可解释AI：一种结合XAI框架用于解释脑肿瘤检测模型
Explainable AI: A Combined XAI Framework for Explaining Brain Tumour Detection Models
AI总结：
本文提出一种结合GRAD-CAM、LRP和SHAP的XAI框架，用于提升脑肿瘤检测模型的可解释性与可靠性。
摘要：
本研究探讨了整合多种可解释AI（XAI）技术以提高深度学习模型在脑肿瘤检测中的可解释性。开发并训练了一个定制的卷积神经网络（CNN），在BraTS 2021数据集上达到91.24%的准确率，用于区分肿瘤和非肿瘤区域。本研究结合梯度加权类激活映射（GRAD-CAM）、层间相关传播（LRP）和SHAP（SHapley Additive exPlanations）技术，以提供对模型决策过程的全面见解。这种多技术方法成功识别了全肿瘤和部分肿瘤，提供了从广区域兴趣到像素级细节的分层解释。GRAD-CAM突出了重要的空间区域，LRP提供了详细的像素级相关性，SHAP量化了特征贡献。整合的方法有效解释了模型预测，包括部分肿瘤可见性的情况，从而显示出比单独XAI方法更优越的解释能力。本研究通过提供对模型推理的更全面视角，增强了AI驱动的医学影像分析的透明度和可信度。本研究展示了整合XAI技术在提高AI系统在医疗领域可靠性与可解释性方面的潜力，特别是在关键任务如脑肿瘤检测方面。
英文摘要：
This study explores the integration of multiple Explainable AI (XAI) techniques to enhance the interpretability of deep learning models for brain tumour detection. A custom Convolutional Neural Network (CNN) was developed and trained on the BraTS 2021 dataset, achieving 91.24% accuracy in distinguishing between tumour and non-tumour regions. This research combines Gradient-weighted Class Activation Mapping (GRAD-CAM), Layer-wise Relevance Propagation (LRP) and SHapley Additive exPlanations (SHAP) to provide comprehensive insights into the model's decision-making process. This multi-technique approach successfully identified both full and partial tumours, offering layered explanations ranging from broad regions of interest to pixel-level details. GRAD-CAM highlighted important spatial regions, LRP provided detailed pixel-level relevance and SHAP quantified feature contributions. The integrated approach effectively explained model predictions, including cases with partial tumour visibility thus showing superior explanatory power compared to individual XAI methods. This research enhances transparency and trust in AI-driven medical imaging analysis by offering a more comprehensive perspective on the model's reasoning. The study demonstrates the potential of integrated XAI techniques in improving the reliability and interpretability of AI systems in healthcare, particularly for critical tasks like brain tumour detection.
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。
