Artificial Intelligence in Gastrointestinal Bleeding Analysis for Video Capsule Endoscopy: Insights, Innovations, and Prospects (2008-2023)

TL;DR

This paper addresses the diagnostic challenge of GI bleeding detection in Video Capsule Endoscopy by surveying two decades of ML approaches (2008–2023) and evaluating their effectiveness across open datasets. It presents a structured methodology (PRISMA-guided) to compile 113 studies, categorizes bleeding detection techniques into classification, segmentation, and detection, and defines a comprehensive set of performance metrics, including both classical (accuracy, precision, recall) and advanced (AUC, MCC, FID) measures. A key contribution is the detailed inventory and assessment of open-source VCE bleeding datasets (e.g., KID, Kvasir-Capsule, RLE), enabling reproducibility and benchmarking of ML methods. The paper also discusses gaps in generalizability, clinical translation, data diversity, and interpretability, and outlines future directions such as DL-enabled segmentation, weak supervision, and cross-disciplinary validation to advance GI diagnostics with ML.

Abstract

The escalating global mortality and morbidity rates associated with gastrointestinal (GI) bleeding, compounded by the complexities and limitations of traditional endoscopic methods, underscore the urgent need for a critical review of current methodologies used for addressing this condition. With an estimated 300,000 annual deaths worldwide, the demand for innovative diagnostic and therapeutic strategies is paramount. The introduction of Video Capsule Endoscopy (VCE) has marked a significant advancement, offering a comprehensive, non-invasive visualization of the digestive tract that is pivotal for detecting bleeding sources unattainable by traditional methods. Despite its benefits, the efficacy of VCE is hindered by diagnostic challenges, including time-consuming analysis and susceptibility to human error. This backdrop sets the stage for exploring Machine Learning (ML) applications in automating GI bleeding detection within capsule endoscopy, aiming to enhance diagnostic accuracy, reduce manual labor, and improve patient outcomes. Through an exhaustive analysis of 113 papers published between 2008 and 2023, this review assesses the current state of ML methodologies in bleeding detection, highlighting their effectiveness, challenges, and prospective directions. It contributes an in-depth examination of AI techniques in VCE frame analysis, offering insights into open-source datasets, mathematical performance metrics, and technique categorization. The paper sets a foundation for future research to overcome existing challenges, advancing gastrointestinal diagnostics through interdisciplinary collaboration and innovation in ML applications.

Figures (13)

• Figure 1: Year-wise distribution of papers included in the review.
• Figure 2: Flowchart depicting the structure of the review.
• Figure 3: Search string for searching the research articles.
• Figure 4: PRISMA: Outlining the review strategy for bleeding detection in VCE frames.
• Figure 5: Distribution of public and private datasets used in the papers.