DOI: https://doi.org/10.14710/jmasif.17.1.78464

Comparative Analysis of Machine Learning for Stroke Classification Using YOLOv11 Detection and a Radiomics-Based Two-Stage Model

1Department of Informatics, University of Bengkulu, Indonesia

2Department of Information Systems, University of Bengkulu, Indonesia

3Graduate School of Engineering, Tottori University, Japan

Received: 13 Oct 2025; Revised: 3 Feb 2026; Accepted: 19 Feb 2026; Published: 26 Feb 2026.
Open Access Copyright (c) 2026 The authors. Published by Department of Informatics Universitas, Diponegoro
Creative Commons License This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Citation Format:
Abstract

Stroke is a leading cause of disability and death worldwide, including in Indonesia. Rapid and accurate diagnosis is crucial, especially during the golden period (3–4.5 hours). CT scans are the primary imaging modality, but manual interpretation is often limited by time, subjectivity, and radiologist availability. This study proposes a two-stage model integrating YOLOv11 for lesion detection and machine learning for classification, using radiomics for feature extraction. In the first stage, YOLOv11 detects lesions and generates bounding boxes, which serve as Regions of Interest (ROIs). In the second stage, radiomics features are extracted and classified using Naïve Bayes, Support Vector Machine (SVM), and Random Forest. Results show YOLOv11 achieved an overall mAP@50 of 0.732, with the highest performance in hemorrhagic stroke (0.741). Radiomics-based classification further improves stability, achieving accuracies of 0.97–0.99 and precision, recall, and F1 scores≥0.94. Among classifiers, SVM performed best, with a test accuracy of 0.97, a false positive rate of 1.23%, total error 0.0218, generalization gap -0.0117, variance 0.0002, standard deviation 0.003635, confidence interval 0.9708 (+/-0.0073), and consistent fold accuracy between 96.5–97.5%, indicating stability without overfitting. These findings confirm that the combination of the YOLOv11 two-stage model, radiomics, and SVM provides a robust approach to support stroke diagnosis.

Fulltext View|Download
Keywords: Digital Image Processing, Stroke, Radiomics, YOLOv11, Machine Learning.

Article Metrics:

