Detecting early gastric cancer: Comparison between the diagnostic ability of convolutional neural networks and endoscopists
-
- Yohei Ikenoyama
- Department of Gastroenterology Cancer Institute Hospital Japanese Foundation for Cancer Research Tokyo Japan
-
- Toshiaki Hirasawa
- Department of Gastroenterology Cancer Institute Hospital Japanese Foundation for Cancer Research Tokyo Japan
-
- Mitsuaki Ishioka
- Department of Gastroenterology Cancer Institute Hospital Japanese Foundation for Cancer Research Tokyo Japan
-
- Ken Namikawa
- Department of Gastroenterology Cancer Institute Hospital Japanese Foundation for Cancer Research Tokyo Japan
-
- Shoichi Yoshimizu
- Department of Gastroenterology Cancer Institute Hospital Japanese Foundation for Cancer Research Tokyo Japan
-
- Yusuke Horiuchi
- Department of Gastroenterology Cancer Institute Hospital Japanese Foundation for Cancer Research Tokyo Japan
-
- Akiyoshi Ishiyama
- Department of Gastroenterology Cancer Institute Hospital Japanese Foundation for Cancer Research Tokyo Japan
-
- Toshiyuki Yoshio
- Department of Gastroenterology Cancer Institute Hospital Japanese Foundation for Cancer Research Tokyo Japan
-
- Tomohiro Tsuchida
- Department of Gastroenterology Cancer Institute Hospital Japanese Foundation for Cancer Research Tokyo Japan
-
- Yoshinori Takeuchi
- Department of Biostatistics School of Public Health Graduate School of Medicine The University of Tokyo Tokyo Japan
-
- Satoki Shichijo
- Department of Gastrointestinal Oncology Osaka International Cancer Institute Osaka Japan
-
- Naoyuki Katayama
- Department of Hematology and Oncology Mie University Graduate School of Medicine Mie Japan
-
- Junko Fujisaki
- Department of Gastroenterology Cancer Institute Hospital Japanese Foundation for Cancer Research Tokyo Japan
-
- Tomohiro Tada
- AI Medical Service Inc Tokyo Japan
説明
<jats:sec><jats:title>Objectives</jats:title><jats:p>Detecting early gastric cancer is difficult, and it may even be overlooked by experienced endoscopists. Recently, artificial intelligence based on deep learning through convolutional neural networks (CNNs) has enabled significant advancements in the field of gastroenterology. However, it remains unclear whether a CNN can outperform endoscopists. In this study, we evaluated whether the performance of a CNN in detecting early gastric cancer is better than that of endoscopists.</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>The CNN was constructed using 13,584 endoscopic images from 2639 lesions of gastric cancer. Subsequently, its diagnostic ability was compared to that of 67 endoscopists using an independent test dataset (2940 images from 140 cases).</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>The average diagnostic time for analyzing 2940 test endoscopic images by the CNN and endoscopists were 45.5 ± 1.8 s and 173.0 ± 66.0 min, respectively. The sensitivity, specificity, and positive and negative predictive values for the CNN were 58.4%, 87.3%, 26.0%, and 96.5%, respectively. These values for the 67 endoscopists were 31.9%, 97.2%, 46.2%, and 94.9%, respectively. The CNN had a significantly higher sensitivity than the endoscopists (by 26.5%; 95% confidence interval, 14.9–32.5%).</jats:p></jats:sec><jats:sec><jats:title>Conclusion</jats:title><jats:p>The CNN detected more early gastric cancer cases in a shorter time than the endoscopists. The CNN needs further training to achieve higher diagnostic accuracy. However, a diagnostic support tool for gastric cancer using a CNN will be realized in the near future.</jats:p></jats:sec>
収録刊行物
-
- Digestive Endoscopy
-
Digestive Endoscopy 33 (1), 141-150, 2020-06-02
Wiley
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1360572092806359808
-
- ISSN
- 14431661
- 09155635
-
- データソース種別
-
- Crossref
- KAKEN