Bridging the gap: Computer-aided detection and Yamada classification system matches expert performance

doi:10.3748/wjg.v31.i40.111120

Advanced Search

BPG is committed to discovery and dissemination of knowledge

Home / Archive / Volume 31, Issue 40

This Article

Academic Content and Language Evaluation of This Article

CrossCheck and Google Search of This Article

Academic Rules and Norms of This Article

Supplementary Materials of This Article

Citation of this article

Corresponding Author of This Article

Research Domain of This Article

Article-Type of This Article

Open-Access Policy of This Article

Times Cited Counts in Google of This Article

Number of Hits and Downloads for This Article

Total Article Views (122)

All Articles published online

The chart showing PDF series, HTML series, Figures (1-3) series, Tables (1-6) series.

Item

Count

PDF

HTML

Figures (1-3)

Tables (1-6)

Sum=46

Publishing Process of This Article

The chart showing Browse series, Download series.

Item

Count

Browse

Download

Sum=62

Oct 28, 2025 (publication date) through Oct 30, 2025

Times Cited of This Article

Times Cited (0)

Journal Information of This Article

Publication Name

World Journal of Gastroenterology

ISSN

1007-9327

Publisher of This Article

Baishideng Publishing Group Inc, 7041 Koll Center Parkway, Suite 160, Pleasanton, CA 94566, USA

Retrospective Cohort Study

World J Gastroenterol. Oct 28, 2025; 31(40): 111120
Published online Oct 28, 2025. doi: 10.3748/wjg.v31.i40.111120

Bridging the gap: Computer-aided detection and Yamada classification system matches expert performance

Lin Qiu, Jian Ding, Chun-Xiao Lai, Hui Yang, Feng Li, Zhi-Jian Li, Wen Wu, Gui-Ming Liu, Quan-Sheng Guan, Xi-Gang Zhang, Rui-Ya Zhang, Li-Zhi Yi, Zhi-Fang Zhao, Lv Deng, Wei-Jian Lun, Zhen-Yu Wang, Wei-Ming Lu, Wei-Guang Qiao, Su-Ling Wang, Si-Mei Chen, Wen-Qian Shen, Li-Min Cheng, Ben-Gui Zhu, Shun-Hui He, Jie Dai, Yang Bai

Lin Qiu, Jian Ding, Feng Li, Zhi-Jian Li, Wei-Guang Qiao, Shun-Hui He, Yang Bai, Department of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou 510515, Guangdong Province, China

Chun-Xiao Lai, Department of Digestive Endoscopy, The People’s Hospital of Baiyun District Guangzhou, Guangzhou 510515, Guangdong Province, China

Hui Yang, Department of Spleen and Stomach, Rizhao Hospital of Traditional Chinese Medicine, Shandong University of Traditional Chinese Medicine, Rizhao 518020, Shandong Province, China

Wen Wu, Department of Gastroenterology, Shanxi Academy of Traditional Chinese Medicine, Taiyuan 030000, Shanxi Province, China

Gui-Ming Liu, Quan-Sheng Guan, Department of Spleen and Stomach Diseases, Traditional Chinese Medicine Hospital of Shayang County, Jingmen 448000, Hubei Province, China

Xi-Gang Zhang, Department of Gastroenterology, Shenzhen Second People’s Hospital, Shenzhen 518000, Guangdong Province, China

Rui-Ya Zhang, Department of Gastroenterology, The Fifth Clinical Medical College of Shanxi Medical University, Taiyuan 030000, Shanxi Province, China

Li-Zhi Yi, Department of Gastroenterology, The People’s Hospital of Leshan, Leshan 614000, Sichuan Province, China

Zhi-Fang Zhao, Lv Deng, Department of Gastroenterology, People’s Hospital of Rongjiang County, Rongjiang 557200, Guizhou Province, China

Wei-Jian Lun, Department of Gastroenterology, People’s Hospital of Nanhai District, Foshan 52800, Guangdong Province, China

Zhen-Yu Wang, Department of Gastrointestinal Endoscopy, The First Affiliated Hospital of Shantou University Medical College, Shantou 515000, Guangdong Province, China

Wei-Ming Lu, Jie Dai, Suzhou Wellomen Information Technology Co., Ltd, Suzhou 510515, Jiangsu Province, China

Su-Ling Wang, Si-Mei Chen, Wen-Qian Shen, Li-Min Cheng, Department of Internal Medicine, Taihe People’s Hospital Baiyun District, Guangzhou 510000, Guangdong Province, China

Ben-Gui Zhu, Department of Gastroenterology, Rizhao Hospital of Traditional Chinese Medicine, Shandong University of Traditional Chinese Medicine, Rizhao 510515, Shandong Province, China

Co-first authors: Lin Qiu and Jian Ding.

