{"ID":2888754,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.22568","arxiv_id":"2507.22568","title":"Subtyping Breast Lesions via Generative Augmentation based Long-tailed Recognition in Ultrasound","abstract":"Accurate identification of breast lesion subtypes can facilitate personalized treatment and interventions. Ultrasound (US), as a safe and accessible imaging modality, is extensively employed in breast abnormality screening and diagnosis. However, the incidence of different subtypes exhibits a skewed long-tailed distribution, posing significant challenges for automated recognition. Generative augmentation provides a promising solution to rectify data distribution. Inspired by this, we propose a dual-phase framework for long-tailed classification that mitigates distributional bias through high-fidelity data synthesis while avoiding overuse that corrupts holistic performance. The framework incorporates a reinforcement learning-driven adaptive sampler, dynamically calibrating synthetic-real data ratios by training a strategic multi-agent to compensate for scarcities of real data while ensuring stable discriminative capability. Furthermore, our class-controllable synthetic network integrates a sketch-grounded perception branch that harnesses anatomical priors to maintain distinctive class features while enabling annotation-free inference. Extensive experiments on an in-house long-tailed and a public imbalanced breast US datasets demonstrate that our method achieves promising performance compared to state-of-the-art approaches. More synthetic images can be found at https://github.com/Stinalalala/Breast-LT-GenAug.","short_abstract":"Accurate identification of breast lesion subtypes can facilitate personalized treatment and interventions. Ultrasound (US), as a safe and accessible imaging modality, is extensively employed in breast abnormality screening and diagnosis. However, the incidence of different subtypes exhibits a skewed long-tailed distrib...","url_abs":"https://arxiv.org/abs/2507.22568","url_pdf":"https://arxiv.org/pdf/2507.22568v1","authors":"[\"Shijing Chen\",\"Xinrui Zhou\",\"Yuhao Wang\",\"Yuhao Huang\",\"Ao Chang\",\"Dong Ni\",\"Ruobing Huang\"]","published":"2025-07-30T10:50:41Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Reinforcement Learning\"]","has_code":false,"code_links":[{"ID":611574,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2888754,"paper_url":"https://arxiv.org/abs/2507.22568","paper_title":"Subtyping Breast Lesions via Generative Augmentation based Long-tailed Recognition in Ultrasound","repo_url":"https://github.com/Stinalalala/Breast-LT-GenAug","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}