American Journal for Young Scientists ยท ISSN 3068-9015
Automated Detection of Fetal Abnormalities in Ultrasound Imaging Using a Convolutional Neural Network
Authors: Dharshana Uvaraj
Published: September 26, 2025
Category: Computer Science
Abstract
Every year, millions of fetal deaths occur due to undetected or misdiagnosed prenatal diseases and abnormalities. Many of these conditions could be managed or treated if identified early, yet current diagnostic methods rely heavily on human interpretation of ultrasound images, which can be subjective, error-prone, and inconsistent across healthcare facilities. This research aims to develop an accurate and accessible deep learning-based detection system using a Convolutional Neural Network (CNN) to automate the identification of fetal brain abnormalities in ultrasound images. The model was trained on a dataset of over 10,000 images, distinguishing between normal and abnormal fetal brain scans. Through rigorous testing and validation, the CNN achieved a detection accuracy of nearly 99%, demonstrating its potential as a highly reliable diagnostic tool. These findings suggest that AI-assisted prenatal screening can enhance early detection, reduce diagnostic disparities, and improve fetal healthcare outcomes, particularly in resource-limited settings. By integrating deep learning into prenatal care, this research provides a scalable solution that could significantly reduce preventable perinatal mortality and improve early medical intervention strategies.