Deep-learning-based detection of large vessel occlusion: A comparison of CT and diffusion-weighted imaging

Background Rapid and accurate identification of large vessel occlusion (LVO) is crucial for determining eligibility for endovascular treatment. We aimed to validate whether computed tomography combined with clinical information (CT&CI) or diffusion-weighted imaging (DWI) offers better predictive...

Full description

Saved in:
Bibliographic Details
Main Authors: JaeYoung Kang, JunYoung Park, YoungJae Kim, BumJoon Kim, SangHee Ha, KwangGi Kim
Format: Article
Language:English
Published: SAGE Publishing 2025-04-01
Series:Digital Health
Online Access:https://doi.org/10.1177/20552076251334040
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850173459507707904
author JaeYoung Kang
JunYoung Park
YoungJae Kim
BumJoon Kim
SangHee Ha
KwangGi Kim
author_facet JaeYoung Kang
JunYoung Park
YoungJae Kim
BumJoon Kim
SangHee Ha
KwangGi Kim
author_sort JaeYoung Kang
collection DOAJ
description Background Rapid and accurate identification of large vessel occlusion (LVO) is crucial for determining eligibility for endovascular treatment. We aimed to validate whether computed tomography combined with clinical information (CT&CI) or diffusion-weighted imaging (DWI) offers better predictive accuracy for anterior circulation LVO. Methods Computed tomography combined with clinical information and DWI data from patients diagnosed with acute ischemic stroke were collected. Three deep-learning models, convolutional neural network, EfficientNet-B2, and DenseNet121, were used to compare CT&CI and DWI for detecting anterior circulation LVO. Results A total of 456 patients, 228 patients with LVO [68.91 ± 12.84 years, 63.60% male; initial National Institutes of Health Stroke Scale (NIHSS) score: median 11 (7–14)] and without LVO [67.06 ± 12.29 years, 64.04% male; initial NIHSS score: median 2 (1–4)] were enrolled. Diffusion-weighted imaging achieved better results than CT&CI did in each performance metric. In DenseNet121, the area under the curves (AUCs) were found to be 0.833 and 0.756, respectively, while in EfficientNet-B2, the AUCs were 0.815 and 0.647, respectively. Conclusions In detecting the presence of anterior circulation LVO, DWI showed better results in each performance metric than CT&CI did, and the best-performing deep-learning model was DenseNet121.
format Article
id doaj-art-0ea87129bd224933b3aa1f04c664bbd0
institution OA Journals
issn 2055-2076
language English
publishDate 2025-04-01
publisher SAGE Publishing
record_format Article
series Digital Health
spelling doaj-art-0ea87129bd224933b3aa1f04c664bbd02025-08-20T02:19:51ZengSAGE PublishingDigital Health2055-20762025-04-011110.1177/20552076251334040Deep-learning-based detection of large vessel occlusion: A comparison of CT and diffusion-weighted imagingJaeYoung Kang0JunYoung Park1YoungJae Kim2BumJoon Kim3SangHee Ha4KwangGi Kim5 , Daegu, Republic of Korea Department of Health Science and Technology, Gachon Advanced Institute for Health Science and Technology, , Incheon, Republic of Korea Gachon Biomedical and Convergence Institute, , Incheon, Republic of Korea , University of Ulsan, Seoul, Republic of Korea Department of Neurology, Gil Medical Center, , Incheon, Republic of Korea Department of Biomedical Engineering, College of Medicine, , Incheon, Republic of Korea Background Rapid and accurate identification of large vessel occlusion (LVO) is crucial for determining eligibility for endovascular treatment. We aimed to validate whether computed tomography combined with clinical information (CT&CI) or diffusion-weighted imaging (DWI) offers better predictive accuracy for anterior circulation LVO. Methods Computed tomography combined with clinical information and DWI data from patients diagnosed with acute ischemic stroke were collected. Three deep-learning models, convolutional neural network, EfficientNet-B2, and DenseNet121, were used to compare CT&CI and DWI for detecting anterior circulation LVO. Results A total of 456 patients, 228 patients with LVO [68.91 ± 12.84 years, 63.60% male; initial National Institutes of Health Stroke Scale (NIHSS) score: median 11 (7–14)] and without LVO [67.06 ± 12.29 years, 64.04% male; initial NIHSS score: median 2 (1–4)] were enrolled. Diffusion-weighted imaging achieved better results than CT&CI did in each performance metric. In DenseNet121, the area under the curves (AUCs) were found to be 0.833 and 0.756, respectively, while in EfficientNet-B2, the AUCs were 0.815 and 0.647, respectively. Conclusions In detecting the presence of anterior circulation LVO, DWI showed better results in each performance metric than CT&CI did, and the best-performing deep-learning model was DenseNet121.https://doi.org/10.1177/20552076251334040
spellingShingle JaeYoung Kang
JunYoung Park
YoungJae Kim
BumJoon Kim
SangHee Ha
KwangGi Kim
Deep-learning-based detection of large vessel occlusion: A comparison of CT and diffusion-weighted imaging
Digital Health
title Deep-learning-based detection of large vessel occlusion: A comparison of CT and diffusion-weighted imaging
title_full Deep-learning-based detection of large vessel occlusion: A comparison of CT and diffusion-weighted imaging
title_fullStr Deep-learning-based detection of large vessel occlusion: A comparison of CT and diffusion-weighted imaging
title_full_unstemmed Deep-learning-based detection of large vessel occlusion: A comparison of CT and diffusion-weighted imaging
title_short Deep-learning-based detection of large vessel occlusion: A comparison of CT and diffusion-weighted imaging
title_sort deep learning based detection of large vessel occlusion a comparison of ct and diffusion weighted imaging
url https://doi.org/10.1177/20552076251334040
work_keys_str_mv AT jaeyoungkang deeplearningbaseddetectionoflargevesselocclusionacomparisonofctanddiffusionweightedimaging
AT junyoungpark deeplearningbaseddetectionoflargevesselocclusionacomparisonofctanddiffusionweightedimaging
AT youngjaekim deeplearningbaseddetectionoflargevesselocclusionacomparisonofctanddiffusionweightedimaging
AT bumjoonkim deeplearningbaseddetectionoflargevesselocclusionacomparisonofctanddiffusionweightedimaging
AT sangheeha deeplearningbaseddetectionoflargevesselocclusionacomparisonofctanddiffusionweightedimaging
AT kwanggikim deeplearningbaseddetectionoflargevesselocclusionacomparisonofctanddiffusionweightedimaging