Classification of Ischemic Stroke with Convolutional Neural Network (CNN) approach on b-1000 Diffusion-Weighted (DW) MRI

  • Andi Kurniawan Nugroho Institut Teknologi Sepuluh Nopember (ITS) Surabaya
  • Dinar Mutiara Kusumo Nugraheni Department of Computer Science, Universitas Diponegoro , Semarang, Indonesia
  • Terawan Agus Putranto RSPAD Gatot Subroto Presidential Hospital, Jakarta, Indonesia
  • I Ketut Eddy Purnama Department of Computer Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
  • Mauridhi Hery Purnomo Electrical Engineering Department, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
Keywords: Ischemic Stroke, Classification, CNN, b-1000 Diffusion-Weighted (DW) MRI, Accuracy


When the blood flow to the arteries in brain is blocked, its known as Ischemic stroke or blockage stroke. Ischemic stroke can occur due to the formation of blood clots in other parts of the body. Plaque buildup in arteries, on the other hand, can cause blockages because if it ruptures, it can form blood clots. The b-1000 Diffusion Weighted (DW) Magnetic Resonance Imaging (MRI) image was used in a general examination to obtain an image of the part of the brain that had a stroke. In this study, classifications used several variations of layer convolution to obtain high accuracy and high computational consumption using b-1000 Diffusion Weighted (DW) MR in ischemic stroke types: acute, sub-acute and chronic. Ischemic stroke was classified using five variants of the Convolutional Neural Network (CNN) architectural design, i.e., CNN1–CNN5. The test results show that the CNN5 architectural design provides the best ischemic stroke classification compared to other architectural designs tested, with an accuracy of 99.861%, precision 99.862%, recall 99.861, and F1-score 99.861%.


Download data is not yet available.


Indah Permata Sari, Faktor-Faktor yang Berhubungan dengan Terjadinya Stroke Berulang pada Penderita Pasca Stroke, Universitas Muhammadiyah Surakarta, 2015.

A. K. Nugroho, T. A. Putranto, I. K. E. Purnama, and M. H. Purnomo, Multi Segmentation Method for Hemorraghic Detection, 2018 Int. Conf. Intell. Auton. Syst., pp. 62–66, 2018.

E. R. da Silva, Ambiente virtual colaborativo de diagn ´ ostico a dist ˆ ancia integrado a ferramentas de manipulac¸ ˜ ao de imagens,” Universidade Federal de Pernambuco, 2010.

A. D. Guo, J. Fridriksson, P. Fillmore, C. Rorden, H. Yu, K. Zheng and S. Wang, Automated Lesion Detection on MRI scans Using Combined Unsupervised and Supervised Methods, BMC Med. Imaging, vol. 15, pp. 1–21, 2015.

and A.-B. M. S. N. Farid, B. M. Elbagoury, M. Roushdy, A Comparative Analysis for Support Vector Machines for Stroke Patients, in WSEAS Proceedings of the 7th European Computing Conference, 2013, pp. 71–76.

and P. J. T. Mroczek, J. W. Grzymała-Busse, Z. S. Hippe, A Machine Learning Approach to Mining Brain Stroke Data, Springer Berlin Heidelb., pp. 147–158, 2012.

C. S. O. Maier and and H. H. oder, N. D. Forkert, T. Martinetz, Classifiers for Ischemic Stroke Lesion Segmentation : A Comparison Study, PLoS One, vol. 10, pp. 1–16, 2015.

and P. J. M. Havaei, N. Guizard, H. Larochelle, Deep Learning Trends for Focal Brain Pathology Segmentation in MRI, arXiv, vol. abs/1607.0, 2016.

and N. A. G. Altan, Y. Kutlu, Deep Belief Network Based brain Activity Classification Using EEG From slow Cortical Potentials in Stroke, in Proceedings of the International Conference on Advanced Technology & Sciences, 2016, pp. 233–239.

