EdgeCVS
Models from EdgeCVS: Democratization of Surgical AI with a Distilled Edge-Deployable Critical View of Safety (CVS) Model (MICCAI 2026).
EdgeCVS assesses the three Critical View of Safety criteria in laparoscopic cholecystectomy from single frames, with a small model distilled from large multi-task teachers that runs in real time on a CPU.
Code: github.com/IMSY-DKFZ/edgecvs
Models
Each model lives in its own folder, named like the code's exp option:
Model (exp) |
Backbone | Params | Weights | SAGES-CVS 2024 test mAP |
|---|---|---|---|---|
edgecvs-5m |
EdgeNeXt-Small | 5.6M | fp16, 11 MB | 66.4 |
config.yaml index of the available models
edgecvs-5m/
βββ config.yaml model configuration used to build the network
βββ edgecvs-5m-fold0.safetensors weights (fold 0, fp16; loaded into an fp32 model)
EdgeCVS-5M
- Input: RGB frame, resized to 448Γ448, ImageNet normalization
- Output: probabilities for C1 (two structures), C2 (hepatocystic triangle) and C3 (cystic plate); optional 7-class anatomy segmentation (background, cystic plate, hepatocystic triangle, cystic artery, cystic duct, gallbladder, tool)
- Deployment: the segmentation head is optional; the classifier alone is used for the CSV predictions.
License
CC BY-NC 4.0: the models are trained on data released for non-commercial use.
Citation
@inproceedings{yamlahi2026edgecvs,
title={EdgeCVS: Democratization of Surgical AI with a Distilled Edge-Deployable Critical View of Safety (CVS) Model},
author={Yamlahi, Amine and Hennighausen, Jakob and Hansen, Pascal and Leeb, David and Maier-Hein, Lena},
booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
pages={134--144},
year={2026},
organization={Springer}
}
- Downloads last month
- 18