International Journal of Advanced Technology and Engineering Exploration ISSN (Print): 2394-5443    ISSN (Online): 2394-7454 Volume-12 Issue-129 August-2025
  1. 4774
    Citations
  2. 2.8
    CiteScore
Development of a CAD system for stroke diagnosis using machine learning on DWI-MRI images

Izzatul Husna Azman1, Norhashimah Mohd Saad1, Abdul Rahim Abdullah1, Rostam Affendi Hamzah1, Ahmad Sobri bin Muda2 and Farzanah Atikah Yamba3

Faculty of Electrical Technology and Engineering,Universiti Teknikal Malaysia Melaka (UTeM), Hang Tuah Jaya, 76100 Durian Tunggal, Melaka,Malaysia1
Faculty of Medicine and Health Sciences,Universiti Putra Malaysia (UPM), 43400 Serdang,Malaysia2
PadiMedical Division, Lönge Medikal Sdn Bhd,Universiti Putra Malaysia (UPM), 43400 Serdang,Malaysia3
Corresponding Author : Norhashimah Mohd Saad

Recieved : 27-December-2024; Revised : 08-August-2025; Accepted : 12-August-2025

Abstract

Stroke remains one of the leading causes of disability and mortality worldwide, necessitating timely and accurate diagnosis to improve treatment outcomes. This study presents a computer-aided diagnosis (CAD) system designed to detect and classify stroke lesions in magnetic resonance imaging (MRI), specifically utilizing diffusion-weighted imaging (DWI) sequences. A hybrid segmentation technique, fuzzy c-means with active contour (FCMAC), is proposed to enhance lesion localization accuracy. For classification, the system evaluates traditional machine learning algorithms like support vector machine (SVM) and k-nearest neighbor (KNN), alongside deep learning models such as convolutional neural network (CNN) and bilayered neural network (BNN). The entire diagnostic pipeline is integrated into a MATLAB-based graphical user interface (GUI), facilitating real-time analysis and ease of use in clinical settings. Experimental results show that the proposed FCMAC method achieves a dice coefficient (DC) of 0.654, outperforming conventional segmentation techniques. Among the classifiers, KNN offered the best balance between prediction accuracy and computational efficiency. The final system, termed SmartStroke-Pro, enables early detection and classification of stroke, providing a reliable and practical tool to assist healthcare professionals, particularly in resource-limited environments. This framework has the potential to reduce diagnostic delays and support improved clinical decision-making in acute stroke care.

Keywords

Stroke diagnosis, Computer-aided diagnosis (CAD), DWI, Machine learning, Fuzzy c-means with active contour (FCMAC), SmartStroke-pro system.

Cite this article

Azman IH, Saad NM, Abdullah AR, Hamzah RA, Muda ASB, Yamba FA. Development of a CAD system for stroke diagnosis using machine learning on DWI-MRI images. International Journal of Advanced Technology and Engineering Exploration. 2025;12(129):1246-1263. DOI : 10.19101/IJATEE.2024.111102264

