Physics-based Fisher-KPP stroke model beats rCBF thresholding: Dice 0.46 vs 0.25
maier_ak · x · 2026-09-11
A physics-based stroke model embeds the Fisher-KPP reaction-diffusion equation into a patient's 3D MRI grid, with diffusion D(x) derived from the Tmax perfusion map and a logistic reaction term driving cell death.
On 29 ISLES 2017 patients it achieved mean Dice 0.46±0.24 and AUC-ROC 0.90±0.10, beating standard rCBF thresholding (Dice 0.25, AUC 0.70). Adding the diffusion term raised Dice by 0.12 over a reaction-only variant.
Related event: Physics-Based Reaction-Diffusion Model Improves Stroke Lesion Prediction(2 posts)→
More from Research
- ParetoRSI-Gym benchmarks whether AI agents can recursively self-improve LLMs across domains — Haojin Wang · 2026-10-28
- Stanford's Ψ-0.6 is a unified vision-language world model with adaptive reasoning streams — Stanford · 2026-10-28
- Shanghai AI Lab's OpenESM shows energy-steered models can scale as foundation learners — Shanghai-AI-Laboratory · 2026-10-28
- CellTrack-Bench tests VLMs on microscopic cell tracking, exposing reasoning gaps — biohub · 2026-10-28
- Hybrid LLM agent scores 83.2%, beats nine VLA policies on new SO-101 robot arm benchmark — Truman Hickok · 2026-10-28
- DeepMind researcher: all of mathematics will soon be formalizable, with agents hunting proofs — ChrSzegedy · 2026-10-28