[2603.26834] Hybrid Diffusion Model for Breast Ultrasound Image Augmentation

Electrical Engineering and Systems Science > Image and Video Processing arXiv:2603.26834 (eess) [Submitted on 27 Mar 2026] Title:Hybrid Diffusion Model for Breast Ultrasound Image Augmentation Authors:Farhan Fuad Abir, Sanjeda Sara Jennifer, Niloofar Yousefi, Laura J. Brattain View a PDF of the paper titled Hybrid Diffusion Model for Breast Ultrasound Image Augmentation, by Farhan Fuad Abir and 3 other authors View PDF HTML (experimental) Abstract:We propose a hybrid diffusion-based augmentation framework to overcome the critical challenge of ultrasound data augmentation in breast ultrasound (BUS) datasets. Unlike conventional diffusion-based augmentations, our approach improves visual fidelity and preserves ultrasound texture by combining text-to-image generation with image-to-image (img2img) refinement, as well as fine-tuning with low-rank adaptation (LoRA) and textual inversion (TI). Our method generated realistic, class-consistent images on an open-source Kaggle breast ultrasound image dataset (BUSI). Compared to the Stable Diffusion v1.5 baseline, incorporating TI and img2img refinement reduced the Frechet Inception Distance (FID) from 45.97 to 33.29, demonstrating a substantial gain in fidelity while maintaining comparable downstream classification performance. Overall, the proposed framework effectively mitigates the low-fidelity limitations of synthetic ultrasound images and enhances the quality of augmentation for robust diagnostic modeling. Comments: Subjects: Im...