Eintrag weiter verarbeiten
Buchumschlag von Stratification of gastric cancer risk using a deep neural network
Verfügbar über Open Access

Stratification of gastric cancer risk using a deep neural network

Gespeichert in:

Bibliographische Detailangaben
Zeitschriftentitel: JGH Open
Personen und Körperschaften: Nakahira, Hiroko, Ishihara, Ryu, Aoyama, Kazuharu, Kono, Mitsuhiro, Fukuda, Hiromu, Shimamoto, Yusaku, Nakagawa, Kentaro, Ohmori, Masayasu, Iwatsubo, Taro, Iwagami, Hiroyoshi, Matsuno, Kenshi, Inoue, Shuntaro, Matsuura, Noriko, Shichijo, Satoki, Maekawa, Akira, Kanesaka, Takashi, Yamamoto, Sachiko, Takeuchi, Yoji, Higashino, Koji, Uedo, Noriya, Matsunaga, Takashi, Tada, Tomohiro
In: JGH Open, 4, 2020, 3, S. 466-471
Medientyp: E-Article
Sprache: Englisch
veröffentlicht:
Wiley
Schlagwörter:
author_facet Nakahira, Hiroko
Ishihara, Ryu
Aoyama, Kazuharu
Kono, Mitsuhiro
Fukuda, Hiromu
Shimamoto, Yusaku
Nakagawa, Kentaro
Ohmori, Masayasu
Iwatsubo, Taro
Iwagami, Hiroyoshi
Matsuno, Kenshi
Inoue, Shuntaro
Matsuura, Noriko
Shichijo, Satoki
Maekawa, Akira
Kanesaka, Takashi
Yamamoto, Sachiko
Takeuchi, Yoji
Higashino, Koji
Uedo, Noriya
Matsunaga, Takashi
Tada, Tomohiro
Nakahira, Hiroko
Ishihara, Ryu
Aoyama, Kazuharu
Kono, Mitsuhiro
Fukuda, Hiromu
Shimamoto, Yusaku
Nakagawa, Kentaro
Ohmori, Masayasu
Iwatsubo, Taro
Iwagami, Hiroyoshi
Matsuno, Kenshi
Inoue, Shuntaro
Matsuura, Noriko
Shichijo, Satoki
Maekawa, Akira
Kanesaka, Takashi
Yamamoto, Sachiko
Takeuchi, Yoji
Higashino, Koji
Uedo, Noriya
Matsunaga, Takashi
Tada, Tomohiro
author Nakahira, Hiroko
Ishihara, Ryu
Aoyama, Kazuharu
Kono, Mitsuhiro
Fukuda, Hiromu
Shimamoto, Yusaku
Nakagawa, Kentaro
Ohmori, Masayasu
Iwatsubo, Taro
Iwagami, Hiroyoshi
Matsuno, Kenshi
Inoue, Shuntaro
Matsuura, Noriko
Shichijo, Satoki
Maekawa, Akira
Kanesaka, Takashi
Yamamoto, Sachiko
Takeuchi, Yoji
Higashino, Koji
Uedo, Noriya
Matsunaga, Takashi
Tada, Tomohiro
spellingShingle Nakahira, Hiroko
Ishihara, Ryu
Aoyama, Kazuharu
Kono, Mitsuhiro
Fukuda, Hiromu
Shimamoto, Yusaku
Nakagawa, Kentaro
Ohmori, Masayasu
Iwatsubo, Taro
Iwagami, Hiroyoshi
Matsuno, Kenshi
Inoue, Shuntaro
Matsuura, Noriko
Shichijo, Satoki
Maekawa, Akira
Kanesaka, Takashi
Yamamoto, Sachiko
Takeuchi, Yoji
Higashino, Koji
Uedo, Noriya
Matsunaga, Takashi
Tada, Tomohiro
JGH Open
Stratification of gastric cancer risk using a deep neural network
Gastroenterology
Hepatology
author_sort nakahira, hiroko
spelling Nakahira, Hiroko Ishihara, Ryu Aoyama, Kazuharu Kono, Mitsuhiro Fukuda, Hiromu Shimamoto, Yusaku Nakagawa, Kentaro Ohmori, Masayasu Iwatsubo, Taro Iwagami, Hiroyoshi Matsuno, Kenshi Inoue, Shuntaro Matsuura, Noriko Shichijo, Satoki Maekawa, Akira Kanesaka, Takashi Yamamoto, Sachiko Takeuchi, Yoji Higashino, Koji Uedo, Noriya Matsunaga, Takashi Tada, Tomohiro 2397-9070 2397-9070 Wiley Gastroenterology Hepatology http://dx.doi.org/10.1002/jgh3.12281 <jats:sec><jats:title>Background and Aim</jats:title><jats:p>Stratifying gastric cancer (GC) risk and endoscopy findings in high‐risk individuals may provide effective surveillance for GC. We developed a computerized image‐ analysis system for endoscopic images to stratify the risk of GC.</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>The system was trained using images taken during endoscopic examinations with non‐magnified white‐light imaging. Patients were classified as high‐risk (patients with GC), moderate‐risk (patients with current or past <jats:italic>Helicobacter pylori</jats:italic> infection or gastric atrophy), or low‐risk (patients with no history of <jats:italic>H. pylori</jats:italic> infection or gastric atrophy). After selection, 20,960, 17,404, and 68,920 images were collected as training images for the high‐, moderate‐, and low‐risk groups, respectively.