Explainable Medical Image Segmentation via Generative Adversarial Networks and Layer-wise Relevance Propagation
It addresses the need for explainable AI in medical imaging to assist clinicians by providing pixel-level explanations for segmentation predictions, though it is incremental as it combines existing methods.
This paper tackled the problem of automating medical image segmentation for endoscopy images by proposing generative adversarial network-based models to segment polyps and instruments, achieving 0.84 accuracy and 0.46 Jaccard index for polyps, and 0.96 accuracy and 0.70 Jaccard index for instruments.
This paper contributes to automating medical image segmentation by proposing generative adversarial network-based models to segment both polyps and instruments in endoscopy images. A major contribution of this work is to provide explanations for the predictions using a layer-wise relevance propagation approach designating which input image pixels are relevant to the predictions and to what extent. On the polyp segmentation task, the models achieved 0.84 of accuracy and 0.46 on Jaccard index. On the instrument segmentation task, the models achieved 0.96 of accuracy and 0.70 on Jaccard index. The code is available at https://github.com/Awadelrahman/MedAI.