Automation of polycystic ovary syndrome diagnostics through machine learning algorithms in ultrasound imaging

• Autorzy: Galagan Roman , Andreiev Serhiy , Stelmakh Nataliia , Rafalska Yaroslava , Momot Andrii

Identyfikatory

DOI

10.35784/acs-2024-24

• Języki publikacji: EN

Abstrakty

EN

This article presents a study aimed at using machine learning to automate the analysis of ultrasound images in the diagnosis of polycystic ovary syndrome (PCOS). Today, various laboratory and instrumental methods are used to diagnose PCOS, including the analysis of ultrasound images performed by medical professionals. The peculiarity of such analysis is that it requires high qualification of medical professionals and can be subjective. The aim of this work is to develop a software module based on convolutional neural networks (CNN), which will improve the accuracy and objectivity of diagnosing polycystic disease as one of the clinical manifestations of PCOS. By using CNNs, which have proven to be effective in image processing and classification, it becomes possible to automate the analysis process and reduce the influence of the human factor on the diagnosis result. The article describes a machine learning model based on CNN architecture, which was proposed by the authors for analyzing ultrasound images in order to determine polycystic disease. In addition, the article emphasizes the importance of the interpretability of the CNN model. For this purpose, the Gradient-weighted Class Activation Mapping (Grad-CAM) visualization method was used, which allows to identify the image areas that most affect the model's decision and provides clear explanations for each individual prediction.

Słowa kluczowe

EN

polycystic ovary syndrome; PCOS; ultrasound imaging; neural networks; gradCAM; Python programming

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2024
• Tom: Vol. 20, no. 2
• Strony: 194--204
• Opis fizyczny: Bibliogr. 47 poz., fig., tab.

Twórcy

autor

Galagan Roman

• Igor Sikorsky Kyiv Polytechnic Institute, Faculty of Instrumentation Engineering, Department of Automation and Non-Destructive Testing Systems, Ukraine

• https://orcid.org/0000-0001-7470-8392

autor

Andreiev Serhiy

• Igor Sikorsky Kyiv Polytechnic Institute, Faculty of Instrumentation Engineering, Department of Automation and Non-Destructive Testing Systems, Ukraine

• https://orcid.org/0009-0007-4314-6017

autor

Stelmakh Nataliia

• Igor Sikorsky Kyiv Polytechnic Institute, Faculty of Instrumentation Engineering, Department of Computer-Integrated Technologies of Device Production, Ukraine

• https://orcid.org/0000-0003-1876-2794

autor

Rafalska Yaroslava

• Bogomolets National Medical University, Pharmaceutical Faculty, Department of Organization and Economy of Pharmacy, Ukraine

• https://orcid.org/0000-0002-1047-3114

autor

Momot Andrii

• Igor Sikorsky Kyiv Polytechnic Institute, Faculty of Instrumentation Engineering, Department of Automation and Non-Destructive Testing Systems, Ukraine

