AI-Driven Stroke Classification and Detection: A Retrospective Study Using MRI Imaging
DOI:
https://doi.org/10.63682/jns.v14i15S.4928Keywords:
Magnetic Resonance Imaging, Diffusion Weighted Imaging, Apparent Diffusion Coefficient, Acute Stroke, Chronic Stroke, Artificial Intelligence, Machine Learning..Abstract
Purpose: This study aims to develop an artificial intelligence (AI)-based method for accurately distinguishing between acute and chronic stroke using MRI imaging, to enhance diagnostic precision, treatment planning, and prognosis evaluation.
Method: A total of 700 patient MRI datasets were utilized, with an 80/20 split for training and testing. The MRI images underwent preprocessing and key feature extraction, followed by classification using a Support Vector Machine (SVM). Model performance was evaluated using standard metrics: precision, recall, F1-score, and support.
Results: The training set, comprising approximately 2,480 data points, demonstrated strong model performance. For non-stroke cases, the model achieved a precision of 0.95 and a recall of 0.92, indicating a low false positive rate. For stroke cases, the precision was 0.95 and the recall was 0.88, reflecting a slightly higher false positive rate. High F1-scores in both categories confirmed a well-balanced performance between precision and recall.
Conclusion: The proposed AI-based classification model effectively distinguishes between stroke and non-stroke MRI images, showing promise in aiding clinical diagnosis and improving patient outcomes. Future research will focus on addressing dataset imbalances and evaluating the performance of alternative machine learning algorithms to further enhance model robustness
Downloads
Metrics
References
Murphy SJ, Werring DJ. Stroke: causes and clinical features. Medicine (Abingdon). 2020 Sep 1;48(9):561.
What Is an Acute (or Sudden) Stroke? [Internet]. [cited 2025 Mar 22]. Available from: https://www.verywellhealth.com/what-is-an-acute-stroke-3146171
Chronic Stroke: Where in the Recovery Process Is This Phase? [Internet]. [cited 2025 Mar 22]. Available from: https://www.flintrehab.com/chronic-stroke/
WHO EMRO | Stroke, Cerebrovascular accident | Health topics [Internet]. [cited 2025 Mar 22]. Available from: https://www.emro.who.int/health-topics/stroke-cerebrovascular-accident/index.html
Zhang S, Xu S, Tan L, Wang H, Meng J. Stroke Lesion Detection and Analysis in MRI Images Based on Deep Learning. J Healthc Eng. 2021 Jan 1;2021(1):5524769.
Singla R. Artificial intelligence in disease diagnosis: a systematic literature review, synthesizing framework and future research agenda. J Ambient Intell Humaniz Comput.
Zhang S, Xu S, Tan L, Wang H, Meng J. Stroke Lesion Detection and Analysis in MRI Images Based on Deep Learning. J Healthc Eng. 2021;2021.
Lee H, Lee EJ, Ham S, Lee H Bin, Lee JS, Kwon SU, et al. Machine Learning Approach to Identify Stroke Within 4.5 Hours. Stroke. 2020 Mar 1;51(3):860–6.
Miyamoto N, Ueno Y, Yamashiro K, Hira K, Kijima C, Kitora N, et al. Stroke classification and treatment support system artificial intelligence for usefulness of stroke diagnosis. Front Neurol. 2023;14.
Pathan MS, Jianbiao Z, John D, Nag A, Dev S. Identifying Stroke Indicators Using Rough Sets. IEEE Access. 2020;8:210318–27
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