Article Info
Section: Research Article
Language : EN
Recent articles
Comparison of Objective Weighting Methods in SAW and Their Effect on Alternative Ranking Results Transformer-Based Encoder-Decoder Model for Medical Image Captioning with Concept Embedding Performance Enhancement of Mushroom Species Classification via Modified InceptionV3 More recent articles
Most cited articles
PENYELESAIAN MASALAH JOB SHOP MENGGUNAKAN ALGORITMA GENETIKA ALGORITMA BACK PROPAGATION NEURAL NETWORK UNTUK PENGENALAN POLA KARAKTER HURUF JAWA Studi Komparasi Ekstraksi Fitur pada Pengenalan Wajah Menggunakan Principal Component Analysis (PCA) dan Wavelet Daubechies APLIKASI SISTEM INFORMASI GEOGRAFIS BERBASIS WEB PENYEBARAN DANA BANTUAN OPERASIONAL SEKOLAH OPTICAL CHARACTER RECOGNITION MENGGUNAKAN ALGORITMA TEMPLATE MATCHING CORRELATION More cited articles
  1. V. L. Feigin and M. Owolabi, “Pragmatic solutions to reduce the global burden of stroke: a World Stroke Organization–Lancet Neurology Commission,” Lancet Neurol., vol. 22, no. 12, pp. 1160–1206, 2023, doi: 10.1016/S1474-4422(23)00277-6
  2. Kemenkes, “Cegah Stroke Dengan Aktivitas Fisik [Prevent Stroke With Physical Activity],” Kementerian Kesehatan, p. 1, 2024, [Online]. Available: https://kemkes.go.id/id/cegah-stroke-dengan-aktivitas-fisik
  3. D. Dwilaksono, T. E. Fau, S. E. Siahaan, C. S. P. B. Siahaan, K. S. P. B. Karo, and T. Nababan, “Faktor-Faktor yang Berhubungan dengan Terjadinya Stroke Iskemik pada Penderita Rawat Inap [Factors Associated with the Occurrence of Ischemic Stroke in Hospitalized Patients],” J. Penelit. Perawat Prof., vol. 5, no. 2, pp. 449–458, 2023, doi: 10.37287/jppp.v5i2.1433
  4. A. K. Boehme, C. Esenwa, and M. S. V. Elkind, “Stroke Risk Factors, Genetics, and Prevention,” Circulation Research, vol. 120, no. 3, pp. 472–495, 2017, doi: 10.1161/CIRCRESAHA.116.308398
  5. I. Tarigan, “Study on the Effectiveness of Thrombolytic Drugs in Emergency Treatment of Ischemic Stroke: Time and Outcome Analysis,” Jurnal Farmasimed, vol. 6, no. 2, pp. 200–204, 2024, [Online]. Available: https://ejournal.medistra.ac.id/index.php/JFM/article/view/2506
  6. A. Familah, A. F. Arifin, A. H. Muchsin, M. E. Rachman, and Dahliah, “Characteristics of Ischemic Stroke and Hemorrhagic Stroke Patients,” Fakumi Med. J. J. Med. Students, vol. 4, no. 6, pp. 456–463, 2024, doi: 10.33096/fmj.v4i6.468
  7. S. Setianingsih, L. E. Darwati, and H. A. Prasetya, “Study Deskriptif Penanganan Pre-Hospital Stroke Life Support Pada Keluarga [Descriptive Study of Pre-Hospital Stroke Life Support Management in Families],” J. Perawat Indones., vol. 3, no. 1, p. 55, 2019, doi: 10.32584/jpi.v3i1.225
  8. L. Dewi and E. Fitraneti, “Stroke Iskemik [Iscemic Stroke]”, Scientific Journal, vol. 3, no. 6, pp. 379–388, 2024, doi: 10.56260/sciena.v3i6.173
  9. M. G. Ragab et al., “A Comprehensive Systematic Review of YOLO for Medical Object Detection (2018 to 2023),” IEEE Access, vol. 12, no. December, pp. 57815–57836, 2024, doi: 10.1109/ACCESS.2024.3386826
  10. A. Vial et al., “The role of deep learning and radiomic feature extraction in cancer-specific predictive modelling: A review,” Transl. Cancer Res., vol. 7, no. 3, pp. 803–816, 2018, doi: 10.21037/tcr.2018.05.02
  11. S. Yousaf, S. M. Anwar, H. RaviPrakash, and U. Bagci, “Brain Tumor Survival Prediction Using Radiomics Features,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 12449 LNCS, pp. 284–293, 2020, doi: 10.1007/978-3-030-66843-3_28
  12. M. Nijiati et al., “Deep learning and radiomics of longitudinal CT scans for early prediction of tuberculosis treatment outcomes,” Eur. J. Radiol., vol. 169, no. July, p. 111180, 2023, doi: 10.1016/j.ejrad.2023.111180