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>Performance of the artificial intelligence (AI) system was evaluated by the prevalence of GC in each group using an independent validation dataset of patients who underwent endoscopic examination and <jats:italic>H. pylori</jats:italic> serum antibody testing. In total, 12,824 images from 454 patients were included in the analysis. The time required for diagnosing all the images was 345 seconds. The AI system diagnosed 46, 250, and 158 patients as low‐, moderate‐, and high risk, respectively. The prevalence of GC in the low‐, moderate‐, and high‐risk groups was 2.2, 8.8, and 16.4%, respectively (<jats:italic>P</jats:italic> = 0.0017). Three experienced endoscopists also successfully stratified the risk; however, interobserver agreement was not satisfactory (kappa value of 0.27, indicating fair agreement).</jats:p></jats:sec><jats:sec><jats:title>Conclusion</jats:title><jats:p>The current AI system detected significant differences in the prevalence of GC among the low‐, moderate‐, and high‐risk groups, suggesting its potential for stratifying GC risk.</jats:p></jats:sec> Stratification of gastric cancer risk using a deep neural network JGH Open
doi_str_mv 10.1002/jgh3.12281
facet_avail Online
Free
finc_class_facet Medizin
format ElectronicArticle
fullrecord blob:ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTAwMi9qZ2gzLjEyMjgx
id ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTAwMi9qZ2gzLjEyMjgx
institution DE-15
DE-Pl11
DE-Rs1
DE-105
DE-14
DE-Ch1
DE-L229
DE-D275
DE-Bn3
DE-Brt1
DE-Zwi2
DE-D161
DE-Gla1
DE-Zi4
imprint Wiley, 2020
imprint_str_mv Wiley, 2020
issn 2397-9070
issn_str_mv 2397-9070
language English
mega_collection Wiley (CrossRef)
match_str nakahira2020stratificationofgastriccancerriskusingadeepneuralnetwork
publishDateSort 2020
publisher Wiley
recordtype ai
record_format ai
series JGH Open
source_id 49
title Stratification of gastric cancer risk using a deep neural network
title_unstemmed Stratification of gastric cancer risk using a deep neural network
title_full Stratification of gastric cancer risk using a deep neural network
title_fullStr Stratification of gastric cancer risk using a deep neural network
title_full_unstemmed Stratification of gastric cancer risk using a deep neural network
title_short Stratification of gastric cancer risk using a deep neural network
title_sort stratification of gastric cancer risk using a deep neural network
topic Gastroenterology
Hepatology
url http://dx.doi.org/10.1002/jgh3.12281
publishDate 2020
physical 466-471
description <jats:sec><jats:title>Background and Aim</jats:title><jats:p>Stratifying gastric cancer (GC) risk and endoscopy findings in high‐risk individuals may provide effective surveillance for GC. We developed a computerized image‐ analysis system for endoscopic images to stratify the risk of GC.</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>The system was trained using images taken during endoscopic examinations with non‐magnified white‐light imaging. Patients were classified as high‐risk (patients with GC), moderate‐risk (patients with current or past <jats:italic>Helicobacter pylori</jats:italic> infection or gastric atrophy), or low‐risk (patients with no history of <jats:italic>H. pylori</jats:italic> infection or gastric atrophy). After selection, 20,960, 17,404, and 68,920 images were collected as training images for the high‐, moderate‐, and low‐risk groups, respectively.