Artificial intelligence for the detection of esophageal and esophagogastric junctional adenocarcinoma.
Adenocarcinoma
/ diagnostic imaging
Adult
Aged
Aged, 80 and over
Artificial Intelligence
Asia
Deep Learning
Early Detection of Cancer
/ methods
Esophageal Neoplasms
/ diagnostic imaging
Esophagogastric Junction
/ diagnostic imaging
Female
Humans
Image Processing, Computer-Assisted
/ methods
Male
Middle Aged
Sensitivity and Specificity
Stomach Neoplasms
/ diagnostic imaging
AI
EGJ
adenocarcinoma
artificial intelligence
detection
esophageal
Journal
Journal of gastroenterology and hepatology
ISSN: 1440-1746
Titre abrégé: J Gastroenterol Hepatol
Pays: Australia
ID NLM: 8607909
Informations de publication
Date de publication:
Jan 2021
Jan 2021
Historique:
received:
24
03
2020
revised:
03
05
2020
accepted:
05
06
2020
pubmed:
9
6
2020
medline:
6
7
2021
entrez:
9
6
2020
Statut:
ppublish
Résumé
Conventional endoscopy for the early detection of esophageal and esophagogastric junctional adenocarcinoma (E/J cancer) is limited because early lesions are asymptomatic, and the associated changes in the mucosa are subtle. There are no reports on artificial intelligence (AI) diagnosis for E/J cancer from Asian countries. Therefore, we aimed to develop a computerized image analysis system using deep learning for the detection of E/J cancers. A total of 1172 images from 166 pathologically proven superficial E/J cancer cases and 2271 images of normal mucosa in esophagogastric junctional from 219 cases were used as the training image data. A total of 232 images from 36 cancer cases and 43 non-cancerous cases were used as the validation test data. The same validation test data were diagnosed by 15 board-certified specialists (experts). The sensitivity, specificity, and accuracy of the AI system were 94%, 42%, and 66%, respectively, and that of the experts were 88%, 43%, and 63%, respectively. The sensitivity of the AI system was favorable, while its specificity for non-cancerous lesions was similar to that of the experts. Interobserver agreement among the experts for detecting superficial E/J was fair (Fleiss' kappa = 0.26, z = 20.4, P < 0.001). Our AI system achieved high sensitivity and acceptable specificity for the detection of E/J cancers and may be a good supporting tool for the screening of E/J cancers.
Sections du résumé
BACKGROUND AND AIM
OBJECTIVE
Conventional endoscopy for the early detection of esophageal and esophagogastric junctional adenocarcinoma (E/J cancer) is limited because early lesions are asymptomatic, and the associated changes in the mucosa are subtle. There are no reports on artificial intelligence (AI) diagnosis for E/J cancer from Asian countries. Therefore, we aimed to develop a computerized image analysis system using deep learning for the detection of E/J cancers.
METHODS
METHODS
A total of 1172 images from 166 pathologically proven superficial E/J cancer cases and 2271 images of normal mucosa in esophagogastric junctional from 219 cases were used as the training image data. A total of 232 images from 36 cancer cases and 43 non-cancerous cases were used as the validation test data. The same validation test data were diagnosed by 15 board-certified specialists (experts).
RESULTS
RESULTS
The sensitivity, specificity, and accuracy of the AI system were 94%, 42%, and 66%, respectively, and that of the experts were 88%, 43%, and 63%, respectively. The sensitivity of the AI system was favorable, while its specificity for non-cancerous lesions was similar to that of the experts. Interobserver agreement among the experts for detecting superficial E/J was fair (Fleiss' kappa = 0.26, z = 20.4, P < 0.001).
CONCLUSIONS
CONCLUSIONS
Our AI system achieved high sensitivity and acceptable specificity for the detection of E/J cancers and may be a good supporting tool for the screening of E/J cancers.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
131-136Informations de copyright
© 2020 Journal of Gastroenterology and Hepatology Foundation and John Wiley & Sons Australia, Ltd.
Références
Blot WJ, Devesa SS, Kneller RW, Fraumeni JF. Rising incidence of adenocarcinoma of the esophagus and gastric cardia. JAMA 1991; 265: 1287-1289.
Hansson LE, Sparen P, Nyren O. Increasing incidence of carcinoma of the gastric cardia in Sweden from 1970 to 1985. Br. J. Surg. 1993; 80: 374-377.