References
[1]
https://www.bernama.com/en/news.php?id=2018367. Accessed 22 October 2024.
[2]
https://www.ncbi.nlm.nih.gov/books/NBK499997/ Accessed 22 October 2024.
[3]
https://codeblue.galencentre.org/2022/12-most-long-term-care-disability-costs-galen/. Accessed 22 October 2024.
[4]
Montaño A, Hanley DF, Hemphill IIIJC. Hemorrhagic stroke. Handbook of Clinical Neurology. 2021; 176:229-48.
[Crossref] [Google Scholar]
[5]
Tan KS, Venketasubramanian N. Stroke burden in Malaysia. Cerebrovascular Diseases Extra. 2022; 12(2):58-62.
[Crossref] [Google Scholar]
[6]
Simonds GR. Recognizing hemorrhagic strokes. MedMastery. 2021.
[7]
https://www.mayoclinic.org/diseases-conditions/stroke/symptoms-causes/syc-20350113. Accessed 22 October 2024.
[8]
Zainuddin A. Malaysian stroke patients take average seven hours for hospital arrival. CodeBlue. 2022.
[9]
Khandelwal A, Sarma K, Hussain M, Dikshit P, Baidya DK. Acute ischemic stroke and the golden hour: critical updates. Journal of Neurosciences in Rural Practice. 2025; 16(2):152-9.
[Crossref] [Google Scholar]
[10]
Collen D, Stump DC, Gold HK. Thrombolytic therapy. Annual Review of Medicine. 1988; 39:405-23.
[Crossref] [Google Scholar]
[11]
Kandaya S, Abdullah AR, Mohd SN, Azman IH, Shair EF, Ali NH. Analysis of early stroke diagnosis based on brain magnetic resonance imaging using machine learning. Journal of Advanced Research in Applied Sciences and Engineering Technology. 2023; 32(3):241-55.
[Crossref] [Google Scholar]
[12]
Cetinoglu YK, Koska IO, Uluc ME, Gelal MF. Detection and vascular territorial classification of stroke on diffusion-weighted MRI by deep learning. European Journal of Radiology. 2021; 145:110050.
[Crossref] [Google Scholar]
[13]
Gheibi Y, Shirini K, Razavi SN, Farhoudi M, Samad-soltani T. CNN-Res: deep learning framework for segmentation of acute ischemic stroke lesions on multimodal MRI images. BMC Medical Informatics and Decision Making. 2023; 23(1):1-14.
[Crossref] [Google Scholar]
[14]
Azman IH, Saad NM, Abdullah AR, Hamzah RA, Samsudin A. Automated cad system for early stroke diagnosis. International Journal of Advanced Computer Science and Applications. 2023; 14(8):77-83.
[Crossref] [Google Scholar]
[15]
Mokli Y, Pfaff J, Dos SDP, Herweh C, Nagel S. Computer-aided imaging analysis in acute ischemic stroke–background and clinical applications. Neurological Research and Practice. 2019; 1(1):1-13.
[Crossref] [Google Scholar]
[16]
Keerthana S, Sathiyakumari K. Brain stroke segmentation using fuzzy C-means clustering. International Journal of Computer Applications. 2016; 154(4):26-30.
[Google Scholar]
[17]
Subudhi A, Dash P, Mohapatra M, Tan RS, Acharya UR, Sabut S. Application of machine learning techniques for characterization of ischemic stroke with MRI images: a review. Diagnostics. 2022; 12(10):1-19.
[Crossref] [Google Scholar]
[18]
Thiyagarajan SK, Murugan K. An exploration enhanced dynamic arithmetic optimization based modified fuzzy clustering framework for ischemic stroke lesion segmentation. International Journal of Information Technology. 2023; 15(8):4389-401.
[Crossref] [Google Scholar]
[19]
Marques AG, Souza LF, Dos SMA, Da CNJJ, Sarmento RM, Lucena IB, et al. Automatic segmentation of hemorrhagic stroke on brain CT images using convolutional neural networks through fine-tuning. In international joint conference on neural networks (IJCNN) 2022 (pp. 1-8). IEEE.
[Crossref] [Google Scholar]
[20]
Mandle AK, Sahu SP, Gupta G. Brain tumor segmentation and classification in MRI using clustering and kernel-based SVM. Biomedical and Pharmacology Journal. 2022; 15(2):699-716.
[Google Scholar]
[21]
Rukmawan SH, Aszhari FR, Rustam Z, Pandelaki J. Cerebral infarction classification using the k-nearest neighbor and naive bayes classifier. In journal of physics: conference series 2021 (pp. 1-7). IOP Publishing.
[Crossref] [Google Scholar]
[22]
Gao H, Bian Y, Cheng G, Yu H, Cao Y, Zhang H, et al. Identifying patients with acute ischemic stroke within a 6-h window for the treatment of endovascular thrombectomy using deep learning and perfusion imaging. Frontiers in Medicine. 2023; 10:1-8.
[Crossref] [Google Scholar]
[23]
Nazari-farsani S, Yu Y, Armindo RD, Lansberg M, Liebeskind DS, Albers G, et al. Predicting final ischemic stroke lesions from initial diffusion-weighted images using a deep neural network. NeuroImage: Clinical. 2023; 37:1-10.
