SonoCyst-Net: Deep Learning-Based Framework for the Automated Detection of PCOS Using Ultrasound Sonography Images

Polycystic Ovary Syndrome (PCOS) is a prevalent endocrine disorder among women of reproductive age, commonly diagnosed through a combination of clinical symptoms and ultrasound imaging of the ovaries. However, the variability in image quality and subjective interpretation of sonographic features often leads to inconsistent diagnoses. This study introduces SonoCyst-Net, an advanced deep learning-based framework for the automated detection of PCOS using ultrasound images. The model employs a high-performance EfficientNet-B3 backbone for robust and efficient feature extraction, coupled with a Variational Autoencoder (VAE) with Interactive Variational Attention to enhance and reconstruct diagnostically significant patterns. To address limitations in dataset diversity, a GAN-based augmentation pipeline is integrated to synthetically enrich training samples. For deployment in real-time healthcare environments, the model is optimized using pruning and quantization techniques, significantly reducing computational load. Evaluation on the Kaggle PCOS ultrasound dataset demonstrates that SonoCyst-Net achieves high diagnostic Accuracy 99.9%, Precision 99.74%, F1-Score 99.87%, and Specificity 99.82%, representing a promising AI-assisted tool for early and reliable PCOS detection.

Authors

Institutions

Publication Details

Journal
International Journal of Drug Delivery Technology
Published
2026-11-16
DOI
https://doi.org/10.25258/ijddt.16.80s.48
Primary Topic
Ovarian function and disorders
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

SonoCyst-Net: Deep Learning-Based Framework for the Automated Detection of PCOS Using Ultrasound Sonography Images

Meghamala Kunderu, K. Venkata Raju
6 links
International Journal of Drug Delivery Technology
Ovarian function and disorders
article

SonoCyst-Net: Deep Learning-Based Framework for the Automated Detection of PCOS Using Ultrasound Sonography Images

Meghamala Kunderu, K. Venkata Raju
article en

Abstract

Polycystic Ovary Syndrome (PCOS) is a prevalent endocrine disorder among women of reproductive age, commonly diagnosed through a combination of clinical symptoms and ultrasound imaging of the ovaries. However, the variability in image quality and subjective interpretation of sonographic features often leads to inconsistent diagnoses. This study introduces SonoCyst-Net, an advanced deep learning-based framework for the automated detection of PCOS using ultrasound images. The model employs a high-performance EfficientNet-B3 backbone for robust and efficient feature extraction, coupled with a Variational Autoencoder (VAE) with Interactive Variational Attention to enhance and reconstruct diagnostically significant patterns. To address limitations in dataset diversity, a GAN-based augmentation pipeline is integrated to synthetically enrich training samples. For deployment in real-time healthcare environments, the model is optimized using pruning and quantization techniques, significantly reducing computational load. Evaluation on the Kaggle PCOS ultrasound dataset demonstrates that SonoCyst-Net achieves high diagnostic Accuracy 99.9%, Precision 99.74%, F1-Score 99.87%, and Specificity 99.82%, representing a promising AI-assisted tool for early and reliable PCOS detection.

International Journal of Drug Delivery TechnologyVol. 16(80s)
Koneru Lakshmaiah Education Foundation (IN)
Good health and well-being
Ovarian function and disorders
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon