Automated Uterine Fibroids Detection in Ultrasound Images Using Deep Learning

Uterine fibroids, or leiomyomas, are benign tumors affecting a significant percentage of women of reproductive age. Early detection and diagnosis are crucial for effective management, particularly in resource-limited settings. This research presents an automated system leveraging deep learning techniques to detect and classify uterine fibroids in ultrasound images. The methodology includes pre-processing steps for image standardization, segmentation using the UNet architecture, and classification employing advanced convolutional neural networks (CNNs) such as VGG-19, ResNet-50, and InceptionV3. Experimental results demonstrate high accuracy, sensitivity, and specificity, proving the system's potential for clinical application. Future improvements and real-time deployment strategies are also discussed.