• https://orcid.org/0000-0001-9092-6699

Bibliografia

• [1] Azziz, R. M. D. (2016). Introduction: Determinants of polycystic ovary syndrome. Fertility and Sterility, 106(1), 4-5. https://doi.org/10.1016/j.fertnstert.2016.05.009
• [2] Bulsara, J., Patel, P., Soni, A., & Acharya, S. (2021). A review: Brief insight into Polycystic Ovarian syndrome. Endocrine and Metabolic Science, 3, 100085. https://doi.org/10.1016/j.endmts.2021.100085
• [3] Chai, J., Zeng, H., Li, A., & Ngai, E. W. (2021). Deep Learning in computer vision: A critical review of emerging techniques and application scenarios. Machine Learning with Applications, 6, 100134. https://doi.org/10.1016/j.mlwa.2021.100134
• [4] Chicco, D., & Jurman, G. (2023). The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification. BioData Mining, 16, 4. https://doi.org/10.1186/s13040-023-00322-4
• [5] Chicco, D., Tötsch, N., & Jurman, G. (2021). The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation. BioData Mining, 14, 13. https://doi.org/10.1186/s13040-021-00244-z
• [6] Choudhari, A., & Korde, A. (2022). PCOS detection using ultrasound images. Kaggle. Retrieved 01.03.2024 from https://www.kaggle.com/datasets/anaghachoudhari/PCOS-detection-using-ultrasound-images
• [7] Christ, J., & Cedars, M. (2023). Current guidelines for diagnosing PCOS. Diagnostics, 13(6), 1113. https://doi.org/10.3390/diagnostics13061113
• [8] Deswal, R., Narwal, V., Dang, A., & Pundir, C. S. (2020). The prevalence of polycystic ovary syndrome: A brief review. Journal of human reproductive sciences, 13(4), 261-271. https://doi.org/10.4103/jhrs.jhrs_95_18
• [9] Dwivedi, S., Ujjaliya, M. K., & Kaushik, A. (2019) Assessment of the best predictor for diagnosis of polycystic ovarian disease in color Doppler study of ovarian artery. International Journal of Scientific Study, 6(12), 154-162.
• [10] Esteva, A., Chou, K., Yeung, S., Naik, N., Madani, A., Mottaghi, A., Liu, Y., Topol, E., Dean, J., & Socher, R. (2021). Deep Learning - enabled medical computer vision. npj Digital Medicine, 4, 5. https://doi.org/10.1038/s41746-020-00376-2
• [11] Garad, R. M., & Teede, H. J. (2020). Polycystic ovary syndrome: improving policies, awareness, and clinical care. Current Opinion in Endocrine and Metabolic Research, 12, 112-118. https://doi.org/10.1016/j.coemr.2020.04.007
• [12] Gyliene, A., Straksyte, V. & Zaboriene, I. (2022). Value of ultrasonography parameters in diagnosing polycystic ovary syndrome. Open Medicine, 17(1), 1114-1122. https://doi.org/10.1515/med-2022-0505
• [13] Hassaballah, M., & Awad, A. I. (Eds.). (2020). Deep learning in computer vision: principles and applications. CRC Press Taylor & Francis Group.
• [14] Hoeger, K., Dokras, A., & Piltonen, T. (2021). Update on PCOS: consequences, challenges, and guiding treatment. The Journal of Clinical Endocrinology & Metabolism, 106(3), e1071-e1083. https://doi.org/10.1210/clinem/dgaa839
• [15] Karpiński, R., Krakowski, P., Jonak, J., Machrowska, A., Maciejewski, M., & Nogalski, A. (2022). Diagnostics of articular cartilage damage based on generated acoustic signals using ANN - Part II: Patellofemoral joint. Sensors, 22(10), 3765. https://doi.org/10.3390/s22103765
• [16] Kshatri, S. S., & Singh, D. (2023). Convolutional Neural Network in medical image analysis: A review. Archives of Computational Methods in Engineering, 30, 2793-2810. https://doi.org/10.1007/s11831-023-09898-w
• [17] Liu, J., Wu, Q., Hao, Y., Jiao, M., Wang, X., Jiang, S., & Han, L. (2021). Measuring the global disease burden of polycystic ovary syndrome in 194 countries: Global burden of disease study 2017. Human Reproduction, 36(4), 1108-1119. https://doi.org/10.1093/humrep/deaa371
• [18] Rasquin, L. I., Anastasopoulou, C., & Mayrin, J. V. (2022). Polycystic ovarian disease. StatPearls.
• [19] Rotterdam ESHRE/ASRM-Sponsored PCOS Consensus Workshop Group. (2004). Revised 2003 consensus on diagnostic criteria and long-term health risks related to polycystic ovary syndrome. Fertility and sterility, 81(1), 19-25. https://doi.org/10.1016/j.fertnstert.2003.10.004
• [20] Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020). Grad-CAM: Visual explanations from deep networks via gradient-based localization. International Journal of Computer Vision, 128, 336-359. https://doi.org/10.1007/s11263-019-01228-7
• [21] Sirmans, S. M., & Pate, K. A. (2013). Epidemiology, diagnosis, and management of polycystic ovary syndrome. Clinical epidemiology, 6, 1-13. https://doi.org/10.2147/CLEP.S37559
• [22] Teede, H. J., Misso, M. L., Costello, M. F., Dokras, A., Laven, J., Moran, L., Piltonen, T., & Norman, R. J. (2018). Recommendations from the international evidence-based guideline for the assessment and management of polycystic ovary syndrome. Clinical endocrinology, 89(3), 251-268. https://doi.org/10.1111/cen.13795
• [23] World Health Organization. (2023). Polycystic ovary syndrome. Retrieved 01.03.2024 from: https://www.who.int/news-room/fact-sheets/detail/polycystic-ovary-syndrome
