| license: apache-2.0 | |
| tags: | |
| - medical-imaging | |
| - model-reliability | |
| - calibration | |
| - robustness | |
| - cancer-imaging | |
| # FIDELIS β Reliability Estimators | |
| Model artifacts for **FIDELIS**, an open-source tool that evaluates the **calibration** and **robustness** | |
| of trained deep-learning models in cancer imaging. FIDELIS operates **post-hoc** on a model's outputs β no | |
| retraining, no access to the original training data β and returns a clinician-facing reliability report. | |
| - Code: https://github.com/ZhixiangWang-CN/FIDELIS | |
| - Program: NCI ITCR (RFA-CA-27-019, U01) | |
| ## Components (to be released) | |
| - **FIDELIS-Calibrate** β post-hoc calibration assessment (Anatomy-Aware ECE / ΞA-ECE) and recalibration maps. | |
| - **FIDELIS-Robust** β stability under simulated scanner / dose / protocol variation. | |
| - **Clinical Decision Impact (CDI)** β maps reliability failures to potential changes in a clinical decision. | |
| ## Status | |
| Repository reserved during early development; trained components and full **model cards** will be uploaded | |
| and version-tagged with each release. Not a diagnostic device; not for autonomous clinical decision-making. | |
| ## License | |
| Code components: Apache-2.0. Standalone model weights: CC-BY-4.0. | |