Polyp-Gen: Realistic and Diverse Polyp Image Generation for Endoscopic Dataset Expansion

2025-01-28

AI Summary

To address the scarcity of annotated training data for colorectal cancer early screening—caused by high annotation costs and privacy constraints in endoscopic imaging—this paper proposes the first fully automated diffusion model framework for high-fidelity, high-quality polyp image synthesis. Methodologically, it introduces a novel spatially aware diffusion training paradigm and a lesion-guided loss function, integrated with a hierarchical retrieval-based sampling strategy to implicitly encode anatomical priors and precise lesion boundary information. Experimental results demonstrate state-of-the-art (SOTA) image quality and significant performance gains across multiple downstream polyp detection tasks (average mAP improvement of +8.2%). Moreover, the framework exhibits strong zero-shot cross-dataset generalization, enabling robust automated diagnosis systems without requiring any manual annotations.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Learning to Search
• Machine Learning: Multimodal Learning

Application Category

• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Data transparency and provenance

Abstract

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.

Problem

• Automated Diagnostic System (ADS)
• Polyp Recognition
• Colorectal Cancer Early Detection

Innovation

• Polyp-Gen
• Realistic Polyp Image Generation
• Automated Diagnosis System Enhancement