Application of artificial intelligence in colonoscopy imaging for polyp analysis-A systematic review

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not quantified in abstract - described as 'substantial potential' and 'significant reduction' in inter-observer variability

• Primary Outcome: AI systems demonstrated improved accuracy, consistency, and objectivity in polyp detection compared to conventional methods

• Nnt Or Sensitivity: Specific sensitivity and specificity values not provided in abstract

• Confidence Interval: Not reported

Clinical Application

Limited by challenges in real-time deployment, data imbalance, and generalizability across diverse populations and equipment Relevant to Australian colorectal cancer screening programs and may support quality improvement initiatives, though implementation would require TGA approval and integration with existing colonoscopy workflows Patients undergoing colonoscopy screening and surveillance, particularly in settings with variable operator expertise

Abstract

The colon is a major component of the digestive system, so early detection of colorectal polyps is essential in preventing colorectal cancer, which is a leading cause of cancer-related death worldwide. While colonoscopy remains the gold standard for polyp detection, its diagnostic accuracy is highly operator-dependent. Recent advances in Deep Learning (DL), a branch of Artificial Intelligence (AI), have shown substantial potential to improve colonoscopy image analysis by enhancing the accuracy, consistency, and objectivity of polyp detection, segmentation, and classification. Artificial intelligence-based systems have significantly reduced inter-observer variability and increased diagnostic efficiency, ultimately transforming the landscape of colorectal lesion assessment. This survey provides a comprehensive and critical analysis of the current status of deep learning applications in colorectal polyp analysis. We systematically review state-of-the-art methodologies across various DL architectures-including Convolutional Neural Networks (CNNs), transformer-based models, and hybrid approaches-and examine their performance on publicly available benchmark datasets. Additionally, we highlight the strengths and limitations of existing techniques, explore the clinical relevance of AI-assisted tools, and identify prevailing challenges such as data imbalance, real-time deployment, and generalizability across diverse populations and colonoscopy devices. By consolidating key advances and outlining future research directions, this review aims to serve as a valuable resource for researchers, clinicians, and developers seeking to leverage deep learning to enhance colorectal polyp detection, diagnosis, and clinical decision-making.

References

1. 1.Amirmohammadi, E., Shalbaf, A., Esteki, A., Sadeghi, A., Moghadam, A. R., Moghtaderi, M., & Moghadam, P. K. (2026). Application of artificial intelligence in colonoscopy imaging for polyp analysis-A systematic review. Computer Methods and Programs in Biomedicine, 109239. https://doi.org/10.1016/j.cmpb.2026.109239