EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Development and validation of a real-time computer-aided measuring system for colorectal polyp size (with video)

Cheng-Long Wang iD, Xiang-Yu Sui, Song Zhang, Jia-Hui Wei, Jia-Yi Wu, Yi-Ta Wu, Xin-Xin Huang, Wen-Long Li, Zi-Ye Zhao iD, Yi Zeng, Zhi-Wei Liu, Huan-Wei Zhang und 9 weitere

Gastroenterology Report · 20.01.2026 · 14

DOI: 10.1093/gastro/goag041 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Gastroenterology Report, online erschienen am 12.05.2026. Verfasst von Cheng-Long Wang und 20 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gastroenterology, Changhai Hospital, Naval Medical University, 168 Changhai Road, Shanghai 200433, P. R. China. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Noncommunicable Chronic Diseases-National Science and Technology Major Project, Shanghai Eastern Talent Elite Program, Changhai hospital special foundation for clinical research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Polyp size measurement is critical in determining the resection method and surveillance interval; however, the accuracy and reliability of existing measurement methods are suboptimal. We establish a computer-aided measuring (CAM) system to automatically and accurately measure colorectal polyp size in real time.

Methods

We conducted a hybrid retrospective and prospective preclinical study to develop models retrospectively and validate them prospectively. The CAM system includes two deep learning models: a polyp detection model trained on 15,620 images and tested on 4,438 images and a depth-map prediction model trained on 18,500 red–green–blue depth-map pairs and tested on 1,500 pairs. A digitized three-dimensional model development setting (3D-MDS) was used to validate the CAM system; here, 3,750 red–green–blue images from 15 digital virtual 3D polyps were generated for size measurements. A high-simulation colon/polyp model was used to test real-time polyp size measurement performance.

Results

In the 3D-MDS, the CAM system had an average relative error of 7.9% (standard deviation 4.19%) for the depth-map prediction model and a mean percentage error of 7.9% (interquartile range [IQR] 4.6%–10.4%) for the polyp size measurement. In the high-simulation colon/polyp model, the CAM system’s depth distance measurement had a percentage error of 12.0% (IQR 5.5%–15.7%). For the polyp size measurement, the highest accuracy and reliability were achieved at the medium-depth distance and the position within the center field-of-view, with percentage errors of 4.1% (IQR 2.6%–4.5%) and 3.3% (IQR 1.8%–3.5%) for the first and second measurements, respectively, and an intraclass correlation coefficient of 0.999.

Conclusions

The CAM system showed excellent accuracy and reliability in diverse testing scenarios; here, the medium-depth distance (15–35 mm) and the position within the center field-of-view was likely the optimal measurement location.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencecolonoscopydeep learningdepth mappolyp size

Autor:innen und Institutionen

  • Department of Gastroenterology, Changhai Hospital, Naval Medical University, 168 Changhai Road, Shanghai 200433, P. R. China.
  • Department of Colorectal Surgery and Gastrointestinal Endoscopy Center, Changhai Hospital, Naval Medical University, 168 Changhai Road, Shanghai 200433, P. R. China.
  • Department of Gastroenterology, Xiamen University Affiliated Chenggong Hospital (Army 73rd Group Military Hospital), 94 Wenyuan Road, Xiamen, Fujian 361003, P. R. China.
  • Department of Construction Engineering, Jinhua Open University, 18 Qingzhao Road, Jinhua, Zhejiang 321000, P. R. China.
  • AI Solutions Department, Insign Medical Technology (Ningbo) Ltd., 112 Binjiang Road, Cixi, Zhejiang 315300, P. R. China.
  • National Key Laboratory of Immunity and Inflammation, Naval Medical University, 258 Zhongyuan Road, Shanghai 200433, P. R. China.

ORCID-Profile: Cheng-Long Wang, Zi-Ye Zhao

Förderung

  • Noncommunicable Chronic Diseases-National Science and Technology Major Project
  • Shanghai Eastern Talent Elite Program
  • Changhai hospital special foundation for clinical research
  • China National Postdoctoral Program for Innovative Talents
  • Natural Science Foundation of Shanghai
  • Shanghai Sailing Program
  • Chenguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission
  • Special Clinical Research on Health Industry of Shanghai Municipal Health Commission

Zitieren

APA

Wang, C. L., Sui, X. Y., Zhang, S., Wei, J. H., Wu, J. Y., Wu, Y. T., Huang, X. X., Li, W. L., Zhao, Z. Y., Zeng, Y., Liu, Z. W., Zhang, H. W., Zhao, Y. D., Fang, Q. W., Wang, S. H., Li, X., Chang, K., Li, Z. S., Yu, E. D., …, & Bai, Y. (2026). Development and validation of a real-time computer-aided measuring system for colorectal polyp size (with video). Gastroenterology Report, 14. https://doi.org/10.1093/gastro/goag041

Vancouver

Wang CL, Sui XY, Zhang S, Wei JH, Wu JY, Wu YT, et al. Development and validation of a real-time computer-aided measuring system for colorectal polyp size (with video). Gastroenterology Report. 2026;14. doi:10.1093/gastro/goag041

BibTeX
@article{Wang2026,
  author = {Wang, Cheng-Long and Sui, Xiang-Yu and Zhang, Song and Wei, Jia-Hui and Wu, Jia-Yi and Wu, Yi-Ta and Huang, Xin-Xin and Li, Wen-Long and Zhao, Zi-Ye and Zeng, Yi and Liu, Zhi-Wei and Zhang, Huan-Wei and Zhao, You-Dong and Fang, Qi-Wen and Wang, Shi-Hang and Li, Xin and Chang, Kevin and Li, Zhao-Shen and Yu, En-Da and Zhao, Sheng-Bing and Bai, Yu},
  title = {Development and validation of a real-time computer-aided measuring system for colorectal polyp size (with video)},
  journal = {Gastroenterology Report},
  year = {2026},
  volume = {14},
  doi = {10.1093/gastro/goag041}
}
Kostenlos starten →