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>Performance of the artificial intelligence (AI) system was evaluated by the prevalence of GC in each group using an independent validation dataset of patients who underwent endoscopic examination and <jats:italic>H. pylori</jats:italic> serum antibody testing. In total, 12,824 images from 454 patients were included in the analysis. The time required for diagnosing all the images was 345 seconds. The AI system diagnosed 46, 250, and 158 patients as low‐, moderate‐, and high risk, respectively. The prevalence of GC in the low‐, moderate‐, and high‐risk groups was 2.2, 8.8, and 16.4%, respectively (<jats:italic>P</jats:italic> = 0.0017). Three experienced endoscopists also successfully stratified the risk; however, interobserver agreement was not satisfactory (kappa value of 0.27, indicating fair agreement).</jats:p></jats:sec><jats:sec><jats:title>Conclusion</jats:title><jats:p>The current AI system detected significant differences in the prevalence of GC among the low‐, moderate‐, and high‐risk groups, suggesting its potential for stratifying GC risk.</jats:p></jats:sec>
container_issue 3
container_start_page 466
container_title JGH Open
container_volume 4
format_de105 Article, E-Article
format_de14 Article, E-Article
format_de15 Article, E-Article
format_de520 Article, E-Article
format_de540 Article, E-Article
format_dech1 Article, E-Article
format_ded117 Article, E-Article
format_degla1 E-Article
format_del152 Buch
format_del189 Article, E-Article
format_dezi4 Article
format_dezwi2 Article, E-Article
format_finc Article, E-Article
format_nrw Article, E-Article
_version_ 1792344195575316484
geogr_code not assigned
last_indexed 2024-03-01T17:03:44.966Z
geogr_code_person not assigned
openURL url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=Stratification+of+gastric+cancer+risk+using+a+deep+neural+network&rft.date=2020-06-01&genre=article&issn=2397-9070&volume=4&issue=3&spage=466&epage=471&pages=466-471&jtitle=JGH+Open&atitle=Stratification+of+gastric+cancer+risk+using+a+deep+neural+network&aulast=Tada&aufirst=Tomohiro&rft_id=info%3Adoi%2F10.1002%2Fjgh3.12281&rft.language%5B0%5D=eng
SOLR
_version_ 1792344195575316484
author Nakahira, Hiroko, Ishihara, Ryu, Aoyama, Kazuharu, Kono, Mitsuhiro, Fukuda, Hiromu, Shimamoto, Yusaku, Nakagawa, Kentaro, Ohmori, Masayasu, Iwatsubo, Taro, Iwagami, Hiroyoshi, Matsuno, Kenshi, Inoue, Shuntaro, Matsuura, Noriko, Shichijo, Satoki, Maekawa, Akira, Kanesaka, Takashi, Yamamoto, Sachiko, Takeuchi, Yoji, Higashino, Koji, Uedo, Noriya, Matsunaga, Takashi, Tada, Tomohiro
author_facet Nakahira, Hiroko, Ishihara, Ryu, Aoyama, Kazuharu, Kono, Mitsuhiro, Fukuda, Hiromu, Shimamoto, Yusaku, Nakagawa, Kentaro, Ohmori, Masayasu, Iwatsubo, Taro, Iwagami, Hiroyoshi, Matsuno, Kenshi, Inoue, Shuntaro, Matsuura, Noriko, Shichijo, Satoki, Maekawa, Akira, Kanesaka, Takashi, Yamamoto, Sachiko, Takeuchi, Yoji, Higashino, Koji, Uedo, Noriya, Matsunaga, Takashi, Tada, Tomohiro, Nakahira, Hiroko, Ishihara, Ryu, Aoyama, Kazuharu, Kono, Mitsuhiro, Fukuda, Hiromu, Shimamoto, Yusaku, Nakagawa, Kentaro, Ohmori, Masayasu, Iwatsubo, Taro, Iwagami, Hiroyoshi, Matsuno, Kenshi, Inoue, Shuntaro, Matsuura, Noriko, Shichijo, Satoki, Maekawa, Akira, Kanesaka, Takashi, Yamamoto, Sachiko, Takeuchi, Yoji, Higashino, Koji, Uedo, Noriya, Matsunaga, Takashi, Tada, Tomohiro