  13. N. H. Putri, J. Jasril, M. Irsyad, S. Agustian, and F. Yanto, “Klasifikasi Citra Stroke Menggunakan Augmentasi dan Convolutional Neural Network EfficientNet-B0 [Stroke Image Classification Using Augmentation and Convolutional Neural Network EfficientNet-B0],” J. Media Inform. Budidarma, vol. 7, no. 2, p. 650, 2023, doi: 10.30865/mib.v7i2.5981
  14. H. Kamozawa, M. Tanaka, “Atrial Fibrillation Detection from Holter ECG Using Hybrid CNN‒LSTM Model and P/f-wave Identification”, Advanced Biomedical Engineering, vol. 14, pp. 46–53, 2025, doi: 10.14326/abe.14.46
  15. V. Dharshini, S. Deepika, S. B. Devamane, R. Divya, and Gaganashree, “Performance Analysis Machine Learning Algorithms for Stress Detection,” Proc. - 2023 Int. Conf. Comput. Intell. Information, Secur. Commun. Appl. CIISCA 2023, vol. 7, no. 4, pp. 395–400, 2023, doi: 10.1109/CIISCA59740.2023.00081
  16. A. I. Ardelean, E. R. Ardelean, and A. Marginean, “Can YOLO Detect Retinal Pathologies? A Step Towards Automated OCT Analysis,” Diagnostics, vol. 15, no. 14, pp. 1–22, 2025, doi: 10.3390/diagnostics15141823
  17. S. M. A. Monisha and R. Rahman, “Brain Tumor Detection in MRI Based on Federated Learning with YOLOv11,” arXiv, 2025, doi: 10.48550/arXiv.2503.04087
  18. J. Gong et al., “Enhancing brain metastasis prediction in non-small cell lung cancer: a deep learning-based segmentation and CT radiomics-based ensemble learning model,” Cancer Imaging, vol. 24, no. 1, pp. 1–12, 2024, doi: 10.1186/s40644-023-00623-1
  19. J. Permatasari, E. U. Armin, E. Sunardi, M. B. Laili, and S. M. Putri,
  20. “Evaluasi kinerja YOLOv11 pada deteksi penyakit tanaman cabai: Studi komparatif dengan YOLOv8, YOLOv5, dan SSD [Performance evaluation of YOLOv11 for chili plant disease detection: A comparative study with YOLOv8, YOLOv5, and SSD],” Jurnal Teknologi, vol. 25, no. 3, 2025, [Online]. Available: https://e-jurnal.pnl.ac.id/teknologi/article/view/8400
  21. A. Ardiansyah, A. S. Widagdo, K. N. Qodri, D. Hidayani, and M. Romadhani,
  22. “Implementasi deteksi tumor otak menggunakan YOLOv11 dan Flask [Implementation of brain tumor detection using YOLOv11 and Flask],” Jurnal FASILKOM (Teknologi Informasi dan Ilmu Komputer), vol. 15, no. 2, 2025, doi: 10.37859/jf.v15i2.9703
  23. W. Zhang, Y. Guo, and Q. Jin, “Radiomics and Its Feature Selection: A Review,” Symmetry (Basel)., vol. 15, no. 10, 2023, doi: 10.3390/sym15101834
  24. M. R. Salmanpour, M. Shamsaei, G. Hajianfar, H. Soltanian-Zadeh, and A. Rahmim, “Longitudinal clustering analysis and prediction of Parkinson’s disease progression using radiomics and hybrid machine learning,” Quant. Imaging Med. Surg., vol. 12, no. 2, pp. 906–919, 2022, doi: 10.21037/qims-21-425
  25. S. B. Lin, Y. Wang, and D. X. Zhou, “Generalization Performance of Empirical Risk Minimization on Over-Parameterized Deep ReLU Nets,” IEEE Trans. Inf. Theory, vol. 71, no. 3, pp. 1978–1993, 2025, doi: 10.1109/TIT.2025.3531048
  26. J. Liu et al., “Deep learning-based identification and localization of intracranial hemorrhage in patients using a large annotated head computed tomography dataset: A retrospective multicenter study,” Intell. Med., vol. 5, no. 1, pp. 14–22, 2025, doi: 10.1016/j.imed.2024.11.002
  27. G. Tapia, H. Allende-Cid, S. Chabert, D. Mery, and R. Salas, “Benchmarking YOLO Models for Intracranial Hemorrhage Detection Using Varied CT Data Sources,” IEEE Access, vol. 12, no. October, pp. 188084–188101, 2024, doi: 10.1109/ACCESS.2024.3510517
  28. M. S. Pepe, Z. Feng, H. Janes, P. M. Bossuyt, and J. D. Potter, “Pivotal evaluation of the accuracy of a biomarker used for classification or prediction: Standards for study design,” J. Natl. Cancer Inst., vol. 100, no. 20, pp. 1432–1438, 2008, doi: 10.1093/jnci/djn326

Last update:

No citation recorded.

Last update: 2026-02-26 08:55:50

No citation recorded.