A multi-center analysis of deep learning methods for video polyp detection and segmentation

2026-03-04

AI Summary

This study addresses the challenge of missed or incompletely resected polyps during colonoscopy—a critical issue undermining colorectal cancer prevention due to the high variability in polyp morphology, location, and size. To tackle this problem, we propose a deep learning-based video analysis model that integrates spatiotemporal features for end-to-end polyp detection and segmentation, trained and validated on multicenter real-world clinical data. Our work presents the first systematic evaluation of the contribution of inter-frame temporal information to model performance, demonstrating significant improvements in detection sensitivity and segmentation accuracy. The results confirm that explicit temporal modeling effectively reduces miss rates and enhances clinical utility, thereby providing a key technical foundation for real-time computer-aided diagnosis systems in colonoscopy.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Colonic polyps are well-recognized precursors to colorectal cancer (CRC), typically detected during colonoscopy. However, the variability in appearance, location, and size of these polyps complicates their detection and removal, leading to challenges in effective surveillance, intervention, and subsequently CRC prevention. The processes of colonoscopy surveillance and polyp removal are highly reliant on the expertise of gastroenterologists and occur within the complexities of the colonic structure. As a result, there is a high rate of missed detections and incomplete removal of colonic polyps, which can adversely impact patient outcomes. Recently, automated methods that use machine learning have been developed to enhance polyps detection and segmentation, thus helping clinical processes and reducing missed rates. These advancements highlight the potential for improving diagnostic accuracy in real-time applications, which ultimately facilitates more effective patient management. Furthermore, integrating sequence data and temporal information could significantly enhance the precision of these methods by capturing the dynamic nature of polyp growth and the changes that occur over time. To rigorously investigate these challenges, data scientists and experts gastroenterologists collaborated to compile a comprehensive dataset that spans multiple centers and diverse populations. This initiative aims to underscore the critical importance of incorporating sequence data and temporal information in the development of robust automated detection and segmentation methods. This study evaluates the applicability of deep learning techniques developed in real-time clinical colonoscopy tasks using sequence data, highlighting the critical role of temporal relationships between frames in improving diagnostic precision.

Problem

• colonic polyps
• missed detection
• colorectal cancer prevention
• polyp segmentation
• colonoscopy

Innovation

• deep learning
• video polyp detection
• temporal information
• multi-center dataset
• real-time segmentation