Control Systems and Computers

Control Systems and Computers, 2024, Issue 2 (306), pp.

UDK 004.8 + 004.932    

Ursu Ihor O., student, National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”, 37 Beresteyskyi Avenue, Kyiv 03056, Ukraine, bs02‑uio‑fbmi24@lll.kpi.ua,

Budnik Yulia S., student, National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”, 37 Beresteyskyi Avenue, Kyiv 03056, Ukraine, bs03‑bys‑fbmi24@lll.kpi.ua,

Shevchenko Oleksandr O., student, National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”, 37 Beresteyskyi Avenue, Kyiv 03056, Ukraine, bs03‑soo‑fbmi24@lll.kpi.ua,

Dyba Maryna B., PhD, senior researcher at the department of hepatology and comorbidities in children, state institution ‘Institute of paediatrics, obstetrics and gynaecology of the National Academy of Medical Sciences of Ukraine’, 8 Platon Maiboroda str., Kyiv 04050, Ukraine, marina_dyba@ukr.net,

Tarasyuk Boris A., doctor of medicine, senior researcher at the ‘Institute for Nuclear Medicine and Radiation Diagnostics of the National Academy of Medical Sciences of Ukraine’, 32 Platon Maiboroda str., Kyiv 04050, Ukraine, btarasyuk13@gmail.com, https://orcid.org/0000‑0003‑4051‑9707,

Pavlov Volodymyr A., PhD, Аs. Рrof, National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”, 37 Beresteyskyi Avenue, Kyiv 03056, Ukraine, pavlov.volodymyr@lll.kpi.ua, https://orcid.org/0000-0002-3293-5308

SYSTEM FOR THE LIVER FIBROSIS STAGE DETERMINATION IN CHILDREN WITH AUTOIMMUNE HEPATITIS USING ULTRASOUND IMAGES

Introduction. Diffuse diseases are the most numerous class of liver diseases. Among them, autoimmune hepatitis stands out for its severe course in children. Its timely diagnosis and assessment of the degree of liver damage is an integral part of a patient’s personalised treatment strategy. The lack of reliable non-invasive methods for assessing liver disease affects the quality of medical services. Therefore, the search for informative signs of liver damage in ultrasound images and the improvement of methods for solving multi-class classification problems are relevant areas for the development of non-invasive systems for determining the degree of liver fibrosis.

Purpose. Improve the diagnosis of liver fibrosis stages through a multi-level classification system.

Methods. A system for classifying the detailed degree of fibrosis (eight classes) based on neural networks according to the state of the blood vessels in ultrasound images of the liver is proposed and substantiated: the first level is a fibrosis degrees group classification of fibrosis degree for regions of interest by convolutional neural networks, the second level is the classification of fibrosis individual degrees for regions of interest by a deep neural network, the third level is the integration of the second level results to obtain conclusions about the patient (image) as a whole.  In order to optimize the feature space, we have performed an exploratory analysis using a logistic multivariate regression model optimized by the Group Method of Data Handling. The resulting set of generalized variables formed the meta-feature space for the second level of the system. A twofold increase in the quality of the system’s classification is shown in comparison with solving the task of image classification by a single convolutional network with an output of eight classes.

Results. Improved version of the hierarchical system for solving multiclass problems based on the use of ANNs is proposed. The system implements the classification of the detailed degree of liver fibrosis in children with autoimmune hepatitis using ultrasound images characterizing the state of liver vessels. The use of a hierarchical classification system allowed us to obtain a classification accuracy of 32.61% higher than the use of a standard multi-class classifier based on a convolutional neural network. The classification accuracy of the hierarchical system: at the first level – 32.46%; at the second level – 50.43%; at the third level – 65.22%.

Conclusion. The article proposes, substantiates and develops a hierarchical classification system based on convolutional neural networks. Its use makes it possible to increase the accuracy of classification of the detailed degree of liver fibrosis by 2 times compared to the standard multi-class classifier based on СNNs. The main source of further improvement of the classification accuracy of the system should be a combination of signs of vascular deformation and texture features that can be obtained with different ultrasound imaging modes. The developed system offers new opportunities for improving methods for solving multiclass classification problems based on image analysis.

