Uncertainty Imaging · Aperivue/medsci-skills
Add calibrated uncertainty and OOD checks to imaging models
Helps design or audit the uncertainty-quantification, out-of-distribution detection, and abstention layer of a medical-imaging model, using methods like MC-dropout, deep ensembles, or conformal prediction, and checks coverage under distribution shift before a deployment claim is made.
Good for
- Audit a conformal prediction interval's actual coverage
- Add an out-of-distribution guard with held-out validation
- Set an abstention threshold at a pre-specified operating point
- Source repository
- Aperivue/medsci-skills
- Category
- Medicine
Open-source skills are maintained by their authors and listed as published, with attribution. Results depend on how well the skill fits your task and material.
A good place to start
Review my imaging model's uncertainty section — is the conformal interval coverage validated and is the OOD detector tested on real OOD data?
Make your next great thing.
Bring a question, a file, or an idea that’s not quite there yet.