Subtyping Breast Lesions via Generative Augmentation based Long-tailed Recognition in Ultrasound

TL;DR

This paper introduces a dual-phase generative augmentation framework with reinforcement learning for improved long-tailed breast lesion classification in ultrasound images, enhancing recognition of rare subtypes.

Contribution

It presents a novel adaptive synthetic data generation method that balances data augmentation and discriminative performance in imbalanced breast US datasets.

Findings

Outperforms existing methods on in-house and public datasets.

Achieves higher accuracy in recognizing rare breast lesion subtypes.

Demonstrates effective use of anatomical priors in synthetic data generation.

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.