An optimized deep neural network and transfer learning approaches for endometriosis classification

An optimized deep neural network and transfer learning approaches for endometriosis classification DOI: https://doi.org/10.65752/eq1tse55Keywords: Endometriosis, Larascopy ResNet50V2, MobileNet, VGG16,, Transfer Learning, ClassificationAbstract The prevalence of endometriosis is underestimated because of the need for laparoscopy an invasive diagnostic method, which is considered the gold standard. Advanced stages of endometriosis may lead to endometrial cancer, infertility, psychological depression, leading to further complications. Endometriosis has multiple appearances; the lesions may be confused with other non-endometriotic lesions or endometriotic lesions that are non-endometriotic by appearance, or deep infiltrating ones may be missed on visual diagnosis. Therefore, this research aims to develop an endometriosis prediction by utilizing four different deep and transfer learning architecture including CNN, RestNet101V2, MobileNet, and VGG16 The proposed model employs Pelican Optimization Algorithm (POA) to extract predominant features for CNN, ResNet101V2, MobileNet, and VGG16 endometriosis classification. Image Dataset was obtained from Gynecologic Laparoscopy Endometriosis (GLENDA) repository containing 25,683 sample laparoscopic images of both pathological and non-pathological identified endometriosis regions. The experimental analysis revealed that POA_ResNet101V2, POA_MobileNet, and POA_VGG16 perform significantly better than CNN during the classification of endometriosis (pathology and non-pathology). Betterstill, MobileNet achieved a general accuracy of 100%, precision 99.5%, Recall 99.5%, and F1-score of 100%. The model demonstrates the effectiveness of transfer learning, MobileNet better than other transfer Learning in the existing studies. To address the diagnostic challenges of endometriosis, this study developed an optimized endometriosis prediction model with deep and transfer learning techniques, perform comparative analysis on the developed model and benchmark the results with existing ones. This model will assist health practitioners to early detect endometriosis and proffer appropriate solutions for patients. Downloads References 1. Ghiasi, Marzieh, Madhavi Thombre Kulkarni, and Stacey A. Missmer. "Is endometriosis more common and more severe than it was 30 years ago?." Journal of minimally invasive gynecology 27, no. 2 (2020): 452-461. 2. K. Dagar and H. D. Ramteke, “Endometriosis: A systemic review,” Feb. 2023, doi: https://doi.org/10.13140/RG.2.2.27664.28164. 3. B. Smolarz, K. Szyłło, and H. Romanowicz, “Endometriosis: Epidemiology, Classification, Pathogenesis, Treatment and Genetics (Review of Literature),” International Journal of Molecular Sciences, vol. 22, no. 19, p. 10554, Sep. 2021, doi: https://doi.org/10.3390/ijms221910554. 4. J. Maddern, L. Grundy, J. Castro, and S. M. Brierley, “Pain in Endometriosis,” Frontiers in Cellular Neuroscience, vol. 14, no. 14, Oct. 2020, doi: https://doi.org/10.3389/fncel.2020.590823. 5. A. Goldstein and S. Cohen, “Self-report symptom-based endometriosis prediction using machine learning,” Scientific Reports, vol. 13, no. 1, Apr. 2023, doi: https://doi.org/10.1038/s41598-023-32761-8. 6. V. Kaul, S. Enslin, and S. A. Gross, “History of artificial intelligence in medicine,” Gastrointestinal Endoscopy, vol. 92, no. 4, pp. 807–812, Oct. 2020, doi: https://doi.org/10.1016/j.gie.2020.06.040. 7. D. Dahiwade, G. Patle, and E. Meshram, “Designing Disease Prediction Model Using Machine Learning Approach,” IEEE Xplore, Mar. 01, 2019. https://ieeexplore.ieee.org/document/8819782 8. K. Pingale, S. Surwase, V. Kulkarni, S. Sarage, and Prof. A. Prof. Abhijeet, “Disease Prediction Using Machine Learning,” International Research Journal of Engineering and Technology (IRJET), vol. 06, no. 12, pp. 831–833, Dec. 2019. 9. M. El-flahgy, W. El-Bassioune, and W. Ayad, “Incidence of Endometriosis among Women Prepared for Laparoscopy in Unexplained Infertility and Chronic Pelvic Pain,” International Journal of Medical Arts, vol. 0, no. 0, Jun. 2020, doi: https://doi.org/10.21608/ijma.2020.22163.1080. 10. S. A. Missmer et al., “Impact of Endometriosis on Life-Course Potential: a Narrative Review,” International Journal of General Medicine, vol. Volume 14, no. 14, pp. 9–25, Jan. 2021, doi: https://doi.org/10.2147/ijgm.s261139. 11. S. Simoens, L. Hummelshoj, and T. D’Hooghe, “Endometriosis: cost estimates and methodological perspective,” Human Reproduction Update, vol. 13, no. 4, pp. 395–404, Jul. 2007, doi: https://doi.org/10.1093/humupd/dmm010. 12. J. V. Cardoso et al., “Epidemiological profile of women with endometriosis: a retrospective descriptive study,” Revista Brasileira de Saúde Materno Infantil, vol. 20, no. 4, pp. 1057–1067, Dec. 2020, doi: https://doi.org/10.1590/1806-93042020000400008. 13. S. Swain and P. K. Jena, “Diagnostic and Therapeutic Laparoscopy in the Management of Endometriosis,” International Journal of Reproduction, Contraception, Obstetrics and Gynecology, vol. 7, no. 11, p. 4695, Oct. 2018, doi: https://doi.org/10.18203/2320-1770.ijrcog20184532. 14. C. Nezhat and Schipper, “Video-assisted Laparoscopy for the Detection and Diagnosis of endometriosis: safety, reliability, and Invasiveness,” International Journal of Women’s Health, p. 383, Jul. 2012, doi: https://doi.org/10.2147/ijwh.s24948. 15. G. Eleje, “Endometriosis Seen at Diagnostic Laparoscopy for Women with Infertility,” Journal of Gynecological Research and Obstetrics, vol. 1, no. 1, pp. 006–009, Aug. 2015, doi: https://doi.org/10.17352/jgro.000002. 16. S Visalaxi and T Sudalai Muthu, “Automated prediction of endometriosis using deep learning,” vol. 12, no. 2, pp. 2403–2416, Jul. 2021, doi: https://doi.org/10.22075/ijnaa.2021.5383. 17. X.-X. Yin, L. Sun, Y. Fu, R. Lu, and Y. Zhang, “U-Net-Based Medical Image Segmentation,” Journal of Healthcare Engineering, vol. 2022, p. 4189781, Apr. 2022, doi: https://doi.org/10.1155/2022/4189781. 18. S. Dargan, M. Kumar, M. R. Ayyagari, and G. Kumar, “A Survey of Deep Learning and Its Applications: A New Paradigm to Machine Learning,” Archives of Computational Methods in Engineering, Jun. 2019, doi: https://doi.org/10.1007/s11831-019-09344-w. 19. A. Sabat-Tomala, E. Raczko, and B. Zagajewski, “Comparison of Support Vector Machine and Random Forest Algorithms for Invasive and Expansive Species Classification Using Airborne Hyperspectral Data,” Remote Sensing, vol. 12, no. 3, p. 516, Feb. 2020, doi: https://doi.org/10.3390/rs12030516. 20. V. Sankaravadivel and S. Thalavaipillai, “Symptoms based endometriosis prediction using machine learning,” Bulletin of Electrical Engineering and Informatics, vol. 10, no. 6, pp. 3102–3109, Dec. 2021, doi: https://doi.org/10.11591/eei.v10i6.3254. 21. A. Goldstein and S. Cohen, “Self-report symptom-based endometriosis prediction using machine learning,” Scientific Reports, vol. 13, no. 1, Apr. 2023, doi: https://doi.org/10.1038/s41598-023-32761-8. 22. A. Balica et al., “Augmenting endometriosis analysis from ultrasound data using deep learning,” Apr. 2023, doi: https://doi.org/10.1117/12.2653940. 23. S. Visalaxi and T. Sudalaimuthu, “Automated segmentation of endometriosis using transfer learning technique,” F1000Research, vol. 11, p. 360, Mar. 2022, doi: https://doi.org/10.12688/f1000research.110283.1. 24. A. Leibetseder, K. Schoeffmann, J. Keckstein, and S. Keckstein, “Endometriosis detection and localization in laparoscopic gynecology,” Multimedia Tools and Applications, vol. 81, no. 5, pp. 6191–6215, Jan. 2022, doi: https://doi.org/10.1007/s11042-021-11730-1. 25. P. Hu, Y. Gao, Y. Zhang, and K. Sun, “Ultrasound image-based deep learning to differentiate tubal-ovarian abscess from ovarian endometriosis cyst,” Frontiers in Physiology, vol. 14, Feb. 2023, doi: https://doi.org/10.3389/fphys.2023.1101810. 