Breast Ultrasound Tumor Generation via Mask Generator and Text-Guided Network:A Clinically Controllable Framework with Downstream Evaluation

TL;DR

This paper presents a controllable generative framework for synthesizing breast ultrasound images with tumors, guided by clinical descriptions and structural masks, to address data scarcity and improve diagnosis models.

Contribution

It introduces a novel mask generator and text-guided network that produce realistic, diverse, and controllable synthetic BUS images for clinical and research use.

Findings

Synthetic images improve breast cancer diagnosis accuracy.

Generated images are validated as realistic by expert sonographers.

Framework enhances data diversity for training deep learning models.

Abstract

The development of robust deep learning models for breast ultrasound (BUS) image analysis is significantly constrained by the scarcity of expert-annotated data. To address this limitation, we propose a clinically controllable generative framework for synthesizing BUS images. This framework integrates clinical descriptions with structural masks to generate tumors, enabling fine-grained control over tumor characteristics such as morphology, echogencity, and shape. Furthermore, we design a semantic-curvature mask generator, which synthesizes structurally diverse tumor masks guided by clinical priors. During inference, synthetic tumor masks serve as input to the generative framework, producing highly personalized synthetic BUS images with tumors that reflect real-world morphological diversity. Quantitative evaluations on six public BUS datasets demonstrate the significant clinical utility of our synthetic images, showing their effectiveness in enhancing downstream breast cancer diagnosis tasks. Furthermore, visual Turing tests conducted by experienced sonographers confirm the realism of the generated images, indicating the framework's potential to support broader clinical applications.