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

2025/07/10 by Haoyu Pan, Hongxin Lin, Pan, Haoyu +13
Computer Science · Medicine · #AI in cancer detection #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Generative Adversarial Networks and Image Synthesis #Image and Video Processing (eess.IV) #Ultrasound Imaging and Elastography #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2507.07721

openalex publication_date 2025/07/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Ultrasound Image Generation using Latent Diffusion Models
• ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models
• Sketch guided and progressive growing GAN for realistic and editable ultrasound image synthesis
• GAN-based disentanglement learning for chest X-ray rib suppression
• Diffusion Models Beat GANs on Image Synthesis
• Learning Transferable Visual Models From Natural Language Supervision
• COVID-19 CT Image Synthesis with a Conditional Generative Adversarial Network
• ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data
• UNet++: A Nested U-Net Architecture for Medical Image Segmentation
• Attention U-Net: Learning Where to Look for the Pancreas
• Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks
• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
• Densely Connected Convolutional Networks
• Deep Residual Learning for Image Recognition
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics

Related

• A Foundational Generative Model for Breast Ultrasound Image Analysis
• An Efficient Solution for Breast Tumor Segmentation and Classification\n in Ultrasound Images Using Deep Adversarial Learning
• Enhancing AI Diagnostics: Autonomous Lesion Masking via Semi-Supervised Deep Learning
• Knowledge-driven AI-generated data for accurate and interpretable breast ultrasound diagnoses
• USF-MAE: Ultrasound Self-Supervised Foundation Model with Masked Autoencoding