Robust Polyp Detection and Diagnosis Through Compositional Prompt-Guided Diffusion Models

作者：Jia Yu, Yan Zhu, Pei‐Yao Fu, Tianyi Chen, Junbo Huang, Quan‐Lin Li, Ping-Hong Zhou, Zhihua Wang, Fei Wu, Shuo Wang, Xian Yang · 发表于：IEEE Transactions on Medical Imaging · 年份：2025 · DOI：10.1109/tmi.2025.3589456 · 被引用次数：3 · 研究领域：Iron and Steelmaking Processes、Powder Metallurgy Techniques and Materials、Metallurgical Processes and Thermodynamics

Colorectal cancer (CRC) is a significant global health concern, and early detection through screening plays a critical role in reducing mortality. While deep learning models have shown promise in improving polyp detection, classification, and segmentation, their generalization across diverse clinical environments, particularly with out-of-distribution (OOD) data, remains a challenge. Multi-center datasets like PolypGen have been developed to address these issues, but their collection is costly and time-consuming. Traditional data augmentation techniques provide limited variability, failing to capture the complexity of medical images. Diffusion models have emerged as a promising solution for generating synthetic polyp images, but the image generation process in current models mainly relies on segmentation masks as the condition, limiting their ability to capture the full clinical context. To overcome these limitations, we propose a Progressive Spectrum Diffusion Model (PSDM) that integrates diverse clinical annotations-such as segmentation masks, bounding boxes, and colonoscopy reports-by transforming them into compositional prompts. These prompts are organized into coarse and fine components, allowing the model to capture both broad spatial structures and fine details, generating clinically accurate synthetic images. By augmenting training data with PSDM-generated samples, our model significantly improves polyp detection, classification, and segmentation. For instance, on the...