RadFusion: Threshold-Controllable Radiology Report Generation for Clinical Flexibility
erichorvitz · x · 2026-08-15
Microsoft Research and collaborators introduce RadFusion, a framework that fuses a classifier and a generator to enable threshold-controllable radiology report generation. By adjusting thresholds, clinicians can trade off sensitivity and specificity, and the generated reports align with the chosen operating points. Validated on MIMIC-CXR, it conforms to the classifier's ROC curve, potentially aiding regulatory approval.
More from Multimodal
- Meituan LongCat's WorldCast benchmark: GPT-Image-2.5 tops at 72.8, open-source lags — meituan-longcat · 2026-10-16
- Three resources to get up to speed with FLUX 3 — ariG23498 · 2026-10-16
- Watch: Claude Opus 5.5 builds a Tesla Roadster from a single prompt — TAbrodi · 2026-10-16
- Midjourney v8.2 turns out striking indigo ink-wash art with sref 1848359068 — azed_ai · 2026-10-16
- "AI television from another dimension": robot grooms a chihuahua on air — BotLordBotflix · 2026-10-16
- 108M-parameter text-to-image denoiser Surjo-Image-Preview lands on Hugging Face — Consistent-Rule-3720 · 2026-10-16