DBTB INT Daniel Golden r
summary
Work uses convolutional neural networks to build automatic segmentation for radiology images, addressing the prior lack of labeled data and tooling. It presents a practical technique for getting more signal from messy data — mixing labeled and unlabeled sets, augmentations, and training tricks to improve segmentation performance — and reports lessons on what actually worked. Advice emphasizes diving in, collaborating with experienced data scientists, and practicing via Kaggle competitions.
AI-written summary · about
related talks
25mDeep Learning in Biomedicine: Challenges and Opportunities
43mBuilding AI That Learns and Adapts: A Case Study in MRI Diagnostics
49mBuilding AI That Learns and Adapts: A Case Study in MRI Diagnostics
48mNeural Networks and Brains
55mDeep Learning in Medical Image Diagnostics
50mBuilding AI That Learns and Adapts: A Case Study in MRI Diagnostics
36mBeyond Medical Image Segmentation. The Road Towards Clinical Insights
15mBrain Tumor Detection and Classification Using Deep Learning Models