science: High-Performance Infrastructure in Biomedical Science
(Em)Powering Science: High-Performance Infrastructure in Biomedical ScienceAri Berman
 
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr..."Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...Edge AI and Vision Alliance
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerPoo Kuan Hoong
 
Data Science Consulting at ThoughtWorks -- NYC Open Data Meetup
Data Science Consulting at ThoughtWorks -- NYC Open Data MeetupData Science Consulting at ThoughtWorks -- NYC Open Data Meetup
Data Science Consulting at ThoughtWorks -- NYC Open Data MeetupDavid Johnston
 
Presentation Selan dos Santos 4Eyes Lab
Presentation Selan dos Santos 4Eyes LabPresentation Selan dos Santos 4Eyes Lab
Presentation Selan dos Santos 4Eyes Labselan_rds
 
Putting the Magic in Data Science
Putting the Magic in Data SciencePutting the Magic in Data Science
Putting the Magic in Data ScienceSean Taylor
 
Introduction to Big Data and its Potential for Dementia Research
Introduction to Big Data and its Potential for Dementia ResearchIntroduction to Big Data and its Potential for Dementia Research
Introduction to Big Data and its Potential for Dementia ResearchDavid De Roure
 
WCG7 (assembled)
WCG7 (assembled)WCG7 (assembled)
WCG7 (assembled)Vivek Mehta
 
brain_tumor_detection.pptxdsksv dkvdksvbkdsk
brain_tumor_detection.pptxdsksv dkvdksvbkdskbrain_tumor_detection.pptxdsksv dkvdksvbkdsk
brain_tumor_detection.pptxdsksv dkvdksvbkdsklikhithkumpala159
 
H2O intro at Dallas Meetup
H2O intro at Dallas MeetupH2O intro at Dallas Meetup
H2O intro at Dallas MeetupSri Ambati
 
TraitCapture: NextGen Monitoring and Visualization from seed to ecosystem
TraitCapture: NextGen Monitoring and Visualization from seed to ecosystemTraitCapture: NextGen Monitoring and Visualization from seed to ecosystem
TraitCapture: NextGen Monitoring and Visualization from seed to ecosystemTimeScience
 
Deep learning introduction
Deep learning introductionDeep learning introduction
Deep learning introductionAdwait Bhave
 
Deep learning health care
Deep learning health care  Deep learning health care
Deep learning health care Meenakshi Sood
 
Data-driven hypothesis generation using deep neural nets
Data-driven hypothesis generation using deep neural netsData-driven hypothesis generation using deep neural nets
Data-driven hypothesis generation using deep neural netsBalázs Kégl
 
GTU GeekDay 2019 Limitations of Artificial Intelligence
GTU GeekDay 2019 Limitations of Artificial IntelligenceGTU GeekDay 2019 Limitations of Artificial Intelligence
GTU GeekDay 2019 Limitations of Artificial IntelligenceKürşat İNCE
 

Similar to Julian - diagnosing heart disease using convolutional neural networks (20)

NYC Open Data Meetup-- Thoughtworks chief data scientist talk
NYC Open Data Meetup-- Thoughtworks chief data scientist talkNYC Open Data Meetup-- Thoughtworks chief data scientist talk
NYC Open Data Meetup-- Thoughtworks chief data scientist talk
 
Artificial Intelligence and the Data Center
Artificial Intelligence and the Data CenterArtificial Intelligence and the Data Center
Artificial Intelligence and the Data Center
 
Computer Design Concepts for Machine Learning
Computer Design Concepts for Machine LearningComputer Design Concepts for Machine Learning
Computer Design Concepts for Machine Learning
 
(Em)Powering Science: High-Performance Infrastructure in Biomedical Science
(Em)Powering Science: High-Performance Infrastructure in Biomedical Science(Em)Powering Science: High-Performance Infrastructure in Biomedical Science
(Em)Powering Science: High-Performance Infrastructure in Biomedical Science
 
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr..."Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
 
AlexNet
AlexNetAlexNet
AlexNet
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
 
Data Science Consulting at ThoughtWorks -- NYC Open Data Meetup
Data Science Consulting at ThoughtWorks -- NYC Open Data MeetupData Science Consulting at ThoughtWorks -- NYC Open Data Meetup
Data Science Consulting at ThoughtWorks -- NYC Open Data Meetup
 
Presentation Selan dos Santos 4Eyes Lab
Presentation Selan dos Santos 4Eyes LabPresentation Selan dos Santos 4Eyes Lab
Presentation Selan dos Santos 4Eyes Lab
 
Putting the Magic in Data Science
Putting the Magic in Data SciencePutting the Magic in Data Science
Putting the Magic in Data Science
 
