Ischemic Stroke Classification using Random Forests Based on Feature Extraction of Convolutional Neural Networks

Glori Stephani Saragih, Zuherman Rustam, Dipo Aldila, Rahmat Hidayat, Reyhan E. Yunus, Jacub Pandelaki


Stroke has become a global health problem, due to high mortality and disability, with two-thirds of all strokes occurring in developing countries. In Indonesia, stroke is a disease with the highest mortality rate, namely in the first rank for more than two decades, 1990-2017. Stroke is divided into two types, ischemic and hemorrhagic; however, 87% of stroke sufferers are ischemic stroke. Suppose an ischemic stroke is found, and the patient is a new sufferer. In that case, the patient should get direct treatment because there is a golden period in stroke management that is if 4.5 hours to help and reduce the risk of death or permanent disability. High mortality and disability raise awareness of the importance of early detection of ischemic stroke; therefore, research has been carried out, especially in technology. To carry out automatic diagnosis, machine learning and deep learning can be used, especially because of their ability to provide high accuracy prediction results. In this study, the authors will provide an update in the detection of ischemic stroke based on patient CT scan by replacing NN's role on CNN with random forests. Thus, after feature extraction on CNN, the fully connected layer on CNN is completely replaced by random forests in classifying data. Based on the proposed method, the accuracy of testing is 100% when the percentage of the testing dataset is 10% and the number of trees more than 100 with criterion Gini or entropy.


convolutional neural networks; image classification; neuroimaging; random forests; stroke ischemic.

Full Text:



J. Stein, Essentials of Physical Medicine and Rehabilitation Chapter 159 Stroke, Philadelphia: Elsevier, 2020.

Heniwati, and H. Thabrany, “Perbandingan Klaim Penyakit Katastropik Peserta Jaminan Kesehatan Nasional di Provinsi DKI Jakarta dan Nusa Tenggara Timur tahun 2014â€, Jurnal Ekonomi Kesehatan Indonesia, 2006, vol. 1, no. 2.

Ministry of Health of the Republic of Indonesia. (2019). [Online]. Available:

C. Chin, et. al, “An Automated Early Ischemic Stroke Detection System Using CNN Deep Learning Algorithm,†IEEE 8th International Conference on Awareness Science and Technology (iCAST), pp. 368-372, 2017.

Ministry of Health of the Republic of Indonesia. (2017). [Online]. Available:

American Stroke Association, Let’s talk about Ischemic Stroke, Dallas: American Heart Association, 2020.

J. G. Lee, et. al, “Deep Learning in Medical Imaging: General Review,†Korean Journal of Radiology, vol. 18, no. 4, pp. 570-584, 2017.

I. Goodfellow, et. al, Deep Learning, England: The MIT Press Cambridge, 2016.

A. Clerigues, et al. “Acute ischemic stroke lesion core segmentation in CT perfusion images using fully convolutional neural networks,†Computers in Biology and Medicine, vol. 115, 2019.

R. S. Baros, et. al. “Automated segmentation of subarachnoid hemorrhages with convolutional neural networks,†Informatics in Medicine Unlocked, vol. 19, 2020.

N. H. Rajini, and R. Bhavani, “Computer aided detection of ischemic stroke using segmentation and texture features,†Measurement, vol. 46, no. 6, 1865-1874, 2013.

O. Maier, et. al, “Classifier for ischemic stroke lesion segmentation: A comparison study,†PloS One, vol. 10, no. 12, 2015.

K. C. Ho, et. al, “A machine learning approach for classifying ischemic stroke onset time from imaging,†IEEE Transactions on Medical Imaging, vol. 38, no. 7, pp. 1666-1676, 2019.

H. Lee, et. al, “Machine learning approach to identify stroke within 4.5 hours,†Stroke, vol. 51, no. 3, pp. 860-866, 2020.

A. Subudhi, et. al, “Automated segmentation and classification of brain stroke using expectation-maximization and random forest classifier,†Biocybernetics and Biomedical Engineering, vol. 40, no. 1, pp. 277-289, 2020.

G. Cao, et. al, “A hybrid Cnn-Rf method for electron microscopy images segmentation,†Journal Biometrics Biomaterials and Tissue Engineering, vol. 18, no. 114, 2013.

Z. Rustam and G. S. Saragih, “Prediction schizophrenia using random forest,†TELKOMNIKA Telecommunication, Computing, Electronics and Control, vol. 18, no 3, pp. 1433-1438, 2019.

A. Vrtkova, “Predicting clinical status of patients after an acute ischemic stroke using random forests,†The International Conference on Information and Digital Technologies, 2017.

Q. Zou, “Predicting diabetes mellitus with machine learning techniques,†Frontier in Genetics. Available: 9.doi:10.3389/fgene.2018.00515.

M. Huljanah, et. al, “Feature selection using random forest classifier for predicting prostate cancer,†IOP Conference Series: Materials science and Engineering, 546, 052031. Available: doi:10.1088/1757-899x/546/5/052031.

U. Apriliani and Z. Rustam, “Osteoarthritis disease prediction based on random forest,†International Conference on Advanced Computer Science and Information Systems (ICACSIS). Available: doi:10.1109/icacsis.2018.8618166.

A. F. M. Agarap, “An architecture combining convolutional neural network (CNN) and support vector machine (SVM) for image classification,†arXiv preprint arXiv. 1712.03541v2, February 2019.

L. Guifang, S. Wei, “Research on convolutional neural network based on improved Relu piecewise activation function,†Science Direct. Elsevier., vol. 13 pp 977-984, 2018.

L. Breiman, “Random forestâ€, Machine learning, vol. 45, pp. 5-32, 2001.

T. Hastie, et. al, The Element of Statistical Learning Data Mining, Inference, and Prediction, California: Springer, 2008.

K. M. Ting, "Confusion Matrix," in Encyclopedia of Machine Learning and Data Mining, C. Sammut and G. I. Webb Eds. Boston, MA: Springer US, 2017, pp. 260-260.

Z. Rustam and G. S. Saragih, “Predict bank financial failures using random forest,†IEEE. Available: doi: 10.1109/IWBIS.2018.8471718.2018



  • There are currently no refbacks.

Published by INSIGHT - Indonesian Society for Knowledge and Human Development