The result is a fair, end‑to‑end comparison that isolates what actually drives performance for radiology foundation models.
#AI #MedicalImaging #FoundationModels #ScalingLaws #Radiology
Max Ilse
I want to reshare @brandfonbrener.bsky.social's @NeurIPSConf 2024 paper on CoLoR-Filter: A simple yet powerful method for selecting high-quality data for language model pre-training!
With @hlzhang109.bsky.social @schwarzjn.bsky.social @shamkakade.bsky.social
We’re looking for a motivated researcher to apply for a Marie Skłodowska-Curie postdoc with our Econometrics & Data Science group at SDU!
Focus: Causal Inference, Machine Learning, Big Data
Full support for promising projects
More info & apply:
www.sdu.dk/en/om-sdu/in...
⚫⚪ It's coming...SHADES. ⚪⚫
The first ever resource of multilingual, multicultural, and multigeographical stereotypes, built to support nuanced LLM evaluation and bias mitigation. We have been working on this around the world for almost **4 years** and I am thrilled to share it with you all soon.
Why this matters: Prior comparisons of radiology encoders have often been apples‑to‑oranges: models trained on different datasets, with different compute budgets, and evaluated mostly on small datasets of finding‑only tasks.
What a damning abstract
✅ Pretrained on 3.5M CXRs to study scaling laws for radiology models
✅ Compared MedImageInsight (CLIP-based) vs RAD-DINO (DINOv2-based)
✅ Found that structured labels + text can significantly boost performance
✅ Showed that as little as 30k in-domain samples can outperform public foundation models
That makes it hard to tell whether wins come from the model design or just from more data/compute or favorable benchmarks. We fix this by holding the pretraining dataset and compute constant and standardizing evaluation across tasks,
including not just findings but also lines & tubes classification/segmentation and report generation. We also test the effect of adding structured labels alongside reports during CLIP‑style pretraining, and study scaling laws under these controlled conditions.
🩻Excited to share our latest preprint: “Data Scaling Laws for Radiology Foundation Models”
Foundation vision encoders like CLIP and DINOv2 have transformed general computer vision, but what happens when we scale them for medical imaging?
📄 Read the full preprint here: arxiv.org/abs/2509.12818
