基于结构磁共振影像的孤独症分类中的数据增强研究
作者:
作者单位:

作者简介:

通讯作者:

基金项目:

国家重点研发计划项目( 2 0 2 1 Y F F 1 2 0 0 1 0 0 ) ; 国家自然科学基金项目(U22A2041) ; 深圳市科技计划资助项目(KQTD20200820113106007);深圳市智能生物信息学重点实验室(ZDSYS20220422103800001);广东省重点研发项目(2021B0101310002)

伦理声明:



Data Augmentation Study in Structural Magnetic Resonance Imaging Based Autism Spectrum Disorder Classification
Author:
Ethical statement:

Affiliation:

Funding:

This work is supported by National Key Research and Development Program of China grant (2021YFF1200100), National Natural Science Foundation of China (U22A2041), Shenzhen Science and Technology Program (KQTD20200820113106007), Shenzhen Key Laboratory of Intelligent Bioinformatics (ZDSYS20220422103800001), Key Research and Development Project of Guangdong Province (2021B0101310002)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    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。

    Abstract:

    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.

    参考文献
    相似文献
    引证文献
引用本文

引文格式
马瑞民,谢锐涛,黄 莹,等.基于结构磁共振影像的孤独症分类中的数据增强研究 [J].集成技术,2023,12(6):33-42

Citing format
MA Ruimin, XIE Ruitao, HUANG Ying, et al. Data Augmentation Study in Structural Magnetic Resonance Imaging Based Autism Spectrum Disorder Classification[J]. Journal of Integration Technology,2023,12(6):33-42

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2023-11-17
  • 出版日期: