Download PDF
Endoscopy 2022; 54(12): 1191-1197
DOI: 10.1055/a-1811-9407
Original article

Artificial intelligence-assisted staging in Barrett’s carcinoma

Mate Knabe 
1   Department of Gastroenterology, Frankfurt University Hospital, Frankfurt, Germany
,
Lukas Welsch
1   Department of Gastroenterology, Frankfurt University Hospital, Frankfurt, Germany
,
Tobias Blasberg
2   Department of Gastroenterology, Sana Klinikum GmbH Offenbach, Offenbach, Germany
,
Elisa Müller
1   Department of Gastroenterology, Frankfurt University Hospital, Frankfurt, Germany
,
Myriam Heilani
1   Department of Gastroenterology, Frankfurt University Hospital, Frankfurt, Germany
,
Christoph Bergen
3   HMS Analytical Software GmbH, HMS Analytical Software, Heidelberg, Germany
,
Eva Herrmann
4   Department of Medicine, Institute of Biostatistics and Mathematical Modeling, Goethe University of Frankfurt, Frankfurt, Germany
,
Andrea May
5   Department of Medicine I, Asklepios Paulinen Klinik Wiesbaden, Wiesbaden, Germany
› Author Affiliations
› Further Information
Also available at
    Permissions and Reprints

Abstract

Background Artificial intelligence (AI) is increasingly being used to detect neoplasia and interpret endoscopic images. The T stage of Barrett’s carcinoma is a major criterion for subsequent treatment decisions. Although endoscopic ultrasound is still the standard for preoperative staging, its value is debatable. Novel tools are required to assist with staging, to optimize results. This study aimed to investigate the accuracy of T stage of Barrett’s carcinoma by an AI system based on endoscopic images.

Methods 1020 images (minimum one per patient, maximum three) from 577 patients with Barrett’s adenocarcinoma were used for training and internal validation of a convolutional neural network. In all, 821 images were selected to train the model and 199 images were used for validation.

Results AI recognized Barrett’s mucosa without neoplasia with an accuracy of 85 % (95 %CI 82.7–87.1). Mucosal cancer was identified with a sensitivity of 72 % (95 %CI 67.5–76.4), specificity of 64 % (95 %CI 60.0–68.4), and accuracy of 68 % (95 %CI 64.6–70.7). The sensitivity, specificity, and accuracy for early Barrett’s neoplasia < T1b sm2 were 57 % (95 %CI 51.8–61.0), 77 % (95 %CI 72.3–80.2), and 67 % (95 %CI 63.4–69.5), respectively. More advanced stages (T3/T4) were diagnosed correctly with a sensitivity of 71 % (95 %CI 65.1–76.7) and specificity of 73 % (95 %CI 69.7–76.5). The overall accuracy was 73 % (95 %CI 69.6–75.5).

Conclusions The AI system identified esophageal cancer with high accuracy, suggesting its potential to assist endoscopists in clinical decision making.