Introduction to Big Data and its Potential for Dementia Research
Introduction to Big Data and its Potential for Dementia ResearchIntroduction to Big Data and its Potential for Dementia Research
Introduction to Big Data and its Potential for Dementia Research
 
WCG7 (assembled)
WCG7 (assembled)WCG7 (assembled)
WCG7 (assembled)
 
brain_tumor_detection.pptxdsksv dkvdksvbkdsk
brain_tumor_detection.pptxdsksv dkvdksvbkdskbrain_tumor_detection.pptxdsksv dkvdksvbkdsk
brain_tumor_detection.pptxdsksv dkvdksvbkdsk
 
H2O intro at Dallas Meetup
H2O intro at Dallas MeetupH2O intro at Dallas Meetup
H2O intro at Dallas Meetup
 
TraitCapture: NextGen Monitoring and Visualization from seed to ecosystem
TraitCapture: NextGen Monitoring and Visualization from seed to ecosystemTraitCapture: NextGen Monitoring and Visualization from seed to ecosystem
TraitCapture: NextGen Monitoring and Visualization from seed to ecosystem
 
Deep learning introduction
Deep learning introductionDeep learning introduction
Deep learning introduction
 
Deep learning health care
Deep learning health care  Deep learning health care
Deep learning health care
 
Data-driven hypothesis generation using deep neural nets
Data-driven hypothesis generation using deep neural netsData-driven hypothesis generation using deep neural nets
Data-driven hypothesis generation using deep neural nets
 
GTU GeekDay 2019 Limitations of Artificial Intelligence
GTU GeekDay 2019 Limitations of Artificial IntelligenceGTU GeekDay 2019 Limitations of Artificial Intelligence
GTU GeekDay 2019 Limitations of Artificial Intelligence
 
Ml - A shallow dive
Ml  - A shallow diveMl  - A shallow dive
Ml - A shallow dive
 

Recently uploaded

Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfsanyamsingh5019
 
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxContemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxRoyAbrique
 
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdfBASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdfSoniaTolstoy
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introductionMaksud Ahmed
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxpboyjonauth
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...EduSkills OECD
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)eniolaolutunde
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionSafetyChain Software
 
Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Educationpboyjonauth
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...Marc Dusseiller Dusjagr
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingTechSoup
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Krashi Coaching
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxSayali Powar
 
CARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxCARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxGaneshChakor2
 
Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3JemimahLaneBuaron
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactPECB
 
Interactive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationInteractive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationnomboosow
 
Arihant handbook biology for class 11 .pdf
Arihant handbook biology for class 11 .pdfArihant handbook biology for class 11 .pdf
Arihant handbook biology for class 11 .pdfchloefrazer622
 

Recently uploaded (20)

Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdf
 
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxContemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
 
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdfBASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introduction
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptx
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory Inspection
 
Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Education
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
 
CARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxCARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptx
 
Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3Q4-W6-Restating Informational Text Grade 3
Q4-W6-Restating Informational Text Grade 3
 
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptxINDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
 
Interactive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationInteractive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communication
 
Arihant handbook biology for class 11 .pdf
Arihant handbook biology for class 11 .pdfArihant handbook biology for class 11 .pdf
Arihant handbook biology for class 11 .pdf
 

Julian - diagnosing heart disease using convolutional neural networks

  • 2. Introduction • Julian de Wit • Freelancer software / machine learning • MSc. Software engineering • Love biologically inspired computing • Last few years neural net “revolution” • Turn academic ideas into practical apps • Documents, plant/fruit grading, Medical, radar
  • 3. Agenda 1. Diagnose heart disease challenge 2. Deep learning 3. Solution discussion 4. Results 5. Some extra slides 6. Feel free to ask questions during talk !
  • 4. Challenge • Second national data science bowl • Kaggle.com / Booz Allen Hamilton • Automate manual 30min clinical procedure • Ca. 500.000 cases/year in USA • Estimate heart volume based on MRI’s • Ratio systole/diastole is ‘health’ predictor • 750 teams • $200.000 prize money
  • 5. Challenge • Kaggle.com • Competition platform for ‘data scientists’ • Challenges hosted for companies • Prize money and exposure • 400.000+ registered users • Learn: Always someone smarter than you ! • Today’s state of the art is tomorrow’s baseline!
  • 6. Challenge • Given: MRI’s, metadata, train-volumes • Train 700, Test: 1000 patients, 300.000+ imgs • Estimate volume of left ventricle
  • 7. Deep learning • Image data → Deep Learning (CNN) • Neural networks 2.0 • Don’t believe ALL the hype • Structured data → feature engineering + Tree/Lin • Great when “perception” data is involved • Spectacular results with image analysis • My take: “Super human” with a twist
  • 8. Solution • Step 1: Preprocessing • Use DICOM info to make images uniform • Crop around heart 180x180 (less distractions) • For my solution less class imbalance • Local contrast enhancement (CLAHE)
  • 9. Solution 123ml • Step 2: Train deep neural net • Standard option: Regression with ‘Vanilla’ architecture. • Approach used by most teams (ie. #2 Ghent university) • Input slices, regress on provided volumes
  • 10. Solution • Less publicized approach (mine): Segment images. • Integrate estimated areas into volume using metadata. • Problem: ‘No annotations provided.’ Sunnybrook/hand
  • 11. Solution • Segmentation : Traditional architecture bad fit • Every layer is higher level features less spatial info (BOW) • Per pixel classification possible coarse due to spatial loss • Cumbersome! H x W x 300.000 classifications.
  • 12. Solution • Segmentation : Fully convolutional architecture + upscale • Efficient. Classify all pixels at once • Still problem spatial bottleneck at bottom : coarse
  • 13. Solution • Segmentation : U-net architecture • Skip connection give more detail in segmentation output • Author works at Deepmind health now • Resnet-like ?!?
  • 14. Solution • Segmentation results impressive. • Machine did exactly what it was told. • Confused with uncommon examples < 1%. • Remedy : Active learning • Nice property : brightness == (un)certainty
  • 15. Solution • Last step: Integrate to volume.. should be simple • Devil was in the details PER PIXEL SEGMENTATION LEFT VENTRICLE Y/N SUM ALL PIXELS AND USE DICOM INFO TO GET TO ML 100ML ... ... ... ... n slices n overlays
  • 16. Solution • Devil in details: MUCH data cleaning • Slice order • Missing slices • Out of bound slices • Wrong orientation • Missing frames • BAD ground truth volumes • Gradient boosting “calibration” procedure • Not relevant in real setting. Just rescan MRI.
  • 17. Results • Result: • 3rd place • Only 1 model. No ensemble. • Sub 10ml MAE → clinically significant • Many improvements possible : • More, cleaner train data • Expert annotations • Active learning
  • 18. Appendix 1. • Other approaches • #1 Similar + 9 extra models Segmentation, age, 4-chamber, regression on images etc. • #2 Traditional, 250!! Models Dynamic ensemble per patient “Cool” end-to-end model
  • 19. Appendix 2. • U-nets and state of the art • Potential successor dilated convolutions. • No more bottleneck. • Somewhat easier to use. • Small improvements for personal project. • Jury is still out. • Kaggle: Ultrasound nerve segmentation • U-nets was baseline and best solution. • FCN also worked. • No significant “discoveries” • Dilated convolutions did not seem to work,
  • 20. Appendix 3. • Medical images challenges • Deep learning => success • Example: Kaggle retinopathy challenge • As good as doctor (better in combination) • Google deepmind (Jeffry De Fauw=Kaggler) • Many other companies “copied” the solution
  • 21. Summary • Deep learning for medical imaging
  • 22.
  • 24. Diagnosing heart diseases with deep neural networks
  • 25. Competition • Kaggle.com • Competition platform for ‘data scientists’ • Challenges hosted for companies • Prize money and exposure • 400.000+ registered competitors • Learn. Always someone smarter than you ! • Today’s state of the art is tomorrow’s baseline!
  • 26. My background • Julian de Wit • Freelancer software / machine learning • Technical University Delft : SE • Biologically inspired computing / AI • Since 2006 heavily re-interested in neural nets • Looking for opportunities to test and bring in practice
  • 27. Approach n slices n overlays PER PIXEL SEGMENTATI ON LEFT VENTRICLE Y/N CLEAN DATA & SUM ... ... ... ... PROVIDED VOLUMES CALIBRATE 110ML
  • 28. Calibration • Use provided volumes to calibrate • Remove systematic errors • Use Gradient Booster on residuals • Top 5 -> top 3 • Beware of overfitting
  • 29. Approach • Every pixel: Left ventricle Yes/No • Use convolutional neural network • Sunnybrook too simplistic • Train with hand-labeled segmentations • Reverse engineer how to label • Fix systematic errors with calibration against provided volumes.
  • 32. Labeling • Hand labeling with own tool • Big performance limiting factor • Could not find how to do it exactly
  • 33. Cat!
  • 34. Cat !
  • 35. Grass
  • 36.
  • 37.
  • 38. Submission • CRPS • Uncertainty based on stdev in error as a function of size. • Model provided uncertainty. • However does not account for uncertainty in labels • Example: patient 429. Error of 89ml !!! • Provided label was wrong…