• 🔥 A detailed papers list of conformal prediction for medical image analysis is regularly maintained in awesome-mia-conformal.
• 🔥 The UQinMIA @ MICCAI'25 tutorial slides and start-up code for using conformal prediction in medical VLMs are available at uqinmia-miccai-25.

The official implementation of Full Conformal Adaptation of Medical Vision-Language Models.
📜 Int. Conference on Information Processing in Medical Imaging (Oral)
Julio Silva-Rodríguez¹, Leo Fillioux², Paul-Henry Cournède², Maria Vakalopoulou²,
Stergios Christodoulidis², Ismail Ben Ayed¹, Jose Dolz^1
1ÉTS Montréal ⋅ ²CentraleSupélec, Université Paris-Saclay
| Conference | ArXiv | Tutorial |

• Install in your environment a compatible torch version with your GPU. For example:

conda create -n fcaenv python=3.11 -y
conda activate fcaenv
pip install torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 --index-url https://download.pytorch.org/whl/cu124

git clone https://github.com/jusiro/FCA.git
cd FCA
pip install -r requirements.txt

• Configure data paths (see ./local_data/constants.py).
• Download, and configure datasets (see ./local_data/datasets/README.md).

We present the basic usage here.

(a) Features extraction:

• python extract_features.py --task Gleason,MESSIDOR

(b) Spit conformal prediction (SCP):

• python scp.py --task Gleason,MESSIDOR --k 16 --alpha 0.10 --ncscore lac

(c) Full conformal adaptation (FCA):

• python fca.py --task Gleason,MESSIDOR --k 16 --alpha 0.10 --ncscore lac

You will find the results upon training at ./local_data/results/.

If you find this repository useful, please consider citing this paper:

@inproceedings{fca25,
    title={Full Conformal Adaptation of Medical Vision-Language Models},
    author={Julio Silva-Rodr\'iguez and Leo Fillioux and Paul-Henry Cournède and Maria Vakalopoulou and
    Stergios Christodoulidis and Ismail {Ben Ayed} and Jose Dolz},
    booktitle={Information Processing in Medical Imaging (IPMI)},
    year={2025}
}