Advertisement
Gastrointestinal Endoscopy
Advanced searchSave search
Research Article|Articles in Press

Computer-Aided Diagnosis of Early-Stage Colorectal Cancer Using Non-Magnified Endoscopic White Light Images

Open AccessPublished:February 02, 2023DOI:https://doi.org/10.1016/j.gie.2023.01.050
Computer-Aided Diagnosis of Early-Stage Colorectal Cancer Using Non-Magnified Endoscopic White Light Images
Previous ArticleA Comparison between Traumatic and Atraumatic Over-The-Scope-Clips in patients with Duodenal Ulcer Bleeding: a Retrospective Analysis with Propensity-Score-based Matching
Next ArticleUtilization Pattern of Prophylactic Measures for Prevention of Post-ERCP Pancreatitis: A National Survey Study.
      This paper is only available as a PDF. To read, Please Download here.

      ABSTRACT

      Background and Aims

      Differentiation of colorectal cancers with deep submucosal invasion (T1b) from colorectal cancers with superficial invasion (T1a) or no invasion (Tis) is not straightforward. This study aimed to develop a computer aided diagnosis system (CADx) to establish the diagnosis of early-stage cancers using non-magnified endoscopic white light images alone.

      Methods

      A total of 1513 lesions (Tis 1074, T1a 145, T1b 294) in 5108 images were collected from 1470 patients at ten academic hospitals and assigned to training and testing datasets (3:1). The ResNet-50 network was used as the backbone to extract features from images. Over sampling and focal loss were used to compensate class imbalance of invasive stage. Diagnostic performance was assessed using the testing dataset including 403 CRCs with 1392 images. Two experts and two trainees read the identical testing dataset.

      Results

      At 90% cutoff for per lesion score, CADx showed the highest specificity of 94.4% [95% confidence interval: 91.3 - 96.6], with 59.8% [48.3 - 70.4] sensitivity and 87.3% [83.7 - 90.4] accuracy. The area under the characteristic curve was 85.1% [79.9 - 90.4] for CADx, 88.2% [83.7 - 92.8] for expert 1, 85.9% [80.9 - 90.9] for expert 2, 77.0% [71.5 - 82.4] for trainee 1 (vs. CADx: p=0.0076), and 66.2% [60.6 - 71.9] for trainee 2 (p<0.0001). The function was also confirmed on nine short videos.

      Conclusion

      CADx developed with endoscopic white light images showed excellent per lesion specificity and accuracy for T1b lesion diagnosis, equivalent to experts and superior to trainees. (UMIN000037053) (249 =<250 words)

      Graphical abstract

      Figure thumbnail fx1
      Graphical Abstract

      Key words

      Acronyms:

      AI (artificial intelligence), BLI (blue laser imaging), CADx (computer-aided diagnosis), CI (confidence interval), CRC (colorectal cancer), NBI (narrow band imaging), WLE (white light endoscopy)

      Article info

      Publication history

      Accepted: January 25, 2023
      Received in revised form: January 5, 2023
      Received: November 14, 2022

      Publication stage

      In Press Journal Pre-Proof

      Footnotes

      Daiki Nemoto and Zhe Guo contributed equally to this manuscript.

      Authors’ Contributions

      Study concept and design; D Nemoto, Z Guo, Y Nakajima, Y Hayashi, H Yamamoto, T Uraoka, N Tanaka, X Zhu, K Togashi

      Acquisition of data; D Nemoto, S Katsuki, T Takezawa, R Maemoto, K Kawasaki, K Inoue, T Akutagawa, H Tanaka, K Sato, T Omori, K Takanashi, Y Hayashi, Y Nakajima, Y Miyakura, T Hisabe, T Matsuda, K Togashi

      Analysis and interpretation of data; D Nemoto, Z Guo, S Katsuki, T Takezawa, R Maemoto, K Kawasaki, K Inoue, T Akutagawa, H Tanaka, K Sato, T Omori, K Takanashi, Y Hayashi, Y Nakajima, Y Miyakura, T Matsumoto, N Yoshida, M Esaki, T Uraoka, H Kato, Y Inoue, B Peng, R Zhang, H Yamamoto, N Tanaka, X Zhu, K Togashi

      Drafting of the manuscript; D Nemoto, Z Guo, Y Nakajima, AK Lefor, X Zhu, K Togashi

      Critical revision of the manuscript for important intellectual content; all authors

      Statistical analysis; D Nemoto, Z Guo, K Togashi, N Tanaka

      Obtained funding; X Zhu, K Togashi

      Technical, or material support; N Tanaka, B Peng, R Zhang, Z Guo, X Zhu

      Study supervision: N Tanaka, AK Lefor, H Yamamoto, X Zhu, K Togashi

      Data Transparency Statement

      All authors had access to the study data stored at the Individual Case Data Repository of University hospital Medical Information Network (ICDR-UMIN, http://www.umin.ac.jp/icdr/index.html) in spreadsheet format.

      Identification

      DOI: https://doi.org/10.1016/j.gie.2023.01.050

      Copyright

      © 2023 by the American Society for Gastrointestinal Endoscopy

      User license

      Creative Commons Attribution – NonCommercial – NoDerivs (CC BY-NC-ND 4.0) |
      How you can reuse Information Icon
      Creative Commons Attribution – NonCommercial – NoDerivs (CC BY-NC-ND 4.0)

      Permitted

      For non-commercial purposes:

      • Read, print & download
      • Redistribute or republish the final article
      • Text & data mine
      • Translate the article (private use only, not for distribution)
      • Reuse portions or extracts from the article in other works

      Not Permitted

      • Sell or re-use for commercial purposes
      • Distribute translations or adaptations of the article

      Elsevier's open access license policy

      ScienceDirect

      Access this article on ScienceDirect

      The content on this site is intended for healthcare professionals.


      We use cookies to help provide and enhance our service and tailor content. To update your cookie settings, please visit the Cookie Preference Center for this site.
      Copyright © 2023 Elsevier Inc. except certain content provided by third parties.


      RELX