Polyp-Gen：用于内镜数据集扩展的逼真且多样化的息肉图像生成
Polyp-Gen: Realistic and Diverse Polyp Image Generation for Endoscopic Dataset Expansion
- Department of Electronic Engineering, Chinese University of Hong Kong（香港中文大学电子工程系）
- Centre for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（香港科学院人工智能与机器人中心）
- Department of Electrical Engineering, The City University of Hong Kong（香港城市大学电子工程系）
- Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
- The Sixth Affiliated Hospital, Sun Yat-sen University（中山大学第六附属医院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
Polyp-Gen提出首个全自动扩散内镜图像生成框架，通过空间感知扩散和分层检索采样，生成逼真多样息肉图像，提升检测性能并具零样本泛化能力。
AI中文摘要：
自动化诊断系统（ADS）在内镜检查中早期检测息肉方面显示出巨大潜力，从而降低结直肠癌的发病率。然而，由于高昂的标注成本和严格的隐私问题，获取高质量的内镜图像对ADS的开发构成了相当大的挑战。尽管近期在生成合成图像以扩展数据集方面取得了进展，但现有的内镜图像生成算法未能准确生成息肉边界区域的细节，并且通常需要医学先验来指定息肉的合理位置和形状，这限制了生成图像的逼真度和多样性。为解决这些局限性，我们提出了Polyp-Gen，这是首个全自动的基于扩散的内镜图像生成框架。具体而言，我们设计了一种具有病灶引导损失的空间感知扩散训练方案，以增强息肉边界区域的结构上下文。此外，为了捕获潜在息肉区域定位的医学先验，我们引入了一种基于分层检索的采样策略，以匹配相似的细粒度空间特征。通过这种方式，我们的Polyp-Gen能够生成逼真且多样的内镜图像，以构建可靠的ADS。大量实验证明了最先进的生成质量，并且合成图像能够改进下游的息肉检测任务。此外，我们的Polyp-Gen在其他数据集上表现出显著的零样本泛化能力。源代码可在https://github.com/CUHK-AIM-Group/Polyp-Gen获取。
英文摘要：
Automated diagnostic systems (ADS) have shown significant potential in the early detection of polyps during endoscopic examinations, thereby reducing the incidence of colorectal cancer. However, due to high annotation costs and strict privacy concerns, acquiring high-quality endoscopic images poses a considerable challenge in the development of ADS. Despite recent advancements in generating synthetic images for dataset expansion, existing endoscopic image generation algorithms failed to accurately generate the details of polyp boundary regions and typically required medical priors to specify plausible locations and shapes of polyps, which limited the realism and diversity of the generated images. To address these limitations, we present Polyp-Gen, the first full-automatic diffusion-based endoscopic image generation framework. Specifically, we devise a spatial-aware diffusion training scheme with a lesion-guided loss to enhance the structural context of polyp boundary regions. Moreover, to capture medical priors for the localization of potential polyp areas, we introduce a hierarchical retrieval-based sampling strategy to match similar fine-grained spatial features. In this way, our Polyp-Gen can generate realistic and diverse endoscopic images for building reliable ADS. Extensive experiments demonstrate the state-of-the-art generation quality, and the synthetic images can improve the downstream polyp detection task. Additionally, our Polyp-Gen has shown remarkable zero-shot generalizability on other datasets. The source code is available at https://github.com/CUHK-AIM-Group/Polyp-Gen.
