UltraGANet: A Class-Conditional GAN Framework for Breast Tumor Classification in Ultrasound Imaging

Purpose This study addresses the critical challenge of limited annotated data in ultrasound-based breast cancer diagnosis by proposing a novel classification framework. The research aims to evaluate whether (cGANs) can effectively augment training datasets and enhance classification performance when integrated with a lightweight (CNN) model, UltraGANet. Methods We developed a cGAN capable of generating class-specific grayscale breast ultrasound images and corresponding segmentation masks for benign, malignant, and normal categories. These synthetic samples were combined with real ultrasound images from the BUSI dataset to create an augmented training set. UltraGANet, a task-specific CNN architecture, was trained using this dataset and evaluated through 5-fold stratified cross-validation and testing on an independent set of 146 real images. Performance metrics included accuracy, precision, recall, and F1-score. Results UltraGANet achieved an average classification accuracy of 91.4% ± 1.2% during cross-validation and 91.03% on the test set. Malignant tumor recall reached 92% , indicating high sensitivity. The model maintained balanced precision and F1-scores across all classes. Qualitative analysis confirmed that synthetic images preserved anatomical plausibility and tumor characteristics. Conclusion The integration of cGAN-based augmentation with UltraGANet substantially improved classification performance, particularly in malignant tumor detection. The proposed framework offers a scalable, computationally efficient solution for breast ultrasound diagnostics, especially valuable in data-scarce or resource-limited clinical environments.