Completed
Intro
Class Central Classrooms beta
YouTube playlists curated by Class Central.
Classroom Contents
MedAI - Training Medical Image Segmentation Models with Less Labeled Data - Sarah Hooper
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Many use cases for deep-learning based medical image segmentation
- 3 Goal: develop and validate methods to use mostly unlabeled data to train segmentation networks.
- 4 Overview Inputs: labeled data. S, and labeled data, Our approach two-step process using data augmentation with traditional supervision, self supervised learning and
- 5 Supervised loss: learn from the labeled data
- 6 Self-supervised loss: learn from the unlabeled data
- 7 Step 1: train initial segmentation network
- 8 Main evaluation questions
- 9 Tasks and evaluation metrics
- 10 Labeling reduction
- 11 Step 2: pseudo-label and retrain
- 12 Visualizations
- 13 Error modes
- 14 Biomarker evaluation
- 15 Generalization
- 16 Strengths
