See More, Detect More: Investigating Colonic Inspection Techniques and Polyp Detection Using Machine Learning
- 1Department of Industrial and Manufacturing Engineering, Penn State, University Park, PA 16802
- 2Department of Mechanical and Nuclear Engineering, Penn State, University Park, PA 16802
Abstract
BACKGROUND: Colorectal cancer (CRC) is a leading cause of cancer mortality despite widespread colonoscopy screening. Colonoscopy effectiveness, which can reduce CRC risk by 90%, depends largely on adenoma detection rate (ADR), a metric strongly influenced by mucosal inspection quality during withdrawal. However, ADR miss rates remain as high as 26% due to incomplete inspection. Although simulation-based training (SBT) improves procedural skills, physical simulators lack objective assessment and feedback on inspection quality. This study aimed to develop an automated machine-learning model (ML) to objectively assess colonoscopy inspection performance and identify feedback to improve ADR. METHODS: A Vision Transformer (ViT)-based ML model was developed to automatically recognize three inspection techniques during SBT required for effective inspection: clear lumen view, lateral wall, and obscured (fold) inspection. Model performance was evaluated using accuracy, precision, recall, and F1 score. The validated model was applied to videos from experts (n = 5), intermediate (n = 5), and novice residents (n = 7) performing withdrawal on a physical simulator embedded with silicone polyps. The model quantified time spent in each technique and surrounding polyp detection. Polyp detection rate (PDR) was quantified based on number of polyps detected. RESULTS: The model achieved high accuracy, precision, recall, and F1 score. Greater inspection time in obscured regions was significantly associated with higher PDR (r = 0.50, p = 0.041). Compared with novices, experts spent more time inspecting with a clear lumen view (p = 0.039) and deeper obscured views (p = 0.017), demonstrated higher PDR, and devoted more time to obscured regions before or after polyp detection. CONCLUSION: The ViT ML model accurately recognizes key inspection techniques and objectively differentiates inspection performance across expertise levels using time-based metrics and PDR. This enables objective assessment and targeted feedback-such as highlighting uninspected, obscured regions within physical SBT, with the potential to improve inspection performance and ADR.
Related
- ACSFANet: Adaptive Cross-Scale Feature Aggregation Network for miniature defect detection in UAV-based distribution network inspection
- Comparative Analysis of Two Real-Time PCR Techniques for the Detection of Congenital Syphilis in Umbilical Cord Blood
- Data Auditing and Quality Assurance in a Federated Learning Consortium; Getting the Best of Both Worlds from Cross-Institutional and In-House Data Quality Inspection
- Recent advances in bacterial detection techniques targeting genetic, protein, and enzymatic biomarkers
- Prediction of gross extrathyroidal extension in papillary thyroid carcinoma using a deep learning radiomics model based on post-processing techniques for multi-phase contrast-enhanced MRI images
BibTeX
@article{elsaadany2026more,
title = {{See More, Detect More: Investigating Colonic Inspection Techniques and Polyp Detection Using Machine Learning}},
author = {Isra K. Elsaadany and Sanaz Motamedi and Hang-Ling Wu and Scarlett R. Miller},
journal = {Surgical endoscopy},
year = {2026},
month = aug,
doi = {10.1007/s00464-026-13204-7},
url = {https://doi.org/10.1007/s00464-026-13204-7},
note = {CC BY},
}
RIS
TY - JOUR
TI - See More, Detect More: Investigating Colonic Inspection Techniques and Polyp Detection Using Machine Learning
AU - Isra K. Elsaadany
AU - Sanaz Motamedi
AU - Hang-Ling Wu
AU - Scarlett R. Miller
PY - 2026
DA - 2026/08/04
JO - Surgical endoscopy
DO - 10.1007/s00464-026-13204-7
UR - https://doi.org/10.1007/s00464-026-13204-7
AB - BACKGROUND: Colorectal cancer (CRC) is a leading cause of cancer mortality despite widespread colonoscopy screening. Colonoscopy effectiveness, which can reduce CRC risk by 90%, depends largely on adenoma detection rate (ADR), a metric strongly influenced by mucosal inspection quality during withdrawal. However, ADR miss rates remain as high as 26% due to incomplete inspection. Although simulation-based training (SBT) improves procedural skills, physical simulators lack objective assessment and feedback on inspection quality. This study aimed to develop an automated machine-learning model (ML) to objectively assess colonoscopy inspection performance and identify feedback to improve ADR. METHODS: A Vision Transformer (ViT)-based ML model was developed to automatically recognize three inspection techniques during SBT required for effective inspection: clear lumen view, lateral wall, and obscured (fold) inspection. Model performance was evaluated using accuracy, precision, recall, and F1 score. The validated model was applied to videos from experts (n = 5), intermediate (n = 5), and novice residents (n = 7) performing withdrawal on a physical simulator embedded with silicone polyps. The model quantified time spent in each technique and surrounding polyp detection. Polyp detection rate (PDR) was quantified based on number of polyps detected. RESULTS: The model achieved high accuracy, precision, recall, and F1 score. Greater inspection time in obscured regions was significantly associated with higher PDR (r = 0.50, p = 0.041). Compared with novices, experts spent more time inspecting with a clear lumen view (p = 0.039) and deeper obscured views (p = 0.017), demonstrated higher PDR, and devoted more time to obscured regions before or after polyp detection. CONCLUSION: The ViT ML model accurately recognizes key inspection techniques and objectively differentiates inspection performance across expertise levels using time-based metrics and PDR. This enables objective assessment and targeted feedback-such as highlighting uninspected, obscured regions within physical SBT, with the potential to improve inspection performance and ADR.
SN - 0930-2794
SN - 1432-2218
ER -