EUVIMEDEUVIMED entdecken
Crossref

Prediction of NIHSS Scores and Acute Ischemic Stroke Severity Using a Cross-attention Vision Transformer Model with Multimodal MRI

Pahati Tuxunjiang, Chencui Huang, Zhen Zhou, Wenyi Zhao, Bingyan Han, Weixiong Tan, Jingru Wang, HuangHanjiaerbieke Kukun, Wei Zhao, Rui Xu, Ainikaerjiang Aihemaiti, Yimuran Subi und 4 weitere

Academic Radiology · 2025

DOI: 10.1016/j.acra.2025.05.031 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Radiology, 2025. Verfasst von Pahati Tuxunjiang und 15 weiteren Autor:innen. Beteiligte Einrichtung: The First Affiliated Hospital of Xinjiang Medical University, Department of Radiology, Urumqi, Xinjiang Uygur Autonomous Region, PR China (P.T., H.H.…. Hauptthemen laut MEDLINE: Ischemic Stroke, Multimodal Imaging, Magnetic Resonance Imaging, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: Natural Science Foundation of Xinjiang Uygur Autonomous Region.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RATIONALE AND OBJECTIVES: This study aimed to develop and evaluate models for classifying the severity of neurological impairment in acute ischemic stroke (AIS) patients using multimodal MRI data. METHODS: A retrospective cohort of 1227 AIS patients was collected and categorized into mild (NIHSS 0.05), and the AUC value consistently exceeds 0.900. A significant predictive difference was observed in the BMI group (p < 0.001). The results of external validation showed that the AUC values of the model 8 in center 2 and center 3 reached 0.910 and 0.912, respectively. Visualization using Grad-CAM emphasized the infarct core as the most critical region contributing to predictions, with consistent feature attention across DWI, T1WI, T2WI, and FLAIR sequences, further validating the interpretability of the model. CONCLUSION: A ViT-based DL model with cross-modal fusion strategies provides a non-invasive and efficient tool for classifying AIS severity. Its robust performance across subgroups and interpretability make it a promising tool for personalized management and decision-making in clinical practice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Ischemic StrokeMultimodal ImagingMagnetic Resonance ImagingImage Interpretation, Computer-AssistedHumansMaleFemaleRetrospective StudiesSeverity of Illness IndexMiddle AgedAgedDeep LearningDiffusion Magnetic Resonance ImagingSensitivity and Specificity

Stichwörter der Autor:innen

Acute ischemic strokeCross-AttentionDeep learningMultimodal MRI FusionPredictionVision transformer

Autor:innen und Institutionen

  • The First Affiliated Hospital of Xinjiang Medical University, Department of Radiology, Urumqi, Xinjiang Uygur Autonomous Region, PR China (P.T., H.H.K., W.Z., R.X., A.A., Y.S., Y.W.). Electronic address: 15140674915@163…
  • Hangzhou Deepwise & League of PHD Technology Co., Ltd, Deepwise AI lab, Hangzhou City, Zhejiang Province, PR China (C.H., Z.Z., W.T., J.W.). Electronic address: huangchencui@deepwise.com.
  • Hangzhou Deepwise & League of PHD Technology Co., Ltd, Deepwise AI lab, Hangzhou City, Zhejiang Province, PR China (C.H., Z.Z., W.T., J.W.). Electronic address: zhouzhen@deepwise.com.
  • Hunan University of Medicine General Hospital, Department of Radiology, Huaihua City, Hunan Province, PR China (W.Z., J.Z.). Electronic address: 49084626@qq.com.
  • The Seventh Affiliated Hospital of Xinjiang Medical University, Department of Radiology, Urumqi, Xinjiang Uygur Autonomous Region, PR China (B.H., C.X., Y.C.). Electronic address: 182429293@qq.com.
  • Hangzhou Deepwise & League of PHD Technology Co., Ltd, Deepwise AI lab, Hangzhou City, Zhejiang Province, PR China (C.H., Z.Z., W.T., J.W.). Electronic address: tanweixiong@deepwise.com.

Förderung

  • Natural Science Foundation of Xinjiang Uygur Autonomous Region

Zitieren

APA

Tuxunjiang, P., Huang, C., Zhou, Z., Zhao, W., Han, B., Tan, W., Wang, J., Kukun, H., Zhao, W., Xu, R., Aihemaiti, A., Subi, Y., Zou, J., Xie, C., Chang, Y., & Wang, Y. (2025). Prediction of NIHSS Scores and Acute Ischemic Stroke Severity Using a Cross-attention Vision Transformer Model with Multimodal MRI. Academic Radiology. https://doi.org/10.1016/j.acra.2025.05.031

Vancouver

Tuxunjiang P, Huang C, Zhou Z, Zhao W, Han B, Tan W, et al. Prediction of NIHSS Scores and Acute Ischemic Stroke Severity Using a Cross-attention Vision Transformer Model with Multimodal MRI. Academic Radiology. 2025. doi:10.1016/j.acra.2025.05.031

BibTeX
@article{Tuxunjiang2025,
  author = {Tuxunjiang, Pahati and Huang, Chencui and Zhou, Zhen and Zhao, Wenyi and Han, Bingyan and Tan, Weixiong and Wang, Jingru and Kukun, HuangHanjiaerbieke and Zhao, Wei and Xu, Rui and Aihemaiti, Ainikaerjiang and Subi, Yimuran and Zou, Jingyang and Xie, Chao and Chang, Yifan and Wang, Yunling},
  title = {Prediction of NIHSS Scores and Acute Ischemic Stroke Severity Using a Cross-attention Vision Transformer Model with Multimodal MRI},
  journal = {Academic Radiology},
  year = {2025},
  doi = {10.1016/j.acra.2025.05.031}
}
Kostenlos starten →