用3D CNN和数据增强提升阿尔茨海默病脑部MRI分类准确率
3D Brain MRI Classification for Alzheimer Diagnosis Using CNN with Data Augmentation
- 构建3D卷积神经网络，结合噪声注入等数据增强方法
- 测试准确率达91.2%，ROC曲线下面积达96.1%，敏感性和特异性均超90%
- 验证简单增强策略有效，适合医学影像智能诊断研究者参考
本文提出一种三维卷积神经网络，用于将T1加权脑部MRI扫描分类为健康或阿尔茨海默病。模型包含3D卷积、池化、批归一化、全连接ReLU层及sigmoid输出层。通过随机噪声注入和五折交叉验证，模型在测试集上达到91.2%的准确率和96.1%的ROC曲线下面积，较仅使用图像重缩放提升了约0.027。敏感性与特异性均超过90%。结果与前期研究一致，表明合成数据增强可带来最高0.10的性能提升。研究证实了简单增强方法在3D MRI分类中的有效性，鼓励未来探索更先进的增强技术与架构，如3D U-Net和视觉变换器。
原文摘要 · Abstract (English)
A three-dimensional convolutional neural network was developed to classify T1-weighted brain MRI scans as healthy or Alzheimer. The network comprises 3D convolution, pooling, batch normalization, dense ReLU layers, and a sigmoid output. Using stochastic noise injection and five-fold cross-validation, the model achieved test set accuracy of 0.912 and area under the ROC curve of 0.961, an improvement of approximately 0.027 over resizing alone. Sensitivity and specificity both exceeded 0.90. These results align with prior work reporting up to 0.10 gain via synthetic augmentation. The findings demonstrate the effectiveness of simple augmentation for 3D MRI classification and motivate future exploration of advanced augmentation methods and architectures such as 3D U-Net and vision transformers.
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。