Abstract

Endometriosis is a prevalent gynecological disease affecting millions of women worldwide, frequently causing chronic pelvic pain and infertility. Despite the widespread availability of pelvic ultrasound as a non-invasive diagnostic tool, its efficacy remains heavily dependent on examiner expertise, leading to notorious diagnostic delays. To address these limitations, this paper proposes a novel clinical decision support system based on serially organized machine learning models to automate and enhance endometriosis screening. Utilizing a real-world dataset of 7,020 medical exams (comprising 294,983 ultrasound images), it trained two complementary Multi-Layer Perceptron (MLP) expert models— one specialized in the positive class and the other in the negative class—integrated via an OR logic framework to strictly mitigate Type II errors (false negatives). Evaluated on a completely independent, out-of-sample test set of 6,080 exams, the proposed methodology achieved an overall Accuracy of 0.815 and an F1-score of 0.844. Crucially, the system reached a perfect Recall of 1.00, ensuring a complete absence of false negatives, which significantly outclasses existing deep learning baselines and traditional classifiers in the literature. These findings demonstrate that the proposed framework serves as a highly robust, low- and high-risk alert system that can optimize clinical monitoring strategies and enable timely therapeutic interventions.

References

• T. S. Arulananth, S. Wilson Prakash, Ramesh Kumar Ayyasamy, V. P. Kavitha, P. G. Kuppusamy, and P. Chinnasamy. Classification of paediatric pneumonia using modified densenet-121 deep-learning model. IEEE Access, 12:35716–35727, 2024.
• Adrian Balica, Jennifer Dai, Kayla Piiwaa, Xiao Qi, Ashlee N Green, Nancy Phillips, Susan Egan, and Ilker Hacihaliloglu. Augmenting endometriosis analysis from ultrasound data using deep learning. In Medical Imaging 2023: Ultrasonic Imaging and Tomography, volume 12470, pages 118–123. SPIE, 2023.
• Marc Bazot, Clarisse Lafont, Roman Rouzier, Gilles Roseau, Isabelle Thomassin-Naggara, and Emile Daraï. Diagnostic accuracy of physical examination, transvaginal sonography, rectal endoscopic sonography, and magnetic resonance imaging to diagnose deep infiltrating endometriosis. Fertility and sterility, 92(6):1825–1833, 2009.
• Elizabeth V Craig, LeAnn M Shannon, and Rochelle F Andreotti. The complementary role of ultrasound and magnetic resonance imaging in the evaluation of endometriosis: a review. Ultrasound Quarterly, 36(2):123–132, 2020.
• L. Della Corte, C. Di Filippo, O. Gabrielli, S. Reppuccia, V. L. La Rosa, R. Ragusa, M. Fichera, E. Commodari, G. Bifulco, and P. Giampaolino. The burden of endometriosis on women’s lifespan: A narrative overview on quality of life and psychosocial wellbeing. Int J Environ Res Public Health, 17(13):4683, 2020.
• Ping Hu, Yanjuan Gao, Yiqian Zhang, and Kui Sun. Ultrasound image-based deep learning to differentiate tubalovarian abscess from ovarian endometriosis cyst. Frontiers in physiology, 14:1101810, 2023.
• Shikha Khullar, Vignesh Ramamoorthy. H, Sreedhar Kollem, Selvendran Ganesan, S. Kaliappan, and Indla Obulesu. Deepthyroscan:efficientnetb2 architecture for automated thyroid diagnosis. In 2025 IEEE 3rd Global Conference on Wireless Computing and Networking (GCWCN), pages 1–6, 2025.
• Jayashri Kolekar, Chhaya Pawar, Amol Pande, and Chandrashekhar Raut. Deep learning based ovarian cancer classification using efficientnetb2 with attention mechanism. Journal of Electronics, Electromedical Engineering, and Medical Informatics, 8(1):32–52, Nov. 2025.
• Leandro A Mattos, Manoel O Goncalves, Marina P Andres, Scott W Young, Myra Feldman, Mauricio S Abrão, and Rosanne M Kho. Structured ultrasound and magnetic resonance imaging reports for patients with suspected endometriosis: guide for imagers and clinicians, 2019.
• S. A. Missmer, F. F. Tu, S. K. Agarwal, C. Chapron, A. M. Soliman, S. Chiuve, S. Eichner, I. Flores-Caldera, A. W. Horne, A. B. Kimball, M. R. Laufer, N. Leyland, S. S. Singh, H. S. Taylor, and S. As-Sanie. Impact of endometriosis on life-course potential: A narrative review. Int J Gen Med, 14:9– 25, 2021.
• Sneha Mittal, Angela Tong, Scott Young, and Priyanka Jha. Artificial intelligence applications in endometriosis imaging. Abdominal Radiology, 50(10):4901–4913, 2025.
• Kelechi E. Nnoaham, Lone Hummelshoj, Premila Webster, Thomas d’Hooghe, Fiorenzo de Cicco Nardone, Carlo de Cicco Nardone, Crispin Jenkinson, Stephen H. Kennedy, and Krina T. Zondervan. Impact of endometriosis on quality of life and work productivity: a multicenter study across ten countries. Fertility and Sterility, 96(2):366–373.e8, 2011.
• Asif Raza, Mohammed S. Alshehri, Sultan Almakdi, Ali Akbar Siddique, Mohammad Alsulami, and Majed Alhaisoni. Enhancing brain tumor classification with transfer learning: Leveraging densenet121 for accurate and efficient detection. International Journal of Imaging Systems and Technology, 34(1):e22957, 2024.
• Letícia Santos, Mateus de Azevedo, Lia Shimamura, Antonio Nogueira, Francisco Candido dos Reis, Eduardo Schor, Julio Rosa e Silva, Daniel Tiezzi, and Omero Poli-Neto. Machine learning as a clinical decision support tool for diagnosing superficial peritoneal endometriosis in women with dysmenorrhea and acyclic pelvic pain. Medical Research Archives, 12(12), 2024.
• Niranjan Yadav, Rajeshwar Dass, and Jitendra Virmani. A systematic review of machine learning based thyroid tumor characterisation using ultrasonographic images. Journal of Ultrasound, 27(2):209–224, 2024.