Inception U-Net for Enhanced Breast Ultrasound Image Segmentation Using Transfer Learning

Background: Breast cancer diagnosis increasingly relies on ultrasound imaging, but challenges related to operator dependency and image quality limitations necessitate automated segmentation approaches. Traditional U-Net architectures, while widely used for medical image segmentation, suffer from shallow encoder structures that limit feature extraction capabilities. Methods: This study proposes an enhanced segmentation model that replaces the conventional U-Net encoder with an Inception architecture and employs transfer learning using ImageNet pre-trained weights. The model was trained and evaluated on a dataset of 900 breast ultrasound images from Kyungpook National University Hospital. Performance evaluation utilized multiple metrics including Intersection over Union (IoU), Dice coefficient, precision, and recall scores. Results: The proposed Inception U-Net achieved superior performance with an IoU score of 0.7774, Dice score of 0.8491, precision score of 0.7081, and recall score of 0.7174, demonstrating approximately 5% improvement over baseline U-Net architecture across all evaluation metrics. Conclusions: The integration of Inception modules within the U-Net architecture effectively addresses feature extraction limitations in breast ultrasound segmentation. Transfer learning from ImageNet datasets proves beneficial even across domain differences, establishing a foundation for broader medical imaging applications.