/TS-CNN-A-Three-Tier-Self-Interpretable-CNN-for-Medical-Image-Classification-Empowered-with-Post-hoc

Primary LanguageJupyter Notebook

TS-CNN-AThree Tier Self Interpretable CNN for Medical Image Classification Empowered with Post hoc

Code used during research for the paper: TS-CNN: A Three-Tier Self-Interpretable CNN for Multi-Region Medical Image Classification

Published in IEEE Access journal.

Status: Published (Link to paper)

The repository resources for the two experiments, each of which contains:

  1. Jupyter notebooks with code for the proposed methodology with both GradCAM and Saliency maps.
  2. Weights of the best-performing model for each method
  3. Train test split of the PAD-UFES-20 dataset used for experiments.