TY - JOUR

T1 - Ensembling Transformer-Based Models for 3D Ischemic Stroke Segmentation in Non-Contrast CT

AU - Cherikbayeva, Lyailya

AU - Berikov, Vladimir

AU - Melis, Zarina

AU - Yeleussinov, Arman

AU - Baigozhanova, Dametken

AU - Tasbolatuly, Nurbolat

AU - Temirbekova, Zhanerke

AU - Mikhailapov, Denis

N1 - This research has been funded by the Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan (AP26195405).

PY - 2025/9/4

Y1 - 2025/9/4

N2 - Ischemic stroke remains one of the leading causes of mortality and disability, and accurate segmentation of the affected areas on CT brain images plays a crucial role in timely diagnosis and clinical decision-making. This study proposes an ensemble approach based on the combination of the transformer-based models SE-UNETR and Swin UNETR using a weighted voting strategy. Its performance was evaluated using the Dice similarity coefficient, which quantifies the overlap between the predicted lesion regions and the ground-truth annotations. In this study, three-dimensional CT scans of the brain from 98 patients with a confirmed diagnosis of acute ischemic stroke were used. The data were provided by the International Tomography Center, SB RAS. The experimental results demonstrated that the ensemble based on transformer models significantly outperforms each individual model, providing more stable and accurate predictions. The final Dice coefficient reached 0.7983, indicating the high effectiveness of the proposed approach for ischemic lesion segmentation in CT images. The analysis showed more precise delineation of ischemic lesion boundaries and a reduction in segmentation errors. The proposed method can serve as an effective tool in automated stroke diagnosis systems and other applications requiring high-accuracy medical image analysis.

AB - Ischemic stroke remains one of the leading causes of mortality and disability, and accurate segmentation of the affected areas on CT brain images plays a crucial role in timely diagnosis and clinical decision-making. This study proposes an ensemble approach based on the combination of the transformer-based models SE-UNETR and Swin UNETR using a weighted voting strategy. Its performance was evaluated using the Dice similarity coefficient, which quantifies the overlap between the predicted lesion regions and the ground-truth annotations. In this study, three-dimensional CT scans of the brain from 98 patients with a confirmed diagnosis of acute ischemic stroke were used. The data were provided by the International Tomography Center, SB RAS. The experimental results demonstrated that the ensemble based on transformer models significantly outperforms each individual model, providing more stable and accurate predictions. The final Dice coefficient reached 0.7983, indicating the high effectiveness of the proposed approach for ischemic lesion segmentation in CT images. The analysis showed more precise delineation of ischemic lesion boundaries and a reduction in segmentation errors. The proposed method can serve as an effective tool in automated stroke diagnosis systems and other applications requiring high-accuracy medical image analysis.

KW - CT

KW - Swin Transformer

KW - UNETR

KW - deep learning

KW - ensemble of models

KW - ischemic stroke

KW - segmentation

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105015582830&origin=inward

UR - https://www.mendeley.com/catalogue/252bad8b-5249-395f-9880-286e85a7438b/

U2 - 10.3390/app15179725

DO - 10.3390/app15179725

M3 - Article

VL - 15

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

SN - 2076-3417

IS - 17

M1 - 9725

ER -