Enhanced Detection of Polycystic Ovary Syndrome through Optimized CNN Architecture on Ultrasound Data

DOI

10.2991/978-94-6463-787-8_7How to use a DOI?

Keywords

Optimized CNN Model; Segmentation; Discernment; Prognostication

Abstract

Polycystic Ovary Syndrome (PCOS) is a physiological anomaly perturbing a consequential percentage of women of conceiving age. This condition can have symptoms such as abnormal menstrual cycles and ovarian cysts, which can even cause long-term health issues like diabetes, heart diseases and infertility. This paper presents an optimized Convolutional Neural Network (CNN) model that obtains an impressive accuracy of 98.92% in detecting PCOS from ultrasound images, outperforming existing models in the field. The study employs a structured data pre-processing approach, organizing images into infected and non-infected categories with training, validation, and testing splits, alongside data augmentation for enhanced model robustness. An optimized CNN architecture was developed to extract detailed image features through layered convolutional and pooling operations, succeeded by dense feed-forward layers to finalize the classification. The predictor, optimized with negative log loss and accuracy metrics, benefits from early stopping and checkpoint mechanisms to minimize over-fitting. Evaluation through a confusion matrix and further validates our optimized CNN model’s effectiveness, suggesting that this approach could support clinicians in early, accurate PCOS diagnosis, thereby facilitating timely medical intervention.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jaya Naga Sai Harshika Masanam
AU  - Mahammad Firose Shaik
AU  - Appalaraju Chintakayala
AU  - Tameem AnsariShaik
AU  - Lakshmi Sumanth Kancharla
PY  - 2025
DA  - 2025/07/17
TI  - Enhanced Detection of Polycystic Ovary Syndrome through Optimized CNN Architecture on Ultrasound Data
BT  - Proceedings of the Recent Advances in Artificial Intelligence for Sustainable Development (RAISD 2025)
PB  - Atlantis Press
SP  - 64
EP  - 76
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-787-8_7
DO  - 10.2991/978-94-6463-787-8_7
ID  - Masanam2025
ER  -