arXiv cs.AI· Sanjana Islam Kasfia, Md. Ismiel Hossen Abir, AKM Bahalul Haque, Abir Mahmud Shahariar·· 3 小时前AI 评分31
轻量级注意力 CNN 结合显著性图可解释性用于皮肤癌检测
A Lightweight Attention-Based CNN with Saliency-Map Interpretability for Skin Cancer Detection
AI 导读
一项研究提出用于皮肤病变二分类的可解释 AI 框架：轻量级注意力 CNN（CNN-Attention），在 2,637 张训练与 660 张测试图像上达到 87% 准确率，参数量仅 195 万、存储 7.45 MB，约为 MobileNet 的一半，ROC AUC 与 PR AUC 分别为 0.9475 和 0.9430。
正文 · 原文
Abstract:Skin cancer is among the most prevalent and life threatening forms of cancer worldwide. Early and accurate diagnosis significantly improves patient survival rates. However, manual dermoscopic assessment remains challenging due to visual similarity. This study proposes an Explainable AI-driven framework for automated binary classification of skin lesions using a lightweight attention-based convolutional neural network (CNN-Attention). The model integrates channel attention to focus on informative regions of dermoscopic images while maintaining low computational complexity. A publicly available dataset comprising 2,637 training and 660 test images was used, with balanced class weights. The proposed model achieved 87 percent accuracy with 1.95 million parameters and 7.45 MB of storage, matching the best baseline (MobileNet) while using approximately half as many parameters and half as much storage. ROC AUC and PR AUC scores reached 0.9475 and 0.9430, respectively. Additionally, saliency maps were incorporated as an explainability technique to visualize regions that influence model decisions. Comparative analysis with VGG16,VGG19,ResNet101,and MobileNet demonstrates the proposed models effectiveness in balancing classification results, computational efficiency, and interpretability.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.37314 [cs.CV] |
| (or arXiv:2610.37314v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37314 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: AKM Bahalul Haque [view email]
[v1]
Tue, 27 Oct 2026 14:30:29 UTC (1,433 KB)
来源：arXiv cs.AI · arxiv.org