Skip to main content

ORIGINAL RESEARCH article

Front. Neurol.
Sec. Applied Neuroimaging
Volume 15 - 2024 | doi: 10.3389/fneur.2024.1477811
This article is part of the Research Topic Advanced Neuroimaging Techniques for Assessing Cerebrovascular Diseases View all 3 articles

Target-based Deep Learning Network Surveillance of Non-contrast Computed Tomography for Small Infarct Core of Acute Ischemic Stroke

Provisionally accepted
Hang Qu Hang Qu 1Dong-yang Gao Dong-yang Gao 2Hui Tang Hui Tang 3Yong-xin Li Yong-xin Li 4Yi Zhao Yi Zhao 1Qi-qi Ban Qi-qi Ban 1Yu-Chen Chen Yu-Chen Chen 5lu Lu lu Lu 1WEI WANG WEI WANG 1*
  • 1 Affiliated Hospital of Yangzhou University, Yangzhou, China
  • 2 Nanjing University of Science and Technology, Nanjing, Jiangsu Province, China
  • 3 Georgia Southern University, Statesboro, Georgia, United States
  • 4 Chinese institute of brain research, Beijing, China
  • 5 First Affiliated Hospital, Nanjing Medical University, Nanjing, Jiangsu Province, China

The final, formatted version of the article will be published soon.

    Purpose: Rapid diagnosis of acute ischemic stroke (AIS) is critical to achieve positive outcomes and prognosis. This study aimed to construct a model to automatically identify the infarct core based on non-contrast-enhanced CT images, especially for small infarcts.The baseline CT scans of AIS patients, who had DWI scans obtained within less than two hours apart, were included in this retrospective study. A modified Target-based deep learning model of YOLOv5 was developed to detect infarctions on CT. Randomly selected CT images were used for testing and evaluated by neuroradiologists and the model, using the DWI as a reference standard.Intraclass correlation coefficient (ICC) and weighted kappa were calculated to assess the agreement. The paired chi-square test was used to compare the diagnostic efficacy of physician groups and automated models in subregions. P<0.05 was considered statistically significant.Results: 584 AIS patients were enrolled in total, finally 275 cases were eligible. Modified YOLOv5 perform better with increased precision (0.82), recall (0.81) and mean average precision (0.79) than original YOLOv5. Model showed higher consistency to the DWI-ASPECTS scores (ICC=0.669, κ =0.447) than neuroradiologists (ICC=0.452, κ=0.247). The sensitivity (75.86% VS. 63.79%), specificity (98.87% VS. 95.02%), and accuracy (96.20% VS.91.40%) were better than neuroradiologists. Automatic model had better diagnostic efficacy than physician diagnosis in the M6 region (P=0.039).The deep learning model was able to detect small infarct core on CT images more accurately. It provided the infarct portion and extent, which is valuable in assessing the severity of disease and guiding treatment procedures.

    Keywords: target-based deep learning network1, small infarct core2, acute ischemic stroke3, You Only Look Once (YOLO)4, non-contrast CT5. Article types: Original research

    Received: 08 Aug 2024; Accepted: 09 Sep 2024.

    Copyright: © 2024 Qu, Gao, Tang, Li, Zhao, Ban, Chen, Lu and WANG. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: WEI WANG, Affiliated Hospital of Yangzhou University, Yangzhou, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.