CVApr 3, 2023

Fine-tuning of explainable CNNs for skin lesion classification based on dermatologists' feedback towards increasing trust

arXiv:2304.01399v12 citationsh-index: 26
Originality Incremental advance
AI Analysis

This work addresses trust issues for users of medical AI systems, specifically in dermatology, and is incremental as it builds on existing CNN and Grad-CAM techniques.

The paper tackles the problem of increasing user trust in CNN-based skin lesion classifiers by proposing a fine-tuning method that incorporates simultaneous user feedback on both classification and visual explanations, resulting in improved visual explanations while preserving classification accuracy.

In this paper, we propose a CNN fine-tuning method which enables users to give simultaneous feedback on two outputs: the classification itself and the visual explanation for the classification. We present the effect of this feedback strategy in a skin lesion classification task and measure how CNNs react to the two types of user feedback. To implement this approach, we propose a novel CNN architecture that integrates the Grad-CAM technique for explaining the model's decision in the training loop. Using simulated user feedback, we found that fine-tuning our model on both classification and explanation improves visual explanation while preserving classification accuracy, thus potentially increasing the trust of users in using CNN-based skin lesion classifiers.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes