PCOS Detection Using Deep Learning and Explainable AI for Ovarian Ultrasound Image Analysis

Author

Chaya C, Amrutha R, Nanditha G

Abstract

 This paper presents a deep learning-based system for detecting Polycystic Ovary Syndrome (PCOS) from ovarian ultrasound images.A fine-tuned MobileNet model classifies images into PCOS and non-PCOS categories using preprocessing and data augmentation.Transfer learning improves the model’s ability to identify relevant image features and generalize to new data.Grad-CAM provides visual explanations by highlighting regions that influence the model’s predictions.The system supports preliminary PCOS screening but does not replace professional medical diagnosis.

Keywords

PCOS, Polycystic Ovary Syndrome, Deep Learning, MobileNet, Transfer Learning, Ultrasound Images, Explainable AI, Grad-CAM.

Full Text:

Download Paper PDF

References

 [1] S. A. Suha and M. N. Islam, “An Extended Machine Learning Technique for Polycystic Ovary Syndrome Detection Using Ovary Ultrasound Image,” Scientific Reports, 2022.

[2] P. Moral, D. Mustafi, A. Mustafi, and S. K. Sahana, “CystNet: An AI Driven Model for PCOS Detection Using Multilevel Thresholding of Ultrasound Images,” Scientific Reports, 2024.

[3] J. Kermanshahchi, A. J. Reddy, J. Xu, G. K. Mehrok, and F. Nausheen, “Development of a Machine Learning-Based Model for Accurate Detection and Classification of Polycystic Ovary Syndrome on Pelvic Ultrasound,” Cureus, 2024.

[4] M. Agirsoy and M. A. Oehlschlaeger, “A Machine Learning Approach for Non-Invasive PCOS Diagnosis from Ultrasound and Clinical Features,” Scientific Reports, 2025.

 [5] G. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” 2017.

[6] R. R. Selvaraju et al., “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization,” 2017.

[7] F. Stein and M. L. Leventhal, “Amenorrhea Associated with Bilateral Polycystic Ovaries,” American Journal of Obstetrics and Gynecology, 1935.

[8] R. Azziz et al., “The Androgen Excess and PCOS Society Criteria for the Polycystic Ovary Syndrome,” Fertility and Sterility, 2009.

[9] H. J. Teede et al., “Recommendations from the International Evidence-Based Guideline for the Assessment and Management of Polycystic Ovary Syndrome,” Clinical Endocrinology, 2018.

[10] C. Gopalakrishnan and M. Iyapparaja, “Active Contour with Modified Otsu Method for Automatic Detection of Polycystic Ovary Syndrome from Ultrasound Image of Ovary,” Multimedia Tools and Applications, 2020.

[11] Pea et al., “Ultrasonographic Criteria in the Diagnosis of Polycystic Ovary Syndrome: A Systematic Review and Diagnostic Meta-Analysis,” Human Reproduction Update, 2024.

[12] Shanmugavadivel et al., “Optimized Polycystic Ovarian Disease Prognosis and Classification Using Based Computational Approaches on Multi-Modality Data,” BMC Medical Informatics and Decision Making, 2024.

[13] D. Bharali, R. Rajendran, J. Goswami, K. Singal, and V. Rajendran, “Prevalence of Polycystic Ovarian Syndrome in India: A Systematic Review and Meta-Analysis,” Cureus, 2022.

[14] A. Ganie et al., “Epidemiology, Pathogenesis, Genetics and Management of Polycystic Ovary Syndrome in India,” Indian Journal of Medical Research, 2019.

[15] V. Y. T. Varshiya and S. B. N. Sanjana, “Automated Detection of Polycystic Ovary Syndrome Using Convolutional Neural Networks on Ultrasound Images,” 2025.

[16] Praneesh, N. Nivetha, S. S. Maidin, and W. Ge, “Optimized Deep Learning Method for Enhanced Medical Diagnostics of Polycystic Ovary Syndrome Detection,” Journal of Applied Data Science, 2024.

[16] Raja and P. Suresh, “Variety of Ovarian Cysts Detection and Classification Using 2D Convolutional Neural Network,” Multimedia Tools and Applications, 2024.

[17] S. Arora, Vedpal, and N. Chauhan, “Polycystic Ovary Syndrome (PCOS) Diagnostic Methods in Machine Learning: A Systematic Literature Review,” Multimedia Tools and Applications, 2024.

 

 

Share your valuable work from Social Media Buttons