• [24] Yamashita, R., Nishio, M., Do, R. K. G., & Togashi, K. (2018). Convolutional neural networks: an overview and application in radiology. Insights into Imaging, 9, 611-629. https://doi.org/10.1007/s13244-018-0639-9 Azziz, R. M. D. (2016). Introduction: Determinants of polycystic ovary syndrome. Fertility and Sterility, 106(1), 4-5. https://doi.org/10.1016/j.fertnstert.2016.05.009
• [25] Bulsara, J., Patel, P., Soni, A., & Acharya, S. (2021). A review: Brief insight into Polycystic Ovarian syndrome. Endocrine and Metabolic Science, 3, 100085. https://doi.org/10.1016/j.endmts.2021.100085
• [26] Chai, J., Zeng, H., Li, A., & Ngai, E. W. (2021). Deep Learning in computer vision: A critical review of emerging techniques and application scenarios. Machine Learning with Applications, 6, 100134. https://doi.org/10.1016/j.mlwa.2021.100134
• [27] Chicco, D., & Jurman, G. (2023). The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification. BioData Mining, 16, 4. https://doi.org/10.1186/s13040-023-00322-4
• [28] Chicco, D., Tötsch, N., & Jurman, G. (2021). The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation. BioData Mining, 14, 13. https://doi.org/10.1186/s13040-021-00244-z
• [29] Choudhari, A., & Korde, A. (2022). PCOS detection using ultrasound images. Kaggle. Retrieved 01.03.2024 from https://www.kaggle.com/datasets/anaghachoudhari/PCOS-detection-using-ultrasound-images
• [30] Christ, J., & Cedars, M. (2023). Current guidelines for diagnosing PCOS. Diagnostics, 13(6), 1113. https://doi.org/10.3390/diagnostics13061113
• [31] Deswal, R., Narwal, V., Dang, A., & Pundir, C. S. (2020). The prevalence of polycystic ovary syndrome: A brief review. Journal of human reproductive sciences, 13(4), 261-271. https://doi.org/10.4103/jhrs.jhrs_95_18
• [32] Dwivedi, S., Ujjaliya, M. K., & Kaushik, A. (2019) Assessment of the best predictor for diagnosis of polycystic ovarian disease in color Doppler study of ovarian artery. International Journal of Scientific Study, 6(12), 154-162.
• [33] Esteva, A., Chou, K., Yeung, S., Naik, N., Madani, A., Mottaghi, A., Liu, Y., Topol, E., Dean, J., & Socher, R. (2021). Deep Learning - enabled medical computer vision. npj Digital Medicine, 4, 5. https://doi.org/10.1038/s41746-020-00376-2
• [34] Garad, R. M., & Teede, H. J. (2020). Polycystic ovary syndrome: improving policies, awareness, and clinical care. Current Opinion in Endocrine and Metabolic Research, 12, 112-118. https://doi.org/10.1016/j.coemr.2020.04.007
• [35] Gyliene, A., Straksyte, V. & Zaboriene, I. (2022). Value of ultrasonography parameters in diagnosing polycystic ovary syndrome. Open Medicine, 17(1), 1114-1122. https://doi.org/10.1515/med-2022-0505
• [36] Hassaballah, M., & Awad, A. I. (Eds.). (2020). Deep learning in computer vision: principles and applications. CRC Press Taylor & Francis Group.
• [37] Hoeger, K., Dokras, A., & Piltonen, T. (2021). Update on PCOS: consequences, challenges, and guiding treatment. The Journal of Clinical Endocrinology & Metabolism, 106(3), e1071-e1083. https://doi.org/10.1210/clinem/dgaa839
• [38] Karpiński, R., Krakowski, P., Jonak, J., Machrowska, A., Maciejewski, M., & Nogalski, A. (2022). Diagnostics of articular cartilage damage based on generated acoustic signals using ANN - Part II: Patellofemoral joint. Sensors, 22(10), 3765. https://doi.org/10.3390/s22103765
• [39] Kshatri, S. S., & Singh, D. (2023). Convolutional Neural Network in medical image analysis: A review. Archives of Computational Methods in Engineering, 30, 2793-2810. https://doi.org/10.1007/s11831-023-09898-w
• [40] Liu, J., Wu, Q., Hao, Y., Jiao, M., Wang, X., Jiang, S., & Han, L. (2021). Measuring the global disease burden of polycystic ovary syndrome in 194 countries: Global burden of disease study 2017. Human Reproduction, 36(4), 1108-1119. https://doi.org/10.1093/humrep/deaa371
• [41] Rasquin, L. I., Anastasopoulou, C., & Mayrin, J. V. (2022). Polycystic ovarian disease. StatPearls.
• [42] Rotterdam ESHRE/ASRM-Sponsored PCOS Consensus Workshop Group. (2004). Revised 2003 consensus on diagnostic criteria and long-term health risks related to polycystic ovary syndrome. Fertility and sterility, 81(1), 19-25. https://doi.org/10.1016/j.fertnstert.2003.10.004
• [43] Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020). Grad-CAM: Visual explanations from deep networks via gradient-based localization. International Journal of Computer Vision, 128, 336-359. https://doi.org/10.1007/s11263-019-01228-7
• [44] Sirmans, S. M., & Pate, K. A. (2013). Epidemiology, diagnosis, and management of polycystic ovary syndrome. Clinical epidemiology, 6, 1-13. https://doi.org/10.2147/CLEP.S37559
• [45] Teede, H. J., Misso, M. L., Costello, M. F., Dokras, A., Laven, J., Moran, L., Piltonen, T., & Norman, R. J. (2018). Recommendations from the international evidence-based guideline for the assessment and management of polycystic ovary syndrome. Clinical endocrinology, 89(3), 251-268. https://doi.org/10.1111/cen.13795
• [46] World Health Organization. (2023). Polycystic ovary syndrome. Retrieved 01.03.2024 from: https://www.who.int/news-room/fact-sheets/detail/polycystic-ovary-syndrome
• [47] Yamashita, R., Nishio, M., Do, R. K. G., & Togashi, K. (2018). Convolutional neural networks: an overview and application in radiology. Insights into Imaging, 9, 611-629. https://doi.org/10.1007/s13244-018-0639-9