面向医学图像计算的可泛化与可解释深度学习：综述
Generalizable and Explainable Deep Learning for Medical Image Computing: An Overview
AI总结：
本文综述了医学影像深度学习中可泛化与可解释人工智能的现状，通过在三个医学数据集上结合ResNet50与多种XAI技术进行实验，并基于结果提出未来研究方向。
摘要：
目的：本文综述了医学影像深度学习（DL）中的可泛化与可解释人工智能（XAI），旨在应对临床应用中对于透明性和可解释性的迫切需求。方法：我们提出在三个医学数据集（脑肿瘤、皮肤癌和胸部X光片）上使用四种CNN进行医学图像分类任务。此外，我们进行了配对t检验，以显示不同方法之间所观察到差异的显著性。进一步地，我们提出将ResNet50与五种常见的XAI技术相结合，以获得模型预测的可解释结果，旨在提高模型透明性。我们还引入了一个定量指标（置信度提升）来评估XAI技术的有用性。主要发现：实验结果表明，ResNet50在所有数据集上均能达到可行的准确率和F1分数（例如，在皮肤癌数据集上准确率为86.31%）。此外，研究结果表明，虽然某些XAI方法（如XgradCAM）能够有效突出医学图像中的相关异常区域，但其他方法（如EigenGradCAM）在特定场景下可能效果较差。另外，与GradCAM++（0.09）和LayerCAM（0.08）相比，XgradCAM显示出更高的置信度提升（例如，在胶质瘤中为0.12）。意义：基于实验结果和最新进展，我们概述了未来研究方向，以增强深度学习模型在生物医学影像领域的鲁棒性和可泛化性。
英文摘要：
Objective. This paper presents an overview of generalizable and explainable artificial intelligence (XAI) in deep learning (DL) for medical imaging, aimed at addressing the urgent need for transparency and explainability in clinical applications. Methodology. We propose to use four CNNs in three medical datasets (brain tumor, skin cancer, and chest x-ray) for medical image classification tasks. In addition, we perform paired t-tests to show the significance of the differences observed between different methods. Furthermore, we propose to combine ResNet50 with five common XAI techniques to obtain explainable results for model prediction, aiming at improving model transparency. We also involve a quantitative metric (confidence increase) to evaluate the usefulness of XAI techniques. Key findings. The experimental results indicate that ResNet50 can achieve feasible accuracy and F1 score in all datasets (e.g., 86.31\% accuracy in skin cancer). Furthermore, the findings show that while certain XAI methods, such as XgradCAM, effectively highlight relevant abnormal regions in medical images, others, like EigenGradCAM, may perform less effectively in specific scenarios. In addition, XgradCAM indicates higher confidence increase (e.g., 0.12 in glioma tumor) compared to GradCAM++ (0.09) and LayerCAM (0.08). Implications. Based on the experimental results and recent advancements, we outline future research directions to enhance the robustness and generalizability of DL models in the field of biomedical imaging.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
