arXiv 2502.179512025-12-29cs.CVcs.AI

通过组成提示引导的扩散模型实现鲁棒的息肉检测与诊断

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

Zhejiang University（浙江大学）；Shanghai Institute for Advanced Study of Zhejiang University（浙江大学上海高等研究院）；Endoscopy Center, Zhongshan Hospital, Fudan University（复旦大学中山医院内窥镜中心）；Shanghai Collaborative Innovation Center of Endoscopy（上海内窥镜协同创新中心）；Digital Medical Research Center, School of Basic Medical Sciences, Fudan University（复旦大学基础医学院数字医疗研究中心）；Shanghai Key Laboratory of MICCAI（上海MICCAI重点实验室）；Alliance Manchester Business School, The University of Manchester（曼彻斯特大学联盟商学院）；Data Science Institute, Imperial College London（伦敦帝国学院数据科学研究所）

Jia Yu, Yan Zhu, Peiyao Fu, Tianyi Chen, Junbo Huang, Quanlin Li, Pinghong Zhou, Zhihua Wang, Fei Wu, Shuo Wang, Xian Yang

发表信息：: IEEE Trans. Med. Imaging, vol. 44, no. 12, pp. 5245-5257, Dec. 2025
DOI：: 10.1109/TMI.2025.3589456.

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出PSDM模型，通过整合多种临床注释生成合成图像，提升息肉检测、分类和分割的鲁棒性和泛化能力。

摘要：

结直肠癌（CRC）是全球的重大健康问题，早期通过筛查检测在降低死亡率中起着关键作用。尽管深度学习模型在提高息肉检测、分类和分割方面显示出潜力，但其在不同临床环境中的泛化能力，特别是面对分布外（OOD）数据时仍面临挑战。像PolypGen这样的多中心数据集已被开发以解决这些问题，但其收集成本高且耗时。传统数据增强技术提供的变化有限，无法捕捉医学图像的复杂性。扩散模型已 emerged 作为生成合成息肉图像的有希望的解决方案，但当前模型的图像生成过程主要依赖于分割掩码作为条件，限制了其捕捉完整临床背景的能力。为克服这些限制，我们提出了一种渐进光谱扩散模型（PSDM），通过将多样化的临床注释（如分割掩码、边界框和内镜报告）转换为组成提示，整合它们。这些提示被组织为粗略和精细组件，使模型能够捕捉广大的空间结构和细节，生成临床准确的合成图像。通过使用PSDM生成的样本增强训练数据，我们的模型显著提高了息肉检测、分类和分割。例如，在PolypGen数据集上，PSDM将F1分数提高了2.12%，平均平均精度提高了3.09%，在OOD场景中表现出优越的性能和增强的泛化能力。

英文摘要：

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 PolypGen dataset, PSDM increases the F1 score by 2.12% and the mean average precision by 3.09%, demonstrating superior performance in OOD scenarios and enhanced generalization.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。