Publication History

Received: 09 September 2021

Accepted after revision: 30 March 2022

Accepted Manuscript online:
30 March 2022

Article published online:
03 June 2022

© 2022. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 

  • References

  • 1 Wang P, Xiao X, Glissen Brown JR. et al. Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy. Nat Biomed Eng 2018; 2: 741-748
    CrossrefPubMedGoogle Scholar
  • 2 Wang P, Berzin TM, Glissen Brown JR. et al. Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study. Gut 2019; 68: 1813-1819
    CrossrefPubMedGoogle Scholar
  • 3 Hirasawa T, Aoyama K, Tanimoto T. et al. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images. Gastric Cancer 2018; 21: 653-660
    CrossrefPubMedGoogle Scholar
  • 4 Pech O, Bollschweiler E, Manner H. et al. Comparison between endoscopic and surgical resection of mucosal esophageal adenocarcinoma in Barrett’s esophagus at two high-volume centers. Ann Surg 2011; 254: 67-72
    CrossrefPubMedGoogle Scholar
  • 5 Stein HJ, von Rahden BH, Siewert JR. Survival after oesophagectomy for cancer of the oesophagus. Langenbecks Arch Surg 2005; 390: 280-285
    CrossrefPubMedGoogle Scholar
  • 6 Holscher AH, Bollschweiler E, Schneider PM. et al. Early adenocarcinoma in Barrett’s oesophagus. Br J Surg 1997; 84: 1470-1473
    PubMedGoogle Scholar
  • 7 Coletta M, Sami SS, Nachiappan A. et al. Acetic acid chromoendoscopy for the diagnosis of early neoplasia and specialized intestinal metaplasia in Barrett’s esophagus: a meta-analysis. Gastrointest Endosc 2016; 83: 57-67
    CrossrefPubMedGoogle Scholar
  • 8 Alvarez Herrero L, Curvers WL, van Vilsteren FG. et al. Validation of the Prague C&M classification of Barrett’s esophagus in clinical practice. Endoscopy 2013; 45: 876-882
    Article in Thieme ConnectPubMedGoogle Scholar
  • 9 Shaheen NJ, Falk GW, Iyer PG. et al. ACG Clinical Guideline: Diagnosis and management of Barrett’s esophagus. Am J Gastroenterol 2016; 111: 30-50
    CrossrefPubMedGoogle Scholar
  • 10 Shah MA, Kennedy EB, Catenacci DV. et al. Treatment of locally advanced esophageal carcinoma: ASCO guideline. J Clin Oncol 2020; 38: 2677-2694
    CrossrefPubMedGoogle Scholar
  • 11 Qumseya BJ, Brown J, Abraham M. et al. Diagnostic performance of EUS in predicting advanced cancer among patients with Barrett’s esophagus and high-grade dysplasia/early adenocarcinoma: systematic review and meta-analysis. Gastrointest Endosc 2015; 81: 865-874
    CrossrefPubMedGoogle Scholar
  • 12 Pech O, May A, Manner H. et al. Long-term efficacy and safety of endoscopic resection for patients with mucosal adenocarcinoma of the esophagus. Gastroenterology 2014; 146: 652-660
    CrossrefPubMedGoogle Scholar
  • 13 Horie Y, Yoshio T, Aoyama K. et al. Diagnostic outcomes of esophageal cancer by artificial intelligence using convolutional neural networks. Gastrointest Endosc 2019; 89: 25-32
    CrossrefPubMedGoogle Scholar
  • 14 Ebigbo A, Mendel R, Ruckert T. et al. Endoscopic prediction of submucosal invasion in Barrett’s cancer with the use of artificial intelligence: a pilot Study. Endoscopy 2021; 53: 878-883
    Google Scholar
  • 15 Pech O, Gunter E, Dusemund F. et al. Value of high-frequency miniprobes and conventional radial endoscopic ultrasound in the staging of early Barrett’s carcinoma. Endoscopy 2010; 42: 98-103
    Article in Thieme ConnectPubMedGoogle Scholar
  • 16 Bartel MJ, Wallace TM, Gomez-Esquivel RD. et al. Role of EUS in patients with suspected Barrett’s esophagus with high-grade dysplasia or early esophageal adenocarcinoma: impact on endoscopic therapy. Gastrointest Endosc 2017; 86: 292-298
    CrossrefPubMedGoogle Scholar
  • 17 Hassan C, Spadaccini M, Iannone A. et al. Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis. Gastrointest Endosc 2021; 93: 77-85
    CrossrefPubMedGoogle Scholar
  • 18 de Groof J, van der Sommen F, van der Putten J. et al. The Argos project: the development of a computer-aided detection system to improve detection of Barrett’s neoplasia on white light endoscopy. United European Gastroenterol J 2019; 7: 538-547
    CrossrefPubMedGoogle Scholar
  • 19 Ebigbo A, Mendel R, Probst A. et al. Computer-aided diagnosis using deep learning in the evaluation of early oesophageal adenocarcinoma. Gut 2019; 68: 1143-1145
    CrossrefPubMedGoogle Scholar
  • 20 de Groof AJ, Struyvenberg MR, van der Putten J. et al. Deep-learning system detects neoplasia in patients with Barrett’s esophagus with higher accuracy than endoscopists in a multistep training and validation study with benchmarking. Gastroenterology 2020; 158: 915-929
    CrossrefPubMedGoogle Scholar
  • 21 Tokai Y, Yoshio T, Aoyama K. et al. Application of artificial intelligence using convolutional neural networks in determining the invasion depth of esophageal squamous cell carcinoma. Esophagus 2020; 17: 250-256
    CrossrefPubMedGoogle Scholar
  • 22 Zhu Y, Wang QC, Xu MD. et al. Application of convolutional neural network in the diagnosis of the invasion depth of gastric cancer based on conventional endoscopy. Gastrointest Endosc 2019; 89: 806-815
    CrossrefPubMedGoogle Scholar