Deep adaptive learning predicts and diagnoses CSVD-related cognitive decline using radiomics from T-FLAIR: a multi-centre study.

Journal: NPJ digital medicine
Published Date: Jul 15, 2025

Abstract

Early identification of cerebral small vessel disease related cognitive impairment (CSVD-CI) is crucial for timely clinical intervention. We developed a Transformer-based deep learning model using white matter hyperintensity (WMH) radiomics features from T-fluid-attenuated inversion recovery images to detect CSVD-CI. A total of 783 subjects (161 longitudinally followed) were enrolled from three centres for model development and external validation, using a domain adaptation strategy. The model achieved AUCs of 0.841 (training) and 0.859/0.749 (validation cohorts), outperforming conventional machine learning models. The gradient-weighted class activation mapping approach highlighted WMH textural features, particularly the logarithm-transformed gray level size zone matrix features, as key contributors. These features were significantly correlated with CSVD macro- and microstructural changes, mediated age-cognition relationships and predicted longitudinal cognitive decline. Our findings indicate that WMH radiomics features, reflecting CI-related biological changes in CSVD, combined with a Transformer-based deep learning model, constitute a feasible, automated, and non-invasive tool for CSVD-CI detection.

Authors

  • Lili Huang
    Department of Endocrinology, Affiliated Hospital of Guilin Medical University, Guilin, Guangxi, China.
  • Zhuoyuan Li
    State Key Lab of Manufacturing Systems Engineering, Shaanxi Key Lab of Intelligent Robots, School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, P. R. China. liboxjtu@xjtu.edu.cn hlchen@xjtu.edu.cn.
  • Xiaolei Zhu
    School of Information and Artificial Intelligence, Anhui Agricultural University, Hefei, Anhui, China.
  • Hui Zhao
    School of Mathematics and Computer Science, Shaanxi University of Technology, Hanzhong, 723000, Shaanxi, China.
  • Chenglu Mao
    Department of Neurology, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
  • Zhihong Ke
    Department of Neurology, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
  • Yuting Mo
    School of Information, Renmin University of China, Beijing 100872, China.
  • Dan Yang
    Baotou Medical College Baotou Inner Mongolia 014060 China 610283014@qq.com dongjiani369@126.com wgdzd@126.com +86 13847201181 +86 13514899325 +86 13474977691.
  • Yue Cheng
  • Ruomeng Qin
    Department of Neurology, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
  • Zheqi Hu
    Department of Neurology, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
  • Pengfei Shao
    Department of Urology, the First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
  • Ying Chen
    Department of Endocrinology and Metabolism, Fudan Institute of Metabolic Diseases, Zhongshan Hospital, Fudan University, Shanghai, China.
  • Min Lou
  • Kelei He
  • Yun Xu
    Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, China.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals