基于结构磁共振影像的自闭症分类中的数据增强研究
作者:
作者单位:

中国科学院深圳先进技术研究院

作者简介:

通讯作者:

基金项目:

国家重点研发计划(No.2021yff1200100),国家自然科学基金(No. 2021yff1200100),深圳市科技计划(No . KQTD20200820113106007),广东省重点研发项目(No.2021B0101310002)

伦理声明:



Data Augmentation Study in Structural MRI Based Autism Spectrum Disorder Classification
Author:
Ethical statement:

Affiliation:

Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences

Funding:

This project is supported by the National Key Research and Development Program of China grant No.2021YFF1200100, National Natural Science Foundation of China under grant No. U22A2041, the Shenzhen Science and Technology Program Nos. KQTD20200820113106007, the Key Research and Development Project of Guangdong Province under grant No.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自闭症分类对于疾病早期筛查和精准诊断具有重要意义,但受到数据噪声及样本不足的影响,基于结构磁共振影像的机器学习分类模型准确率并不理想。本文提出了一种新型的数据增强模型,我们采用ABIDE-I中的UM1数据集进行模型测试,随机选取了UM1数据集中78个样本进行实验,对自闭症分类准确率进行评估。实验结果显示本方法在500次实验的494次中(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自闭症的分类准确率,通过分析准确率提升和标注变化比例之间的关系,文中进一步对数据标注噪音的问题进行了探讨。

    Abstract:

    Structural-MRI 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-MRI 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 UM1 dataset of ABIDE I for autism study was used for training and evaluating the proposed model. 78 samples of the UM1 dataset was selected randomly for performing the experiment, and the performance improved using proposed data augmentation algorithm for ASD 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

马瑞民,谢瑞涛,黄莹,等.基于结构磁共振影像的自闭症分类中的数据增强研究 [J].集成技术,

Citing format
Ma Ruimin, Xie Ruitao, Huang Ying, et al. Data Augmentation Study in Structural MRI Based Autism Spectrum Disorder Classification[J]. Journal of Integration Technology.

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:2023-04-13
  • 最后修改日期:2023-04-23
  • 录用日期:
  • 在线发布日期: 2023-08-10
  • 出版日期: