ORIGINAL RESEARCH article
Front. Neurosci.
Sec. Brain Imaging Methods
Volume 19 - 2025 | doi: 10.3389/fnins.2025.1660870
This article is part of the Research TopicAutonomous Low-field Magnetic Resonance Imaging - Volume IIView all 6 articles
Comparative Validation of Automated Perfusion Analysis Software for Ischemic Penumbra Estimation and EVT Decision-Making
Provisionally accepted
Jonguk Kim1,2
Jong-Hyeok Park3Dongmin Kim3
Myungjae Lee3
Joon-Tae Kim4
Leonard Sunwoo5
Cheolkyu Jung5
Wi-Sun Ryu3*
Beom Joon Kim1*- 1Seoul National University Bundang Hospital Department of Neurology, Seongnam-si, Republic of Korea
- 2Seoul National University College of Medicine, Jongno-gu, Republic of Korea
- 3Artificial Intelligence Research Center, JLK Inc, Gangnam-gu, Republic of Korea
- 4Chonnam National University Hospital Department of Neurology, Gwangju, Republic of Korea
- 5Department of Radiology, Seoul National University Bundang Hospital, Seongnam-si, Republic of Korea
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Background While computed tomography perfusion is widely used in acute stroke imaging, magnetic resonance perfusion-weighted imaging (PWI) offers superior spatial resolution and tissue specificity, particularly when combined with diffusion-weighted imaging (DWI). However, no prior study has systematically compared automated PWI analysis platforms. This study aims to evaluate the performance of a newly developed software (JLK PWI) against the established RAPID platform in terms of volumetric agreement and clinical decision concordance. Methods This retrospective multicenter study included 299 patients with acute ischemic stroke who underwent PWI within 24 hours of symptom onset. Volumetric agreement between RAPID and JLK PWI was assessed using concordance correlation coefficients (CCC), Bland–Altman plots, and Pearson correlations. Agreement in endovascular therapy (EVT) eligibility was evaluated using Cohen's kappa based on DAWN and DEFUSE-3 criteria. Results The mean age was 70.9 years, 55.9% were male, and the median NIHSS score was 11 (IQR 5–17). The median time from the last known well to PWI was 6.0 hours. JLK PWI showed excellent agreement with RAPID for ischemic core (CCC=0.87; p<0.001) and hypoperfused volume (CCC = 0.88; p<0.001). EVT eligibility classifications based on DAWN criteria showed very high concordance across subgroups (κ=0.80–0.90), and substantial agreement was observed using DEFUSE-3 criteria (κ=0.76). Conclusion JLK PWI demonstrates high technical and clinical concordance with RAPID, supporting its use as a reliable alternative for MRI-based perfusion analysis in acute stroke care.
Keywords: Stroke, Perfusion-weighted image, Automated software, Magnetic resonance image, Mechanical thrombectomy
Received: 07 Jul 2025; Accepted: 20 Oct 2025.
Copyright: © 2025 Kim, Park, Kim, Lee, Kim, Sunwoo, Jung, Ryu and Kim. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Wi-Sun Ryu, wisunryu@jlkgroup.com
Beom Joon Kim, kim.bj.stroke@gmail.com
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.