Scholarlink

Background <p>Colonoscopic withdrawal time is an important metric for evaluating colonoscopy quality, but it can be substantially affected by therapeutic maneuvers, impaired visualization, and other interruptions unrelated to mucosal inspection. In this study, we developed an artificial intelligence-based approach to estimate effective withdrawal time (EWT), defined as the periods during which the mucosa or lesions are clearly observed, with the aim of providing a more objective description of inspection time.</p> Methods <p>We developed an InternImage-based model to classify complete colonoscopy withdrawal videos into four categories: Observation, Operation, Obscure, and Outside. The Observation category was defined as EWT. The annotated data were split at the video level into development and independent test sets to avoid data leakage. To explore the potential clinical relevance of EWT, we compared therapeutic, biopsy, polyp, and non-polyp examinations across multiple analyses.</p> Results <p>The model achieved a classification accuracy of 97.18% (95% CI: 96.66% to 97.39%) on the independent test set. EWT differed between therapeutic and screening-related examinations, whereas the EWT values of the biopsy, polyp, and non-polyp groups were relatively similar despite clear differences in conventional withdrawal time. EWT also varied across hospitals and physician seniority strata, suggesting potential usefulness for cross-context quality assessment.</p> Conclusions <p>Our model can identify clinically relevant withdrawal phases from complete colonoscopy videos and objectively calculate EWT. These findings support the technical feasibility of EWT as a complementary surrogate metric for colonoscopy quality assessment across different procedural contexts. However, prospective validation with established clinical outcomes, including ADR and APC, is still needed.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Calculation and evaluation of the effective withdrawal time of colonoscopy on the basis of internimage

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月22日

查看全文
  • Xiangyu Wang,
  • Ziye Peng,
  • Jinghui Du,
  • Ximo Wang,
  • Siqi He,
  • Shuyi Zhang,
  • Yanru Li,
  • Qi Zhang,
  • Lei Shi,
  • Dong Yang,
  • Duo Li,
  • Yang Xu,
  • Xueliang Wu,
  • Wenrui Wang,
  • Linlin Gao,
  • Jiaxin Li,
  • Zhengcun Pei

摘要

Background

Colonoscopic withdrawal time is an important metric for evaluating colonoscopy quality, but it can be substantially affected by therapeutic maneuvers, impaired visualization, and other interruptions unrelated to mucosal inspection. In this study, we developed an artificial intelligence-based approach to estimate effective withdrawal time (EWT), defined as the periods during which the mucosa or lesions are clearly observed, with the aim of providing a more objective description of inspection time.

Methods

We developed an InternImage-based model to classify complete colonoscopy withdrawal videos into four categories: Observation, Operation, Obscure, and Outside. The Observation category was defined as EWT. The annotated data were split at the video level into development and independent test sets to avoid data leakage. To explore the potential clinical relevance of EWT, we compared therapeutic, biopsy, polyp, and non-polyp examinations across multiple analyses.

Results

The model achieved a classification accuracy of 97.18% (95% CI: 96.66% to 97.39%) on the independent test set. EWT differed between therapeutic and screening-related examinations, whereas the EWT values of the biopsy, polyp, and non-polyp groups were relatively similar despite clear differences in conventional withdrawal time. EWT also varied across hospitals and physician seniority strata, suggesting potential usefulness for cross-context quality assessment.

Conclusions

Our model can identify clinically relevant withdrawal phases from complete colonoscopy videos and objectively calculate EWT. These findings support the technical feasibility of EWT as a complementary surrogate metric for colonoscopy quality assessment across different procedural contexts. However, prospective validation with established clinical outcomes, including ADR and APC, is still needed.