author_sort nakahira, hiroko
container_issue 3
container_start_page 466
container_title JGH Open
container_volume 4
description <jats:sec><jats:title>Background and Aim</jats:title><jats:p>Stratifying gastric cancer (GC) risk and endoscopy findings in high‐risk individuals may provide effective surveillance for GC. We developed a computerized image‐ analysis system for endoscopic images to stratify the risk of GC.</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>The system was trained using images taken during endoscopic examinations with non‐magnified white‐light imaging. Patients were classified as high‐risk (patients with GC), moderate‐risk (patients with current or past <jats:italic>Helicobacter pylori</jats:italic> infection or gastric atrophy), or low‐risk (patients with no history of <jats:italic>H. pylori</jats:italic> infection or gastric atrophy). After selection, 20,960, 17,404, and 68,920 images were collected as training images for the high‐, moderate‐, and low‐risk groups, respectively.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>Performance of the artificial intelligence (AI) system was evaluated by the prevalence of GC in each group using an independent validation dataset of patients who underwent endoscopic examination and <jats:italic>H. pylori</jats:italic> serum antibody testing. In total, 12,824 images from 454 patients were included in the analysis. The time required for diagnosing all the images was 345 seconds. The AI system diagnosed 46, 250, and 158 patients as low‐, moderate‐, and high risk, respectively. The prevalence of GC in the low‐, moderate‐, and high‐risk groups was 2.2, 8.8, and 16.4%, respectively (<jats:italic>P</jats:italic> = 0.0017). Three experienced endoscopists also successfully stratified the risk; however, interobserver agreement was not satisfactory (kappa value of 0.27, indicating fair agreement).</jats:p></jats:sec><jats:sec><jats:title>Conclusion</jats:title><jats:p>The current AI system detected significant differences in the prevalence of GC among the low‐, moderate‐, and high‐risk groups, suggesting its potential for stratifying GC risk.</jats:p></jats:sec>
doi_str_mv 10.1002/jgh3.12281
facet_avail Online, Free
finc_class_facet Medizin
format ElectronicArticle
format_de105 Article, E-Article
format_de14 Article, E-Article
format_de15 Article, E-Article
format_de520 Article, E-Article
format_de540 Article, E-Article
format_dech1 Article, E-Article
format_ded117 Article, E-Article
format_degla1 E-Article
format_del152 Buch
format_del189 Article, E-Article
format_dezi4 Article
format_dezwi2 Article, E-Article
format_finc Article, E-Article
format_nrw Article, E-Article
geogr_code not assigned
geogr_code_person not assigned
id ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTAwMi9qZ2gzLjEyMjgx
imprint Wiley, 2020
imprint_str_mv Wiley, 2020
institution DE-15, DE-Pl11, DE-Rs1, DE-105, DE-14, DE-Ch1, DE-L229, DE-D275, DE-Bn3, DE-Brt1, DE-Zwi2, DE-D161, DE-Gla1, DE-Zi4
issn 2397-9070
issn_str_mv 2397-9070
language English
last_indexed 2024-03-01T17:03:44.966Z
match_str nakahira2020stratificationofgastriccancerriskusingadeepneuralnetwork
mega_collection Wiley (CrossRef)
physical 466-471
publishDate 2020
publishDateSort 2020
publisher Wiley
record_format ai
recordtype ai
series JGH Open
source_id 49
