Skip to content
/ CIPL Public

[TMI 2025] Cross- and Intra-image Prototypical Learning for Multi-label Disease Diagnosis and Interpretation

Notifications You must be signed in to change notification settings

cwangrun/CIPL

Repository files navigation

Cross- and Intra-image Prototypical Learning (CIPL)

In this work, we present the Cross- and Intra-image Prototypical Learning (CIPL) framework for accurate multi-label disease diagnosis and interpretation. CIPL takes advantage of cross-image common semantics to disentangle multiple diseases during the prototype learning, ensuring high-quality prototypes in the multi-label interpretation setting. Additionally, a two-level alignment-based regularization strategy enhances interpretation robustness and predictive performance by enforcing consistent intra-image information. Email: [email protected].

Datasets:

Chest X-ray (NIH ChestX-ray14) and fundus (ODIR) images are publicly available.

Training and Testing:

  1. Run python main.py to train the model and evaluate its disease diagnosis accuracy. Our trained models are provided at ChestX-ray14 and ODIR:
  2. Each prototype is visualized as the nearest non-repetitive training patch representing its corresponding disease class using push.py.

Interpretable reasoning:

CIPL leverages disentangled class prototypes, learned from the training set, as anchors for diagnostic reasoning. To understand the decision process for a given test image, run interpretable_reasoning.py. This will generate a set of similarity (activation) maps that highlight the correspondence between the test image and the prototypes of each disease class, providing insights into the model's reasoning.

Results:

CIPL exhibits high-quality visual prototypes that are both disentangled and accurate (aligning well with actual lesion signs), outperforming previous studies. For further details, please refer to our paper.

Citation:

@article{wang2025cross,
  title={Cross-and Intra-image Prototypical Learning for Multi-label Disease Diagnosis and Interpretation},
  author={Wang, Chong and Liu, Fengbei and Chen, Yuanhong and Frazer, Helen and Carneiro, Gustavo},
  journal={IEEE Transactions on Medical Imaging},
  year={2025},
  publisher={IEEE}
}

Releases

No releases published

Packages

No packages published

Languages