Automating the Problem of Predicting Cervical Cancer Recurrence using a Conditional Generative Adversarial Network

This paper presents an intelligent model based on the Pix2Pix conditional generative adversarial network that automates the process of predicting the recurrence of cervical malignancy in patients who have not yet undergone surgery. The implemented model accepts a pelvic MRI image as input data and provides an output probability of tumor recurrence and a generated image for the "post-operative" perspective. The presented model differs from its basic analogue by modifying the loss function for the problem conditions and replacing the standard generator with a convolutional neural network U-Net. Since the formulated problem belongs to the class of medical diagnostic tasks, the presence of false negatives of the intelligent model was reduced to zero by slightly increasing the number of false positives. In the process of comparative analysis of prognostic and real postoperative images, it was experimentally proven that the model not only accurately predicts the recurrence of the disease, but also generates almost identical centers of tumor foci and their relative areas on the magnetic resonance tomography image. The feasibility of modifying the basic version of Pix2Pix was confirmed by comparing the results of the two models using common quality metrics – precision, recall and their harmonic mean. The modification developed makes it possible to obtain prediction data in the shortest possible time, allowing it to be used in real-time mode.

1. Globocan 2018: Estimated cancer incidence, mortality and prevalence worldwide in November 2018 [Internet]. URL: http://globocan.iarc.fr

2. Каприн А. Д., Старинский В. В., Шахзадовой А. О. Злокачественные новообразования в России в 2020 г. (заболеваемость и смертность). Москва, Московский научно-исследовательский онкологический институт им. П.А. Герцена – филиал ФГБУ «Национальный медицинский исследовательский центр радиологии» Минздрава России, 2021, 252 с. / Caprin A. D., Starinsky V. V., Shakhzadova A. O. Malignant neoplasms in Russia in 2020 (morbidity and mortality). Moscow, Moscow Research Oncological Institute named after P.A. Herzen. P.A. Herzen - branch of FGBU "National Medical Research Centre of Radiology" of the Ministry of Health of Russia, 2021, 252 p. (In Russian).

3. Тучинов Б.Н., Суворов В., Моторин К.О., Павловский Е.Н., Василькив Л.М., Станкевич Ю.А., Тулупов А.А. Применение алгоритма компьютерного зрения для определения очагов демиелинизации при рассеянном склерозе на МРТ-изображениях. Сибирский научный медицинский журнал. 2024;44(1):107-115. DOI: 10.18699/SSMJ20240111 / Tuchinov B.N., Suvorov V., Motorin K.O., Pavlovsky E.N., Vasilkiv L.M., Stankevich Yu.A., Tulupov A.A. Application of a computer vision algorithm to identify foci of demyelination in multiple sclerosis on MRI images. Сибирский научный медицинский журнал. 2024;44(1):107-115. (In Russian). DOI: 10.18699/SSMJ20240111

4. Агафонова Ю. Д., Гайдель А. В., Зельтер П. М., Капишников А. В. Эффективность алгоритмов машинного обучения и свёрточной нейронной сети для обнаружения патологических изменений на магнитно-резонансных томограммах головного мозга. Самара, ФНИЦ «Кристаллография и Фотоника» РАН, Компьютерная оптика, 2020, Т. 44, № 2, С. 266-273. DOI: 10.18287/2412-6179-CO-671. / Agafonova Y. D., Gaidel A. V., Zelter P. M., Kapishnikov A. V. Effectiveness of machine learning algorithms and convolutional neural network for detection of pathological changes on brain magnetic resonance tomograms. V. Effectiveness of machine learning algorithms and convolutional neural network for detection of pathological changes on magnetic resonance tomograms of the brain. Samara, FNIC "Crystallography and Photonics" RAS, Computer Optics, 2020, Vol. 44, No. 2, P. 266-273. (in Russian). DOI: 10.18287/2412-6179-CO-671.

5. Rumala D. J. How You Split Matters: Data Leakage and Subject Characteristics Studies in Longitudinal Brain MRI Analysis. CLIP EPIMI FAIMI 2023 2023 2023. Lecture Notes in Computer Science, vol 14242. Springer, Cham., 235-245 pp. DOI: 10.1007/978-3-031-45249-9_23.