Download full text! (On Ukrainian)

Keywords: convolutional neural networks, multi-level system, group classification, GMDH, logistic regression, exploratory analysis, liver fibrosis, ultrasound images.

1. Poynard, T., Imbert-Bismut, F., Ratziu, V., Chevret, S., Jardel, C., Moussalli, J., Messous, D., Degos, F., & GERMED cyt04 group (2002). Biochemical markers of liver fibrosis in patients infected by hepatitis C virus: longitudinal validation in a randomized trial. Journal of viral hepatitis, 9(2), 128–133. https://doi.org/10.1046/j.1365-2893.2002.00341.x
2. Kuroda, H., Abe, T., Kakisaka, K., Fujiwara, Y., Yoshida, Y., Miyasaka, A., Ishida, K., Ishida, H., Sugai, T., & Takikawa, Y. (2016). Visualizing the hepatic vascular architecture using superb microvascular imaging in patients with hepatitis C virus: A novel technique. World journal of gastroenterology, 22(26), 6057–6064. https://doi.org/10.3748/wjg.v22.i26.6057
3. Koyama, N., Hata, J., Sato, T., Tomiyama, Y., & Hino, K. (2017). Assessment of hepatic fibrosis with superb microvascular imaging in hepatitis C virus-associated chronic liver diseases. Hepatology research : the official journal of the Japan Society of Hepatology, 47(6), 593–597. https://doi.org/10.1111/hepr.12776
4. Lee, J. H., Joo, I., Kang, T. W., Paik, Y. H., Sinn, D. H., Ha, S. Y., Kim, K., Choi, C., Lee, G., Yi, J., & Bang, W. C. (2020). Deep learning with ultrasonography: automated classification of liver fibrosis using a deep convolutional neural network. European radiology, 30(2), 1264–1273. https://doi.org/10.1007/s00330-019-06407-1
5. Nastenko, O. Nosovets, V. Babenko, M. Dyba, V. Maksymenko, B. Tarasiuk, V. Kruhlyi, V. Umanets, I. Dykan, V. Pavlov, V. Soloduschenko. Liver Pathological States Identification in Diffuse Diseases with Self-Organization Models Based on Ultrasound Images Texture Features. 2020 IEEE 15th International Conference on Computer Sciences and Information Technologies (CSIT), Zbarazh Castle, UKRAINE, 23-26 September, 2020 – 314 p. / pp. 21-26,   e-ISSN: 2766-3639 – https://link.springer.com/chapter/10.1007/978-3-030-63270-0_26.
6. Meng, L. Zhang, G. Cao, W. Cao, G. Zhang and B. Hu, “Liver Fibrosis Classification Based on Transfer Learning and FCNet for Ultrasound Images,” in IEEE Access, vol. 5, pp. 5804-5810, 2017, doi: 10.1109/ACCESS.2017.2689058, https://ieeexplore.ieee.org/document/7890483.
7. Park, HC., Joo, Y., Lee, OJ. et al. Automated classification of liver fibrosis stages using ultrasound imaging. BMC Med Imaging 24, 36 (2024). https://doi.org/10.1186/s12880-024-01209-4 – https://bmcmedimaging.biomedcentral.com/articles/10.1186/s12880-024-01209-4.
8. Babenko, Ie. Nastenko, V. Solodushenko, V. Pavlov, I. Dykan. Hierarchical algorithm for multiclassification of liver fibrosis stages with integrated region of interest analysis. Biomedical Engineering and Technology. Issue 14 (2024).
9. V. Radchenko, V.A. Pavlov, O.K. Horodetska, G.A. Korniienko. Multiclass classifier based on binary logistic regressions obtained according to the principles of GMDH. Control Systems and Computers – Kyiv, Ukraine. – 2023.  http://usim.org.ua/?page_id=16327&lang=en

Received 14.03.2024