A. Wouters, P. Dupont, B. Norrving, and R. Laage, Prediction of Stroke Onset Is Improved by Relative Fluid-Attenuated Inversion Recovery and Perfusion Imaging, Stroke, pp. 2559–2564, 2016, doi: 10.1161/STROKEAHA.116.013903.

M. P. P. ; S. T. ;Toan H. B. Visitsattapongse;Chuchart, Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and, Sensor, vol. 21, pp. 1–18, 2021, doi:

X. Liu, M. Niethammer, R. Kwitt, and M. Mccormick, Low-Rank to the Rescue – Atlas-based Analyses in the Presence of Pathologies, HHS, vol. 17, pp. 97–104, 2016, doi: 10.1007/978-3-319-10443-0_13.

A. K. Nugroho, T. A. Putranto, M. H. Pumomo, and I. K. E. Purnama, Semi Automatic Method for Basal Ganglia and White Matter Lesion Segmentation in MRI Images of Cronic Stroke Patients Using Adaptive Otsu, 2018 Int. Conf. Comput. Eng. Netw. Intell. Multimedia, CENIM 2018 - Proceeding, pp. 1–6, 2018, doi: 10.1109/CENIM.2018.8711285.

Ellwaa A. et al, Brain Tumor Segmantation Using Random Forest Trained on Iteratively Selected Patients, 2016, doi:

L. Le Folgoc, A. V. Nori, S. Ancha, and A. Criminisi, Lifted Auto-Context Forests for Brain Tumour Segmentation, Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 10154 LNCS, pp. 171–183, 2016, doi: 10.1007/978-3-319-55524-9_17.

and L. S. L´aszl´o Lefkovits, Szid´onia Lefkovits, Brain Tumor Segmentation with Optimized Random Forest, in MICCAI, 2016, vol. 1, pp. 88–99, doi: 10.1007/978-3-319-55524-9.

M.-C. L. Bi Song, Chen-Rui Chou, Xiaojing Chen, Albert Huang, Anatomy-Guided Brain Tumor Segmentation and Classification, in International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, 2017, pp. 162–170, doi:

H. V. N. Z. Vemulapalli, Cross-Domain Synthesis of Medical Images Using Efficient Location-Sensitive Deep Network, in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015, pp. 1–8, doi: //

M. Ghafoorian et al., Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities, Sci. Rep., no. November 2016, pp. 1–12, 2017, doi: 10.1038/s41598-017-05300-5.

M. Z. Abdelrahman Ellwaa, Ahmed Hussein, Essam AlNaggar, Brain Tumor Segmantation Using Random Forest Trained on Iteratively Selected Patients, 2016.

A. C. Loic Le Folgoc, Aditya V. Nori, Lifted Auto-Context Forests for Brain Tumour Segmentation, 2016.

A.-B. M. S. Heba Mohsena, El-Sayed A.El-Dahshan, El-Sayed M.El-Horbaty, Classification Using Deep Learning Neural Networks for Brain Tumors, Futur. Comput. Informatics J., pp. 68–71, 2018.

E. L. G. Pedro Henrique BandeiraDiniz, Thales Levi Azevedo Valente, João Otávio Bandeira Diniz, Aristófanes Corrêa Silva, Marcelo Gattassa , Nina Ventura, Bernardo Carvalho Muniz, Detection of White Matter Lesion Regions in MRI Using SLIC0 and Convolutional Neural Network, Comput. Methods Programs Biomed., vol. 167, pp. 49–63, 2018.

and V. H. C. D. A. D. R. Pereira, P. P. R. Filho, G. H. De Rosa, J. P. Papa, Stroke Lesion Detection Using Convolutional Neural Networks, 2018.

M. Everingham, S. M. A. Eslami, L. Van Gool, C. K. I. Williams, and J. Winn, The P ASCAL Visual Object Classes Challenge : A Retrospective, Int. J. Comput. Vis., vol. 111, no. 1, pp. 98–136, 2015, doi: 10.1007/s11263-014-0733-5.