Bytzer P, Christensen PB, Damkier P et al. Adenocarcinoma of the esophagus and Barrett's esophagus: a population-based study. Am. J. Gastroenterol. 1999; 94: 86-91.
Parfitt JR, Miladinovic Z, Driman DK. Increasing incidence of adenocarcinoma of the gastroesophageal junction and distal stomach in Canada-an epidemiological study from 1964 to 2002. Can. J. Gastroenterol. 2006; 20: 271-276.
Kusano C, Gotoda T, Khor CJ et al. Changing trends in the proportion of adenocarcinoma of the esophagogastric junction in a large tertiary referral center in Japan. J. Gastroenterol. Hepatol. 2008; 23: 1662-1665.
Matsuno K, Ishihara R, Ohmori M et al. Time trends in the incidence of esophageal adenocarcinoma, gastric adenocarcinoma, and superficial esophagogastric junction adenocarcinoma. J. Gastroenterol. 2019; 54: 784-791.
Goda K, Singh R, Oda I et al. Current status of endoscopic diagnosis and treatment of superficial Barrett's adenocarcinoma in Asia-Pacific region. Dig Endosc 2013; 25: 146-150.
Spechler SJ, Sharma P, Souza RF, Inadomi JM, Shaheen NJ. American Gastroenterological Association medical position statement on the management of Barrett's esophagus. Gastroenterology 2011; 140: 1084-1091.
Sharma P, Bergman JJ, Goda K et al. Development and validation of a classification system to identify high-grade dysplasia and esophageal adenocarcinoma in Barrett's esophagus using barrow-band imaging. Gastroenterology 2016; 150: 591-598.
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.
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.
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.
Ghatwary N, Zolgharni M, Ye X. Early esophageal adenocarcinoma detection using deep learning methods. Int. J. Comput. Assist. Radiol. Surg. 2019; 14: 611-621.
Ebigbo A, Mendel R, Probst A et al. Real-time use of artificial intelligence in the evaluation of cancer in Barrett's oesophagus. Gut 2020; 69: 615-616.
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.
Hasegawa S, Yoshikawa T, Cho H, Tsuburaya A, Kobayashi O. Is adenocarcinoma of the esophagogastric junction different between Japan and western countries? The incidence and clinicopathological features at a Japanese high-volume cancercenter. World J Surg 2009; 33: 95-103.
Yamasaki A, Shimizu T, Kawachi H et al. Endoscopic features of esophageal adenocarcinoma derived from short-segment versus long-segment Barrett's esophagus. J Gastroenterol Hepatol 2020; 35: 211-217.
Anonymous. Japanese Classification of Esophageal Cancer, 11th Edition: part I. Esophagus 2017; 14: 1-36.
Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics 1977; 33: 159-174.
Kanda Y. Investigation of the freely available easy-to-use software 'EZR' for medical statistics. Bone Marrow Transplant. 2013; 48: 452-458.
Ohmori M, Ishihara R, Aoyama K et al. Endoscopic detection and differentiation of esophageal lesions using a deep neural network. Gastrointest Endosc 2019. https://doi.org/10.1016/j.gie.2019.09.034
Takemura Y, Yoshida S, Tanaka S et al. Quantitative analysis and development of a computer-aided system for identification of regular pit patterns of colorectal lesions. Gastrointest. Endosc. 2010; 72: 1047-1051.
Kominami Y, Yoshida S, Tanaka S et al. Computer-aided diagnosis of colorectal polyp histology by using a real-time image recognition system and narrow-band imaging magnifying colonoscopy. Gastrointest. Endosc. 2016; 83: 643-649.
Mori Y, Kudo SE, Chiu PW et al. Impact of an automated system for endocytoscopic diagnosis of small colorectal lesions: an international web-based study. Endoscopy 2016; 48: 1110-1118.
Komeda Y, Handa H, Watanabe T et al. Computer-aided diagnosis based on convolutional neural network system for colorectal polyp classification: preliminary experience. Oncology 2017; 93: 30-34.
Horiuchi Y, Aoyama K, Tokai Y et al. Convolutional neural network for differentiating gastric cancer from gastritis using magnified endoscopy with narrow band imaging. Dig Dis Sci 2019. https://doi.org/10.1007/s10620-019-05862-6