探索用于提升肺癌与结肠癌分类可解释性的可解释AI技术
Exploring Explainable AI Techniques for Improved Interpretability in Lung and Colon Cancer Classification
- Ahsanullah University of Science and Technology（阿赫萨努拉科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究针对肺癌和结肠癌的组织病理图像分类，调整8种预训练CNN模型并优化增强策略，实现97%-99%的准确率，同时结合多种注意力可视化方法提升模型决策的可解释性。
AI中文摘要：
肺癌和结肠癌是全球范围内严峻的健康挑战，需要早期精准识别以降低死亡风险。然而，诊断工作大多依赖病理组织学家的专业能力，当专业经验不足时，会出现诊断困难与风险。尽管影像学、血液标志物等诊断手段有助于早期检测，但组织病理学仍是诊断金标准，不过该方法耗时且易受观察者间差异的影响。高端技术获取渠道有限，进一步限制了患者获得即时医疗护理与诊断的能力。近年来深度学习的发展引发了人们将其应用于医学影像分析的兴趣，具体是利用组织病理学图像诊断肺癌和结肠癌。本研究旨在应用并调整现有基于CNN的预训练模型（如Xception、DenseNet201、ResNet101、InceptionV3、DenseNet121、DenseNet169、ResNet152、InceptionResNetV2），通过更优的数据增强策略提升分类效果。结果显示研究取得了显著进展，8个模型的准确率均达到97%至99%的优异水平。此外，研究还采用GradCAM、GradCAM++、ScoreCAM、Faster Score-CAM、LayerCAM等注意力可视化技术，以及Vanilla Saliency和SmoothGrad方法，来揭示模型的分类决策依据，从而提升良恶性图像分类的可解释性与可理解性。
英文摘要：
Lung and colon cancer are serious worldwide health challenges that require early and precise identification to reduce mortality risks. However, diagnosis, which is mostly dependent on histopathologists' competence, presents difficulties and hazards when expertise is insufficient. While diagnostic methods like imaging and blood markers contribute to early detection, histopathology remains the gold standard, although time-consuming and vulnerable to inter-observer mistakes. Limited access to high-end technology further limits patients' ability to receive immediate medical care and diagnosis. Recent advances in deep learning have generated interest in its application to medical imaging analysis, specifically the use of histopathological images to diagnose lung and colon cancer. The goal of this investigation is to use and adapt existing pre-trained CNN-based models, such as Xception, DenseNet201, ResNet101, InceptionV3, DenseNet121, DenseNet169, ResNet152, and InceptionResNetV2, to enhance classification through better augmentation strategies. The results show tremendous progress, with all eight models reaching impressive accuracy ranging from 97% to 99%. Furthermore, attention visualization techniques such as GradCAM, GradCAM++, ScoreCAM, Faster Score-CAM, and LayerCAM, as well as Vanilla Saliency and SmoothGrad, are used to provide insights into the models' classification decisions, thereby improving interpretability and understanding of malignant and benign image classification.
