TY - JOUR

T1 - TRANSFORMER BASED ENSEMBLE FOR ISCHEMIC STROKE SEGMENTATION ON 3D CT SCANS

AU - Cherikbayeva, L. Ch

AU - Berikov, V. B.

AU - Melis, Z. M.

AU - Yeleussinov, A. I.

AU - Adilzhanova, S. A.

AU - Ataniyazova, A. S.

AU - Daiyrbayeva, E. N.

N1 - Cherikbayeva L.Ch., Berikov V.B., Melis Z.M., Yeleussinov A.I., Adilzhanova S.A., Ataniyazova A.S., Daiyrbayeva E.N. TRANSFORMER BASED ENSEMBLE FOR ISCHEMIC STROKE SEGMENTATION ON 3D CT SCANS. Herald of the Kazakh-British Technical University. 2026;23(1):37-51. (In Kazakh) https://doi.org/10.55452/1998-6688-2026-23-1-37-51

PY - 2026

Y1 - 2026

N2 - Ischemic stroke is one of the leading causes of mortality and disability. Accurate segmentation of damaged regions in brain CT images is critical for timely diagnosis and clinical decision-making. In this study, an ensemble approach is proposed, combining SE-UNETR and Swin UNETR transformer models via weighted voting. The Dice coefficient was used for evaluation, measuring the overlap between predicted lesion regions and reference annotations. Unlike single-model approaches, ensemble neural network methods provide higher reliability and segmentation accuracy by integrating predictions from multiple architectures. Three-dimensional CT scans of 98 patients with acute ischemic stroke, provided by the International Tomography Center of the Siberian Branch of the Russian Academy of Sciences, were used. The results demonstrated that the proposed ensemble outperforms individual models. The average Dice coefficient was 0.7983, indicating the high effectiveness of the method in segmenting ischemic lesions. Analysis showed that the ensemble approach more accurately delineates lesion boundaries in brain CT images and reduces segmentation errors. The proposed method can be applied not only to stroke but also to other pathologies requiring precise medical image analysis in automated diagnostic systems.

AB - Ischemic stroke is one of the leading causes of mortality and disability. Accurate segmentation of damaged regions in brain CT images is critical for timely diagnosis and clinical decision-making. In this study, an ensemble approach is proposed, combining SE-UNETR and Swin UNETR transformer models via weighted voting. The Dice coefficient was used for evaluation, measuring the overlap between predicted lesion regions and reference annotations. Unlike single-model approaches, ensemble neural network methods provide higher reliability and segmentation accuracy by integrating predictions from multiple architectures. Three-dimensional CT scans of 98 patients with acute ischemic stroke, provided by the International Tomography Center of the Siberian Branch of the Russian Academy of Sciences, were used. The results demonstrated that the proposed ensemble outperforms individual models. The average Dice coefficient was 0.7983, indicating the high effectiveness of the method in segmenting ischemic lesions. Analysis showed that the ensemble approach more accurately delineates lesion boundaries in brain CT images and reduces segmentation errors. The proposed method can be applied not only to stroke but also to other pathologies requiring precise medical image analysis in automated diagnostic systems.

KW - Swin Transformer

KW - UNETR

KW - computed tomography (CT)

KW - deep learning

KW - ischemic stroke

KW - model ensemble

KW - segmentation

KW - UNETR

KW - Swin Transformer

KW - компьютерная томография

KW - ишемический инсульт

KW - глубокое обучение

KW - сегментация

KW - ансамбль моделей

UR - https://www.scopus.com/pages/publications/105034674653

UR - https://www.mendeley.com/catalogue/f1394fff-59c7-3b30-a5cb-bc09205c0a1d/

U2 - 10.55452/1998-6688-2026-23-1-37-51

DO - 10.55452/1998-6688-2026-23-1-37-51

M3 - Article

VL - 23

SP - 37

EP - 51

JO - Вестник Казахстанско-Британского технического университета

JF - Вестник Казахстанско-Британского технического университета

SN - 1998-6688

IS - 1

M1 - 3

ER -