RSNA lab details: build medical VLM datasets with EHR cohorts, de-ID and QC in Colab
PRouzrokh · x · 2026-11-04
Follow-up details on RSNA 2026 Deep Learning Lab 08: attendees will work through the full medical-imaging VLM dataset pipeline in a Colab notebook with public data — selecting a cohort from EHR and report data, pulling studies with pynetdicom, de-identifying images and reports, running quality control, and pairing each report with its images so the dataset is ready for VLM training.
Related event: RSNA 2026 Lab to Teach Building Medical Imaging VLM Datasets(2 posts)→
More from Companies & People
- Salesforce's 700-person AI org switched from Cursor to Claude Code, no mandate needed — aakashgupta · 2026-11-04
- Dev says ByteDance bots have been scraping his app for 18 months, eyeing CFAA lawsuit — Kyrannio · 2026-11-04
- Linear co-founder and CEO Karri Saarinen guests on podcast to talk design-led building — soleio · 2026-11-04
- vLLM, Red Hat and NVIDIA to host open-source inference meetup in Madrid on Nov 12 — vllm_project · 2026-11-04
- Superhuman CEO Shishir Mehrotra: the five AI debates every board is having — MatthewBerman · 2026-11-04
- Ollama CEO Jeffrey Morgan gives first Korea lecture on open models at Seoul National University — ollama · 2026-11-04