Research on stroke medical image classification based on Wavelet Scattering Network

Zhongying Pei; Zhoule Pei

doi:10.54254/2977-3903/2025.25529

Advances in Engineering InnovationOpen access

Research on stroke medical image classification based on Wavelet Scattering Network

Research Article

Open Access

Research on stroke medical image classification based on Wavelet Scattering Network

Zhongying Pei ^1* Zhoule Pei ²

¹ Tianjin Normal University

² Henan Agriculture University

^*Corresponding author: pzyTJNU@163.com

Published on 23 July 2025

AEI Vol.16 Issue 7

ISSN (Print): 2977-3911

ISSN (Online): 2977-3903

Download Cover

Abstract

Stroke can lead to brain dysfunction and, in severe cases, may result in long-term paralysis, aphasia, or memory impairment, significantly affecting daily life. Acute stroke episodes can be life-threatening and require timely treatment to minimize sequelae. Traditional stroke detection methods are often insensitive to early subtle lesions, prone to misdiagnosis or missed diagnosis, and incapable of real-time dynamic monitoring of disease progression. To overcome these limitations, this study proposes a stroke medical image classification method based on the Wavelet Scattering Network (WSN), aiming to improve the detection of stroke lesions. The WSN classifies medical images through multi-scale wavelet transformation and hierarchical nonlinear operations. The core principle involves first decomposing the image using wavelet filters to extract local features such as multi-scale edges and textures. This is followed by modulus operations to eliminate phase variations and enhance translation invariance, and then layer-by-layer downsampling to compress feature dimensions. Finally, stable low-dimensional feature vectors are generated for classification. The proposed method was applied to Dataset 1 and the stroke dataset from the Teknofest-2021 Medical AI Competition. The results show that the method achieved an accuracy of 88.69% on Dataset 1 and 93.75% on the Teknofest-2021 dataset. Compared with traditional methods such as Convolutional Neural Networks (CNN) and Long Short-Term Memory Networks (LSTM), the proposed approach improves classification accuracy by 7.33%–11.33%. The WSN-based method effectively overcomes the limitations of traditional stroke medical image classification and diagnosis techniques, offering a novel technical approach and solution for this field.

Keywords:

stroke, WSN, medical image, multi-scale wavelet transform, classification accuracy

View PDF

References

[1]. El-Hajj, M., Salameh, P., Rachidi, S., & Hosseini, H. (2016). The epidemiology of stroke in the Middle East.European Stroke Journal, 1(3), 180–198.

[2]. Wu, J., Srinivasan, R., Quinlan, E. B., Solodkin, A., Small, S. L., & Cramer, S. C. (2016). Utility of EEG measures of brain function in patients with acute stroke.Journal of Neurophysiology, 115(5), 2399–2405.

[3]. Nakling, A. E., Aarsland, D., Næss, H., Wollschlaeger, D., Fladby, T., Hofstad, H., & Wehling, E. (2017). Cognitive deficits in chronic stroke patients: Neuropsychological assessment, depression, and self-reports.Dementia and Geriatric Cognitive Disorders Extra, 7(2), 283–296.

[4]. Herzberg, M., Boy, S., Hölscher, T., Ertl, M., Zimmermann, M., Ittner, K. P., Pemmerl, J., Pels, H., Bogdahn, U., & Schlachetzki, F. (2014). Prehospital stroke diagnostics based on neurological examination and transcranial ultrasound.Critical Ultrasound Journal, 6, 1–13.

[5]. Mayya, V., Tummala, V., Reddy, C. U., Mishra, P., Boddu, R., Olivia, D., & Kamath, S. S. (2023). Applications of machine learning in diabetic foot ulcer diagnosis using multimodal images: A review.IAENG International Journal of Applied Mathematics, 53(3).

[6]. Gautam, A., & Raman, B. (2021). Towards effective classification of brain hemorrhagic and ischemic stroke using CNN.Biomedical Signal Processing and Control, 63, 102178.

[7]. Xiao, Y., Yin, H., Wang, S. H., Zhang, Y. D., Yang, J., Liu, C., Zhang, Y., Wang, Q., & Zhang, B. (2021). TReC: Transferred ResNet and CBAM for detecting brain diseases.Frontiers in Neuroinformatics, 15, 781551.

[8]. Alam, A. M., Ahad, A., & Ahmed, S. (2024). Comparative analysis of brain stroke prediction using various pretrained CNN and ViT models. In 2024 IEEE International Conference on Computing, Applications and Systems (COMPAS)(pp. 1–6). IEEE.

