Radiomics-based MRI model to predict hypoperfusion in lacunar infarction
Magnetic Resonance Imaging · 2025-07 · 120 · 110366
DOI: 10.1016/j.mri.2025.110366 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance Imaging, 2025-07. Verfasst von Chia-Peng Chang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Emergency Medicine, Chang Gung Memorial Hospital, Chiayi, Taiwan; Department of Nursing, Chang Gung University of Science and Technolog…. Hauptthemen laut MEDLINE: Stroke, Lacunar, Magnetic Resonance Imaging. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 24 Literaturangaben. Gefördert von: Chang Gung Memorial Hospital, Ministry of Education, National Science and Technology Council.
Abstract (Originalsprache)
BACKGROUND: Approximately 20-30 % of patients with acute ischemic stroke due to lacunar infarction experience early neurological deterioration (END) within the first three days after onset, leading to disability or more severe sequelae. Hemodynamic perfusion deficits may play a crucial role in END, causing growth in the infarcted area and functional impairments, and even poor long-term prognosis. Therefore, it is vitally important to predict which patients may be at risk of perfusion deficits to initiate treatment and close monitoring early, preparing for potential reperfusion. Our goal is to utilize radiomic features from magnetic resonance imaging (MRI) and machine learning techniques to develop a predictive model for hypoperfusion. METHOD: During January 2011 to December 2020, a retrospective collection of 92 patients with lacunar stroke was conducted, who underwent MRI within 48 h, had clinical laboratory values, follow-up prognosis records, and advanced perfusion image to confirm the presence of hypoperfusion. Using the initial MRI of these patients, radiomics features were extracted and selected from Diffusion Weighted Imaging (DWI), Apparent Diffusion Coefficient (ADC), and Fluid Attenuated Inversion Recovery (FLAIR) sequences. The data was divided into an 80 % training set and a 20 % testing set, and a hypoperfusion prediction model was developed using machine learning. RESULT: Tthe model trained on DWI + FLAIR sequence showed superior performance with an accuracy of 84.1 %, AUC 0.92, recall 79.5 %, specificity 87.8 %, precision 83.8 %, and F1 score 81.2. Statistically significant clinical factors between patients with and without hypoperfusion included the NIHSS scores and the size of the lacunar infarction. Combining these two features with the top seven weighted radiomics features from DWI + FLAIR sequence, a total of nine features were used to develop a new prediction model through machine learning. This model in test set achieved an accuracy of 88.9 %, AUC 0.91, recall 87.5 %, specificity 90.0 %, precision 87.5 %, and F1 score 87.5. CONCLUSION: Utilizing radiomics techniques on DWI and FLAIR sequences from MRI of patients with lacunar stroke, it is possible to predict the presence of hypoperfusion, necessitating close monitoring to prevent the deterioration of clinical symptoms. Incorporating stroke volume and NIHSS scores into the prediction model enhances its performance. Future studies of a larger scale are required to validate these findings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Emergency Medicine, Chang Gung Memorial Hospital, Chiayi, Taiwan; Department of Nursing, Chang Gung University of Science and Technology, Chiayi Campus, Chiayi, Taiwan; In-service Master Program in Artific…
- College of Medicine, Chang Gung University, Taoyuan, Taiwan; Department of Neurology, Chang Gung Memorial Hospital, Chiayi, Taiwan. Electronic address: deepblue@cgmh.org.tw.
- College of Medicine, Chang Gung University, Taoyuan, Taiwan; Department of Diagnostic Radiology, Chang Gung Memorial Hospital, Chiayi, Taiwan.
- Department of Emergency Medicine, Chang Gung Memorial Hospital, Chiayi, Taiwan. Electronic address: a3456711@cloud.cgmh.org.tw.
- College of Medicine, Chang Gung University, Taoyuan, Taiwan; Department of Neurosurgery, Chang Gung Memorial Hospital, Chiayi, Taiwan. Electronic address: dr1469@cgmh.org.tw.
- Department of Emergency Medicine, Chang Gung Memorial Hospital, Chiayi, Taiwan; Department of Nursing, Chang Gung University of Science and Technology, Chiayi Campus, Chiayi, Taiwan.
Förderung
- Chang Gung Memorial Hospital
- Ministry of Education
- National Science and Technology Council
Zitieren
APA
Chang, C. P., Huang, Y. C., Tsai, Y. H., Lin, L. C., Yang, J. T., Wu, K. H., Wu, P. H., & Peng, S. J. (2025). Radiomics-based MRI model to predict hypoperfusion in lacunar infarction. Magnetic Resonance Imaging, 120, 110366. https://doi.org/10.1016/j.mri.2025.110366
Vancouver
Chang CP, Huang YC, Tsai YH, Lin LC, Yang JT, Wu KH, et al. Radiomics-based MRI model to predict hypoperfusion in lacunar infarction. Magnetic Resonance Imaging. 2025;120:110366. doi:10.1016/j.mri.2025.110366
BibTeX
@article{Chang2025,
author = {Chang, Chia-Peng and Huang, Yen-Chu and Tsai, Yuan-Hsiung and Lin, Leng-Chieh and Yang, Jen-Tsung and Wu, Kai-Hsiang and Wu, Po-Han and Peng, Syu-Jyun},
title = {Radiomics-based MRI model to predict hypoperfusion in lacunar infarction},
journal = {Magnetic Resonance Imaging},
year = {2025},
volume = {120},
pages = {110366},
doi = {10.1016/j.mri.2025.110366}
}
EUVIMED