6. Zhu Y., Zhou Z., Liao G., Yang Q., Yuan K. The Method of Multimodal MRI Brain Image Segmentation Based on Differential Geometric Features. arXiv: 1811.04281. 2018. URL: https://arxiv.org/abs/1811.04281

7. Теплякова А. Р., Старков С. О. Применение компьютерного зрения для диагностики нозологических единиц по медицинским снимкам. Барнаул, Южно-Сибирский научный вестник, 2022, № 4(44), С. 134-148. DOI: 10.25699/SSSB.2022.44.4.004. / Teplyakova A. R., Starkov S. О. Application of computer vision for diagnostics of nosological units on medical images. Barnaul, South Siberian Scientific Bulletin, 2022, No. 4(44), P. 134-148. (in Russian). DOI: 10.25699/SSSB.2022.44.4.004.

8. Zalevskyi V., Sanchez T., Roulet M., Verddera J. A., Hutter J., Kebiri H., Cuadra M. B. Improving cross-domain brain tissue segmentation in fetal MRI with synthetic data. arXiv: 2403.15103. 2024. URL:https://arxiv.org/abs/2403.15103

9. Филиппенко Е. В., Жолдыбай Ж. Ж. Возможности магнитно-резонансной томографии в диагностике ретинобластомы. Алматы, Казахский научно-исследовательский институт онкологии и радиологии, Онкология и радиология Казахстана, 2018, № 4(50), С. 47-49. / Filippenko E. V., Zholdybay J. J. Possibilities of magnetic resonance imaging in the diagnosis of retinoblastoma. Almaty, Kazakh Research Institute of Oncology and Radiology, Oncology and Radiology of Kazakhstan, 2018, No. 4(50), P. 47-49. (in Russian).

10. Исмаилова М. Х., Ибрагимова Ш. У., Хайдарова Г. Б. Компьютерная и магнитно-резонансная томография в диагностике рака поджелудочной железы. London, European research: innovation in science, education and technology: Collection of scientific articles ХLV International scientific and practical conference, 2018, С. 55-57. / Ismailova M. H., Ibragimova Sh. U., Haidarova G. B. Computer and magnetic resonance imaging in the diagnosis of pancreatic cancer. London, European research: innovation in science, education and technology: Collection of scientific articles XLV International scientific and practical conference, 2018, P. 55-57. (in Russian).

11. Солопова А. Е., Носова Ю. В., Бендженова Б. Б. Магнитно-резонансная томография при раке шейки матки: современные возможности радиомного анализа и перспективы развития методики. Акушерство, Гинекология и Репродукция. 2023;17(4):500-511. DOI: 10.17749/2313-7347/ob.gyn.rep.2023.440 / Solopova A. E., Nosova J. V., Bendzhenova B. B. Magnetic resonance imaging in cervical cancer: current opportunities of radiomics analysis and prospects for its further developmen. Obstetrics, Gynecology and Reproduction. 2023;17(4):500-511. (In Russian). DOI: 10.17749/2313-7347/ob.gyn.rep.2023.440.

12. Тарачкова Е. В., Стрельцова О. Н., Панов О. В., Базаева И. Я., Тюрин И. Е. Мультипараметрическая магнитно-резонансная томография в диагностике рака шейки матки. Вестник рентгенологии и радиологии. 2015;(6):43-55. DOI: 10.20862/0042-4676-2015-0-6-43-55 / Tarachkova E. V., Strel’tsova O. N., Panov V. O., Bazaeva I. Ya., Tyurin I. E. Multiparameter magnetic resonance imaging in the diagnosis of cancer of the cervix uteri. Journal of radiology and nuclear medicine. 2015;(6):43-55. (In Russian). DOI: 10.20862/0042-4676-2015-0-6-43-55.

13. Isola P., Zhou T. et al. Image-to-Image Translation with Conditional Adversarial Networks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, 15 p. DOI: 10.1109/CVPR.2017.632.

14. Chen L.-C., Papandreou G., Kokkinos I., Murphy K., and Yuille A. L. Semantic image segmentation with deep convolutional nets and fully connected crfs. In ICLR, 2015. DOI: 10.1109/TPAMI.2017.2699184.

15. Mehdi M., Simon O. Conditional Generative Adversarial Nets. arXiv:1411.1784. 2014. URL: http://arxiv.org/abs/1411.1784

16. Diederik P. Kingma B. and Jimmy B. Adam: A Method for Stochastic Optimization. arXiv:1412.6980. 2017. URL: https://arxiv.org/abs/1412.6980

17. Wang T.-C., Liu M.-Y., Zhu J.-Y., Tao A., Kautz J., et al. High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs. In Proc. IEEE CVPR. Salt Lake City, UT, USA, June 2018, pp. 8798–8807. DOI: 10.1109/CVPR.2018.00917.