MedOtter Abdominal Multi-Organ CT — Attention U-Net

2D AttU_Net for 11-organ abdominal CT segmentation, trained on AMOS22 (canonical labels). Self-contained: predictor.py (AttU_Net inlined) pulls weights.pth at load. Input: single-channel CT (1,i,j,k). Output {0=bg,1=liver,...,11=adrenal} on native grid. Per-slice: HU window [-160,240]->[0,1], resize 256, replicate 3ch, argmax.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support