Paper Detail
Farhan Fuad Abir, Sanjeda Sara Jennifer, Niloofar Yousefi, Laura J. Brattain
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{abir2026hybrid,
title = {Hybrid Diffusion Model for Breast Ultrasound Image Augmentation},
author = {Farhan Fuad Abir and Sanjeda Sara Jennifer and Niloofar Yousefi and Laura J. Brattain},
year = {2026},
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 ima},
url = {https://arxiv.org/abs/2603.26834},
keywords = {eess.IV, cs.AI, cs.CV},
eprint = {2603.26834},
archiveprefix = {arXiv},
}
{}