26. F. S. Nahm, “Receiver Operating Characteristic curve: Overview and Practical Use for Clinicians,” Korean Journal of Anesthesiology, vol. 75, no. 1, pp. 25–36, Feb. 2022, doi: https://doi.org/10.4097/kja.21209. 27. H. Zhang, “Machine Vision: A Comprehensive Analysis of Techniques, Applications, and Challenges,” Highlights in science, engineering and technology, vol. 71, pp. 299–304, Nov. 2023, doi: https://doi.org/10.54097/hset.v71i.13050. 28. M. Rahimzadeh and A. Attar, “A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2,” Informatics in Medicine Unlocked, vol. 19, p. 100360, 2020, doi: https://doi.org/10.1016/j.imu.2020.100360. 29. Djarot Hindarto, “Use ResNet50V2 Deep Learning Model to Classify Five Animal Species,” Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi), vol. 7, no. 4, pp. 758–768, Dec. 2023, doi: https://doi.org/10.35870/jtik.v7i4.1845. 30. Nisnab Udas, F. Beuth, and D. Kowerko, “Concept Detection in Medical Images using Xception Models - TUCMC at ImageCLEFmed 2020.,” CLEF (Working Notes), Jan. 2020. 31. X. Yu, N. Zeng, S. Liu, and Y.-D. Zhang, “Utilization of DenseNet201 for diagnosis of breast abnormality,” Machine Vision and Applications, vol. 30, no. 7–8, pp. 1135–1144, Jul. 2019, doi: https://doi.org/10.1007/s00138-019-01042-8. 32. R. Anand, V. Sowmya, Vijaykrishnamenon, E. A. Gopalakrishnan, And K. P. Soman, “Modified Vgg Deep Learning Architecture For Covid-19 Classification Using Bio-Medical Images,” IOP Conference Series: Materials Science and Engineering, vol. 1084, no. 1, p. 012001, Mar. 2021, doi: https://doi.org/10.1088/1757-899x/1084/1/012001. 33. Ikegwu, A. C., Onyilo, J., & Nweke, H. F. (2025). Artificial intelligence-based clinical decision support systems: enhancing modern healthcare for smart diagnosis and prognosis. Nat J Emerging Sci Technol Innovations, 1(1), 17-34. 34. Lee, S. Y., Koo, Y. J., & Lee, D. H. (2021). Classification of endometriosis. Yeungnam University journal of medicine, 38(1), 10-18. 35. Pašalić, E., Tambuwala, M. M., & Hromić-Jahjefendić, A. (2023). Endometriosis: Classification, pathophysiology, and treatment options. Pathology-Research and Practice, 251, 154847. 36. Condous, G., Gerges, B., Thomassin-Naggara, I., Becker, C. M., Tomassetti, C., Krentel, H., ... & Hudelist, G. (2024). Non-invasive imaging techniques for diagnosis of pelvic deep endometriosis and endometriosis classification systems: an International Consensus Statement. Human Reproduction Open, 2024(3), hoae029. 37. Keckstein, J., & Hudelist, G. (2021). Classification of deep endometriosis (DE) including bowel endometriosis: From r-ASRM to# Enzian-classification. Best practice & research Clinical obstetrics & gynaecology, 71, 27-37. 38. Missmer, S., Abrao, M. S., Einarsson, J. I., Horne, A. W., ... & De Wilde, R. L. (2022). International Working Group of AAGL, ESGE, ESHRE and WES, Zondervan, K. T., Endometriosis classification systems: an international survey to map current knowledge and uptake. Human Reproduction Open, 2022(1), hoac002. 39. Bazot, Marc, Emile Daraï, Giuseppe P. Benagiano, Caroline Reinhold, Amelia Favier, Horace Roman, Jacques Donnez, and Sofiane Bendifallah. "ENDO_STAGE magnetic resonance imaging: classification to screen endometriosis." Journal of clinical medicine 11, no. 9 (2022): 2443. 40. Maciel, C., Ferreira, H., Djokovic, D., Kyaw Tun, J., Keckstein, J., Rizzo, S., & Manganaro, L. (2023). MRI of endometriosis in correlation with the# Enzian classification: applicability and structured report. Insights into Imaging, 14(1), 120 Downloads Published Data Availability Statement Nil Issue Section License Copyright (c) 2026 Opeyemi Aderiike Abisoye, Ruth Ailoyafen, Solomon Adelowo Adepoju, Blessing Olatunde Abisoye, Oladayo Tosin Akinwande, Ikouwen Ufort Usoh (Author) This work is licensed under a Creative Commons Attribution 4.0 International License. This is an open-access article distributed under a CC BY license (Creative Commons Attribution 4.0 International License) https://creativecommons.org/licenses/by/4.0/