Co-corresponding authors: Shun-Hui He and Yang Bai.

Author contributions: Bai Y, Qiu L, and Ding J designed the study; Bai Y and Qiu L coordinated the project; Qiu L, Ding J, Dai J, Li F, He SH, Li ZJ, Wu W, Yang H, and Guan QS performed data collection; Lai CX, Liu GM, Zhang XG, Zhang RY, Yi LZ, Zhao ZF, Deng L, Lun WJ, Wang ZY, Lu WM, Qiao WG, Wang SL, Chen SM, Shen WQ, Cheng LM, and Zhu BG analyzed the data; Qiu L and Ding J drafted the initial manuscript and made equal contributions as co-first authors; Bai Y revised the manuscript; He SH and Bai Y contributed equally as co-corresponding authors. All authors critically reviewed and approved the submitted version of the manuscript.

Supported by Science and Technology Projects in Guangzhou, No. 2023A04J2282.

Institutional review board statement: The study was approved by the Ethics Committee of Nanfang Hospital, Southern Medical University, No. NFEC-2024-333.

Informed consent statement: The informed consent was waived by the Institutional Review Board.

Conflict-of-interest statement: Dr. Yang reports grants from Science and Technology Projects in Guangzhou, during the conduct of the study.

STROBE statement: The authors have read the STROBE Statement-checklist of items, and the manuscript was prepared and revised according to the STROBE Statement-checklist of items.

Data sharing statement: The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.

Open Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/

Corresponding author: Yang Bai, PhD, Professor, Department of Gastroenterology, Nanfang Hospital, Southern Medical University, No. 1838 Guangzhou Avenue North, Guangzhou 510515, Guangdong Province, China. 13925001665@163.com

Received: June 25, 2025
Revised: August 11, 2025
Accepted: September 23, 2025
Published online: October 28, 2025
Processing time: 125 Days and 6.4 Hours

Abstract

BACKGROUND

Computer-aided diagnosis (CAD) may assist endoscopists in identifying and classifying polyps during colonoscopy for detecting colorectal cancer.

AIM

To build a system using CAD to detect and classify polyps based on the Yamada classification.

METHODS

A total of 24045 polyp and 72367 nonpolyp images were obtained. We established a computer-aided detection and Yamada classification model based on the YOLOv7 neural network algorithm. Frame-based and image-based evaluation metrics were employed to assess the performance.

RESULTS

Computer-aided detection and Yamada classification screened polyps with a precision of 96.7%, a recall of 95.8%, and an F1-score of 96.2%, outperforming those of all groups of endoscopists. In regard to the Yamada classification of polyps, the CAD system displayed a precision of 82.3%, a recall of 78.5%, and an F1-score of 80.2%, outperforming all levels of endoscopists. In addition, according to the image-based method, the CAD had an accuracy of 99.2%, a specificity of 99.5%, a sensitivity of 98.5%, a positive predictive value of 99.0%, a negative predictive value of 99.2% for polyp detection and an accuracy of 97.2%, a specificity of 98.4%, a sensitivity of 79.2%, a positive predictive value of 83.0%, and a negative predictive value of 98.4% for poly Yamada classification.

CONCLUSION

We developed a novel CAD system based on a deep neural network for polyp detection, and the Yamada classification outperformed that of nonexpert endoscopists. This CAD system could help community-based hospitals enhance their effectiveness in polyp detection and classification.

Keywords: Yamada classification; Endoscopy; Deep learning; Artificial intelligence; Computer-aided diagnosis

Core Tip: This study developed a novel deep learning (YOLOv7-based) computer-aided detection and classification system that significantly outperformed endoscopists in both detecting colorectal polyps (96.7% precision, 95.8% recall) and classifying them morphologically via the Yamada classification (80.2% F1-score). Achieving high image-based accuracy (detection: 99.2%; classification: 97.2%), this computer-aided detection and classification system offers a powerful tool to enhance polyp identification and characterization, particularly benefiting community hospital settings.