A machine learning model reveals invisible microscopic variation in acute ischaemic stroke (≤ 6 h) with non-contrast computed tomography.

Journal: BMC medical imaging
Published Date: Jul 9, 2025

Abstract

BACKGROUND: In most medical centers, particularly in primary hospitals, non-contrast computed tomography (NCCT) serves as the primary imaging modality for diagnosing acute ischemic stroke. However, due to the small density difference between the infarct and the surrounding normal brain tissue on NCCT images within the initial 6 h post-onset, it poses significant challenges in promptly and accurately positioning and quantifying the infarct at the early stage.

Authors

  • Jiahe Tan
    Computer Science, Graduate Studies, University of California, 1 Shields Ave, Davis, CA, 95616, USA.
  • Mengjun Xiao
    Department of Radiology, Shandong Provincial Hospital, Shandong First Medical University, Jingwu Road No. 324, Jinan, Shandong, 250021, China.
  • Zhipeng Wang
    Department of Pharmacy, Changzheng Hospital, Second Military Medical University, Shanghai, 200003, PR China.
  • Shuzhen Wu
    Shandong First Medical University, Jinan, China (J.L., M.L., S.W.); Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China (S.W.).
  • Kun Han
    DeepVoxel Inc., Irvine, USA.
  • Haiyan Wang
    College of Chemistry and Material Science, Shandong Agricultural University, Tai'an 271018, PR China.
  • Yong Huang
    State Key Laboratory for the Chemistry and Molecular Engineering of Medicinal Resources, Key Laboratory of Ecology of Rare and Endangered Species and Environmental Protection of Ministry Education, Guangxi Normal University, Guilin 541004, China.

Keywords

External Resources

Popular Topics
Recent Journals