Adversarial Debiasing With Partial Learning - Medical Image Studies

Adversarial Debiasing With Partial Learning - Medical Image Studies

Stanford MedAI via YouTube Direct link

Intro

1 of 22

1 of 22

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Adversarial Debiasing With Partial Learning - Medical Image Studies

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Bias in ML models
  3. 3 Background: Studying Biases in Medical AI models
  4. 4 These Algorithms Look at X-Rays-and Somehow Detect Your Race
  5. 5 Solution: Retrain Model With Balance Dataset
  6. 6 Emory CXR dataset Balanced Training
  7. 7 TPR disparities persist in "balanced" datasets
  8. 8 Adversarial debiasing: Unlearn Biasing features
  9. 9 Adversarial Debiasing Architecture
  10. 10 Adversarial Debiasing Background
  11. 11 Ablation Studies: Review
  12. 12 How do we identify the layers to debias?
  13. 13 Emory Mammogram Dataset • Cohorts of 150-180k patients each featuring screening
  14. 14 Emory Mammography Dataset (Race Distribution )
  15. 15 Deep learning model for tissue density classification
  16. 16 Studying Models Ability to predict Race
  17. 17 Findings on Predicting Race
  18. 18 Removing Race Related Features (Step 2)
  19. 19 TPR Disparity Measures
  20. 20 CXR Model Performance
  21. 21 Questions?
  22. 22 CXR Debiasing Results

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.