spelling Nakahira, Hiroko Ishihara, Ryu Aoyama, Kazuharu Kono, Mitsuhiro Fukuda, Hiromu Shimamoto, Yusaku Nakagawa, Kentaro Ohmori, Masayasu Iwatsubo, Taro Iwagami, Hiroyoshi Matsuno, Kenshi Inoue, Shuntaro Matsuura, Noriko Shichijo, Satoki Maekawa, Akira Kanesaka, Takashi Yamamoto, Sachiko Takeuchi, Yoji Higashino, Koji Uedo, Noriya Matsunaga, Takashi Tada, Tomohiro 2397-9070 2397-9070 Wiley Gastroenterology Hepatology http://dx.doi.org/10.1002/jgh3.12281 <jats:sec><jats:title>Background and Aim</jats:title><jats:p>Stratifying gastric cancer (GC) risk and endoscopy findings in high‐risk individuals may provide effective surveillance for GC. We developed a computerized image‐ analysis system for endoscopic images to stratify the risk of GC.</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>The system was trained using images taken during endoscopic examinations with non‐magnified white‐light imaging. Patients were classified as high‐risk (patients with GC), moderate‐risk (patients with current or past <jats:italic>Helicobacter pylori</jats:italic> infection or gastric atrophy), or low‐risk (patients with no history of <jats:italic>H. pylori</jats:italic> infection or gastric atrophy). After selection, 20,960, 17,404, and 68,920 images were collected as training images for the high‐, moderate‐, and low‐risk groups, respectively.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>Performance of the artificial intelligence (AI) system was evaluated by the prevalence of GC in each group using an independent validation dataset of patients who underwent endoscopic examination and <jats:italic>H. pylori</jats:italic> serum antibody testing. In total, 12,824 images from 454 patients were included in the analysis. The time required for diagnosing all the images was 345 seconds. The AI system diagnosed 46, 250, and 158 patients as low‐, moderate‐, and high risk, respectively. The prevalence of GC in the low‐, moderate‐, and high‐risk groups was 2.2, 8.8, and 16.4%, respectively (<jats:italic>P</jats:italic> = 0.0017). Three experienced endoscopists also successfully stratified the risk; however, interobserver agreement was not satisfactory (kappa value of 0.27, indicating fair agreement).</jats:p></jats:sec><jats:sec><jats:title>Conclusion</jats:title><jats:p>The current AI system detected significant differences in the prevalence of GC among the low‐, moderate‐, and high‐risk groups, suggesting its potential for stratifying GC risk.</jats:p></jats:sec> Stratification of gastric cancer risk using a deep neural network JGH Open
spellingShingle Nakahira, Hiroko, Ishihara, Ryu, Aoyama, Kazuharu, Kono, Mitsuhiro, Fukuda, Hiromu, Shimamoto, Yusaku, Nakagawa, Kentaro, Ohmori, Masayasu, Iwatsubo, Taro, Iwagami, Hiroyoshi, Matsuno, Kenshi, Inoue, Shuntaro, Matsuura, Noriko, Shichijo, Satoki, Maekawa, Akira, Kanesaka, Takashi, Yamamoto, Sachiko, Takeuchi, Yoji, Higashino, Koji, Uedo, Noriya, Matsunaga, Takashi, Tada, Tomohiro, JGH Open, Stratification of gastric cancer risk using a deep neural network, Gastroenterology, Hepatology
title Stratification of gastric cancer risk using a deep neural network
title_full Stratification of gastric cancer risk using a deep neural network
title_fullStr Stratification of gastric cancer risk using a deep neural network
title_full_unstemmed Stratification of gastric cancer risk using a deep neural network
title_short Stratification of gastric cancer risk using a deep neural network
title_sort stratification of gastric cancer risk using a deep neural network
title_unstemmed Stratification of gastric cancer risk using a deep neural network
topic Gastroenterology, Hepatology
url http://dx.doi.org/10.1002/jgh3.12281