Explainable Deep Learning for Medical Image Segmentation With Learnable Class Activation Mapping
Open Access
- 17 March 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 210-215
Abstract
Medical image segmentation is crucial for facilitating pathology assessment, ensuring reliable diagnosis and monitoring disease progression. Deep-learning models have been extensively applied in automating medical image analysis to reduce human effort. However, the non-transparency of deep-learning models limits their clinical practicality due to the unaffordably high risk of misdiagnosis resulted from the misleading model output. In this paper, we propose a explainability metric as part of the loss function. The proposed explainability metric comes from Class Activation Map(CAM) with learnable weights such that the model can be optimized to achieve desirable balance between segmentation performance and explainability. Experiments found that the proposed model visibly heightened Dice score from to , Jaccard similarity from to and Recall from to respectively compared with U-net. In addition, results make clear that the drawn model outdistances the conventional U-net in terms of explainability performance.Keywords
This publication has 16 references indexed in Scilit:
- Deep Attentional Features for Prostate Segmentation in Ultrasound2018
- Mask R-CNN2017
- Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Differential Privacy for Edge Weights in Social NetworksSecurity and Communication Networks, 2017
- Learning Deep Features for Discriminative Localization2016
- Attention to Scale: Scale-Aware Semantic Image Segmentation2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Fully convolutional networks for semantic segmentation2015
- Visualizing and Understanding Convolutional Networks2014