[Crossref] [Google Scholar]
[24]
Aytaç E, Gönen M, Tatli S, Balgetir F, Dogan S, Tuncer T. Large vessel occlusion detection by non-contrast CT using artificial ıntelligence. Neurological Sciences. 2024; 45(9):4391-7.
[Crossref] [Google Scholar]
[25]
Garcia-salgado BP, Almaraz-damian JA, Cervantes-chavarria O, Ponomaryov V, Reyes-reyes R, Cruz-ramos C, et al. Enhanced ischemic stroke lesion segmentation in mri using attention u-net with generalized dice focal loss. Applied Sciences. 2024; 14(18):1-26.
[Crossref] [Google Scholar]
[26]
Ghaderi S, Mohammadi S, Ghaderi K, Kiasat F, Mohammadi M. Marker-controlled watershed algorithm and fuzzy C-means clustering machine learning: automated segmentation of glioblastoma from MRI images in a case series. Annals of Medicine and Surgery. 2024; 86(3):1460-75.
[Crossref] [Google Scholar]
[27]
İnce S, Kunduracioglu I, Bayram B, Pacal I. U-net-based models for precise brain stroke segmentation. Chaos Theory and Applications. 2025;7(1):50-60.
[Crossref] [Google Scholar]
[28]
Inna A, Selvakumar S, Khan A, Brijesh SG, Gurrala N, Pragnathmik. Brain stroke detection and classification system: a hybrid approach using deep learning techniques. Journal of Information Systems Engineering and Management. 2025; 10(40s):90-105.
[29]
Batra A, Kaushik G. SECTUBIM: automatic segmentation and classification of tumeric brain MRI images using FHS (FCM, HWT and SVM). International Journal of Engineering Science and Computing. 2017; 7(6):13190-4.
[Google Scholar]
[30]
Saad NM, Abdullah AR, Azman IH, Noor NS. A review on image classification techniques for MRI brain stroke lesion. Journal of Advanced Research in Applied Sciences and Engineering Technology. 2024; 40(2):62-73.
[Google Scholar]
[31]
Su H, Wang F, Zhang L, Li G. Fuzzy clustering algorithm‐segmented MRI images in analysis of effects of mental imagery on neurorehabilitation of stroke patients. Scientific Programming. 2021; 2021(1):1-10.
[Crossref] [Google Scholar]
[32]
Feng B, Zhou H, Feng J, Chen Y, Liu Y, Yu T, et al. Active contour model of breast cancer DCE‐MRI segmentation with an extreme learning machine and a fuzzy C‐means cluster. IET Image Processing. 2022; 16(11):2947-58.
[Crossref] [Google Scholar]
[33]
https://naemazam.medium.com/support-vector-machine-svm-in-machine-learning-66d0f6688ca5. Accessed 16 April 2024.
[34]
Siddiqi MH, Azad M, Alhwaiti Y. An enhanced machine learning approach for brain MRI classification. Diagnostics. 2022; 12(11):1-19.
[Crossref] [Google Scholar]
[35]
Yu Y, Heit JJ, Zaharchuk G. Improving ischemic stroke care with MRI and deep learning artificial intelligence. Topics in Magnetic Resonance Imaging. 2021; 30(4):187-95.
[Crossref] [Google Scholar]
[36]
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. Frontiers in Neurology. 2023; 14:1-12.
[Crossref] [Google Scholar]
[37]
Eshmawi AA, Khayyat M, Algarni AD, Hilali-jaghdam I. An ensemble of deep learning enabled brain stroke classification model in magnetic resonance images. Journal of Healthcare Engineering. 2022; 2022(1):1-10.
[Crossref] [Google Scholar]
[38]
Liu CF, Hsu J, Xu X, Ramachandran S, Wang V, Miller MI, et al. Deep learning-based detection and segmentation of diffusion abnormalities in acute ischemic stroke. Communications Medicine. 2021; 1(1):1-18.
[Crossref] [Google Scholar]
[39]
Zhu G, Chen H, Jiang B, Chen F, Xie Y, Wintermark M. Application of deep learning to ischemic and hemorrhagic stroke computed tomography and magnetic resonance imaging. In seminars in ultrasound, CT and MRI 2022 (pp. 147-52). WB Saunders.
[Crossref] [Google Scholar]
[40]
Saeedi S, Rezayi S, Keshavarz H, SR NK. MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques. BMC Medical Informatics and Decision Making. 2023; 23(1):1-17.
[Crossref] [Google Scholar]
[41]
Firmansyah MR, Astuti YP. Stroke classification comparison with KNN through standardization and normalization techniques. Advance Sustainable Science, Engineering and Technology. 2024; 6(1):1-8.
[Crossref] [Google Scholar]
[42]
https://prof-frenzel.medium.com/dear-friends-854ba66361d7. Accessed 22 October 2024.
[43]
Omarov B, Tursynova A, Postolache O, Gamry K, Batyrbekov A, Aldeshov S, et al. Modified UNet model for brain stroke lesion segmentation on computed tomography images. Computers, Materials & Continua. 2022; 71(3):1-17.
[Crossref] [Google Scholar]