[9]. Lai, Y. L., Wu, Y. D., Yeh, H. J., Lee, C. Y., Wang, J. J., & Chiu, H. Y. (2022). Using convolutional neural network to analyze brain MRI images for predicting functional outcomes of stroke.Medical & Biological Engineering & Computing, 60(10), 2841–2849.

[10]. Gautam, A., & Raman, B. (2021). Towards effective classification of brain hemorrhagic and ischemic stroke using CNN.Biomedical Signal Processing and Control, 63, 102178.

[11]. Tahyudin, I., Prabuwono, A. S., Dianingrum, M., Pandega, D. M., Winarto, E., Nazwan, Rozak, R. A., Lestari, P., & Tikaningsih, A. (2024). ResNet-CBAM in medical imaging: A high-accuracy tool for stroke detection from CT scans. In2024 8th International Conference on Information Technology, Information Systems and Electrical Engineering(ICITISEE) (pp. 551–556). IEEE.

[12]. Yopiangga, A. P., Badriyah, T., Syarif, I., & Sakinah, N. (2024). Stroke disease classification using CT scan image with vision transformer method. In2024 International Electronics Symposium (IES)(pp. 436–441). IEEE.

[13]. Sakinah, N., Subhan, M., Saputri, T. B. B., Badriah, T., & Syarif, I. (2024). VGGNet-16 convolutional neural network for classification of stroke based on CT scan images.International Conference on Applied Science and Technology on Engineering Science 2023 (iCAST-ES 2023)(pp. 1138–1150). Atlantis Press.

[14]. Agboola, H. A., & Zaccheus, J. E. (2023). Wavelet image scattering based glaucoma detection.BMC Biomedical Engineering, 5(1), 1.

[15]. Flanders, A. E., Prevedello, L. M., Shih, G., Halabi, S. S., Kalpathy-Cramer, J., Ball, R., Mongan, J. T., Stein, A., Kitamura, F. C., Lungren, M. P., Choudhary, G., Cala, L., Coelho, L., Mogensen, M., Morón, F., Miller, E., Ikuta, I., Zohrabian, V., McDonnell, O., Lincoln, C., Shah, L., Joyner, D., Agarwal, A., Lee, R. K., Nath, J., & RSNA-ASNR 2019 Brain Hemorrhage CT Annotators. (2020). Construction of a machine learning dataset through collaboration: The RSNA 2019 brain CT hemorrhage challenge.Radiology: Artificial Intelligence, 2(3), e190211.

[16]. Koç, U., Akçapınar Sezer, E., Alper Özkaya, Y., et al. (2022). Artificial intelligence in healthcare competition (TEKNOFEST-2021): Stroke data set.Eurasian Journal of Medicine, 54(3), 248–258.

[17]. Lin, C.-L. (2010). A tutorial of the wavelet transform.NTUEE, Taiwan, 21(22), 2.

[18]. Liu, Z., Yao, G., Zhang, Q., Zhang, J., & Zeng, X. (2020). Wavelet scattering transform for ECG beat classification.Computational and Mathematical Methods in Medicine, 2020(1), 3215681.

[19]. Islam, M. M., Akter, S., Rokunojjaman, M., Rony, J. H., & Amin, A. (2021). Stroke prediction analysis using machine learning classifiers and feature technique.International Journal of Electronics and Communications Systems, 1(2), 17–22.

[20]. Yu, Y., Parsi, B., Speier, W., Arnold, C., Lou, M., & Scalzo, F. (2019). LSTM network for prediction of hemorrhagic transformation in acute stroke. InInternational Conference on Medical Image Computing and Computer-Assisted Intervention(pp. 177–185). Cham: Springer International Publishing.

[21]. Huang, Z., & Yu, S. (2024). Intelligent diagnosis and treatment model of hemorrhagic stroke based on graph convolutional neural network. InProceedings of the 2024 International Conference on Smart Healthcare and Wearable Intelligent Devices(pp. 108–114).

[22]. Maya, B. S., & Asha, T. (2017). Segmentation and classification of brain hemorrhage using U-net and CapsNet.Journal of Seybold Report ISSN NO, 2017(1533), 9211.

[23]. Shi, J., Zhao, Y., Xiang, W., Monga, V., Liu, X., & Tao, R. (2021). Deep scattering network with fractional wavelet transform.IEEE Transactions on Signal Processing, 69, 4740–4757.

[24]. Bruna, J., & Mallat, S. (2013). Invariant scattering convolution networks.IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8), 1872–1886.