P. Ambrosini, I. Smal, D. Ruijters, W. J. Niessen, A. Moelker, and T. Van Walsum, A Hidden Markov Model for 3D Catheter Tip Tracking with 2D X-ray Catheterization Sequence and 3D Rotational Angiography, IEEE Trans. Med. Imaging, vol. 0062, no. c, pp. 1–11, 2016, doi: 10.1109/TMI.2016.2625811.

R. Rokhana, Classification of Biomedical Data of Thermoacoustic Tomography to Detect Physiological Abnormalities in the Body Tissues, in 2016 International Electronics Symposium (IES) Classification, 2016, vol. 2, pp. 60–65.

N. Tamami, P. S. Wardana, R. Rokhana, and H. Hermawan, Neural Network Classification of Supraspinatus Muscle Electromyography Feature Signal, in 2017 International Electronics Symposium on Engineering Technology and Applications (IES-ETA), 2017, pp. 223–228.

Y. Yamasari, S. M. S. Nugroho, D. F. Suyatno, and M. H. Purnomo, Meta-Algoritme Adaptive Boosting untuk Meningkatkan Kinerja Metode Klasifikasi pada Prestasi Belajar Mahasiswa, JNTETI, vol. 6, no. 3, pp. 333–341, 2017, doi:

M. H. Purnomo, Klasifikasi Nyeri pada Video Ekspresi Wajah Bayi Menggunakan DCNN Autoencoder dan LSTM, JNTETI, vol. 7, no. 3, pp. 308–316, 2018, doi:

A. Nasuha, T. A. Sardjono, and M. H. Purnomo, Pengenalan Viseme Dinamis Bahasa Indonesia Menggunakan Convolutional Neural Network, JNTETI, vol. 7, no. 3, pp. 258–265, 2018, doi:

S. E. Limantoro, Y. Kristian, and D. D. Purwanto, Pemanfaatan Deep Learning pada Video Dash Cam untuk Deteksi Pengendara Sepeda Motor, JNTETI, vol. 7, no. 2, pp. 3–9, 2018, doi:

W. Setiawan and F. Damayanti, Layers Modification of Convolutional Neural Network for Pneumonia Detection, J. Phys. Conf. Ser., vol. 1477, no. 5, 2020, doi: 10.1088/1742-6596/1477/5/052055.

H. Wu, M. Xin, W. Fang, H. M. Hu, and Z. Hu, Multi-Level Feature Network with Multi-Loss for Person Re-Identification, IEEE Access, vol. 7, pp. 91052–91062, 2019, doi: 10.1109/ACCESS.2019.2927052.

G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, Densely connected convolutional networks, Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 2261–2269, 2017, doi: 10.1109/CVPR.2017.243.

M. Sandler, M. Zhu, A. Zhmoginov, and C. V Mar, MobileNetV2: Inverted Residuals and Linear Bottlenecks, in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 4510–4520.

A. D. J. Haicheng Wang, Vineeth Bhaskara, Alex Levinshtein, Stavros Tsogkas, Efficient Super-Resolution Using MobileNetV3, in Computer Vision - ECCV 2020 Workshops - Glasgow, UK, August 23-28, 2020, 2020, pp. 87–102, doi:

H. P. A. Tjahyaningtijas, A. K. Nugroho, C. V. Angkoso, I. K. E. Purnama, and M. H. Purnomo, Automatic Segmentation on Glioblastoma Brain Tumor Magnetic Resonance Imaging Using Modified U-Net, Emit. Int. J. Eng. Technol., vol. 8, no. 1, pp. 161–177, 2020, doi: 10.24003/emitter.v8i1.505.

How to Cite
Nugroho, A. K., Dinar Mutiara Kusumo Nugraheni, Terawan Agus Putranto, I Ketut Eddy Purnama, & Mauridhi Hery Purnomo. (2022). Classification of Ischemic Stroke with Convolutional Neural Network (CNN) approach on b-1000 Diffusion-Weighted (DW) MRI . EMITTER International Journal of Engineering Technology, 10(1), 195-216.