基于结构磁共振影像的孤独症分类中的数据增强研究

基于结构磁共振影像的孤独症分类对孤独症疾病的早期筛查和精准诊断具有重要意义,但受数据噪声及样本不足的影响,基于结构磁共振影像的孤独症分类模型的准确率并不理想。该文提出一种新的数据增强模型,并采用孤独症脑成像交换数据库 I 中的密西根大学样本库 1 数据集进行模型测试,随机选取密西根大学样本库 1 数据集中的 78 个样本进行实验,以对孤独症分类准确率进行评估。实验结果显示：该方法在 500 次实验的 494 次(98% 以上的实验)中能够将分类准确率提升10%～20%,在不增加数据量的情况下显著提升了孤独症的分类准确率。通过分析准确率提升和标注变化比例之间的关系,该文进一步对数据标注噪声的问题进行了探讨。

Data Augmentation Study in Structural Magnetic Resonance Imaging Based Autism Spectrum Disorder Classification

Structural magnetic resonance imaging based autism spectrum disorder classification is important nowadays for early-stage screening and accurate diagnosis of autism spectrum disorder. However, due to the limitation of large data noise and small data volume, the predictive accuracy of structural magnetic resonance imaging based autism classification is not ideal. In this study, a new data augmentation model is proposed to improve classification accuracy without increasing training data volume. The University of Michigan sample 1 dataset of autism brain imaging data exchange I for autism study was used for training and evaluating the proposed model. 78 samples of the University of Michigan sample 1 dataset was selected randomly for performing the experiment, and the performance improved using proposed data augmentation algorithm for autism spectrum disorder classification task was calculated. Such a procedure was repeated for 500 times to collect results that are statistically significant. Based on the results, this method can stably improve classification accuracy between 10% and 20% in 494 out of 500 experiments (over 98% of the experiments). Through a comparative study of accuracy improvement and label change ratio, the problem of data label noise was explored.