利用脑部对称性差异提升阿尔茨海默病诊断准确率
Symmetry Interactive Transformer with CNN Framework for Diagnosis of Alzheimer's Disease Using Structural MRI
- 设计对称交互变压器，融合3D CNN与跨半球特征对齐机制
- 在ADNI数据集上达到92.5%诊断准确率，优于主流CNN与Transformer组合
- 可视化显示模型聚焦于不对称萎缩区域，解释性强，适合医学影像分析
结构磁共振成像（sMRI）结合深度学习在阿尔茨海默病（AD）预测与诊断中取得显著进展。现有研究多采用CNN或Transformer构建高性能网络，但多数依赖预训练或忽略脑部疾病引起的不对称性。本文提出一种端到端网络，用于检测由左右脑萎缩引发的疾病相关不对称性，由3D CNN编码器与对称交互变压器（SIT）组成。通过等距网格块获取操作，将左右半球特征对齐后输入SIT进行诊断分析，使模型更关注由结构变化引起的不对称区域，从而提升诊断性能。基于ADNI数据集的评估结果显示，该方法诊断准确率达92.5%，优于多种CNN方法及CNN与通用Transformer的组合。可视化结果表明，网络更关注脑萎缩区域，尤其是由AD引发的不对称病理特征，验证了方法的可解释性与有效性。
原文摘要 · Abstract (English)
Structural magnetic resonance imaging (sMRI) combined with deep learning has achieved remarkable progress in the prediction and diagnosis of Alzheimer's disease (AD). Existing studies have used CNN and transformer to build a well-performing network, but most of them are based on pretraining or ignoring the asymmetrical character caused by brain disorders. We propose an end-to-end network for the detection of disease-based asymmetric induced by left and right brain atrophy which consist of 3D CNN Encoder and Symmetry Interactive Transformer (SIT). Following the inter-equal grid block fetch operation, the corresponding left and right hemisphere features are aligned and subsequently fed into the SIT for diagnostic analysis. SIT can help the model focus more on the regions of asymmetry caused by structural changes, thus improving diagnostic performance. We evaluated our method based on the ADNI dataset, and the results show that the method achieves better diagnostic accuracy (92.5\%) compared to several CNN methods and CNNs combined with a general transformer. The visualization results show that our network pays more attention in regions of brain atrophy, especially for the asymmetric pathological characteristics induced by AD, demonstrating the interpretability and effectiveness of the method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。