Endoscopic detection and differentiation of esophageal lesions using a deep neural network

Autor: Tomohiro Tada, Satoki Shichijo, Kenji Aoi, Katsumi Yamamoto, Hiroyoshi Iwagami, Ryu Ishihara, Takuya Inoue, Masanori Nakahara, Koji Nagaike, Kazuharu Aoyama, Noriko Matsuura, Masayasu Ohmori, Kentaro Nakagawa, Hiroyuki Okada
Rok vydání: 2019
Předmět:
Adult
Male
medicine.medical_specialty
Esophageal Neoplasms
Validation test
Esophageal Diseases
Esophageal lesions
Esophageal squamous cell carcinoma
Sensitivity and Specificity
03 medical and health sciences
Narrow Band Imaging
0302 clinical medicine
Deep Learning
Esophagus
Normal esophagus
medicine
Image Processing
Computer-Assisted
Humans
Radiology
Nuclear Medicine and imaging
Neoplasm Invasiveness
Esophageal SCC
Aged
Aged
80 and over
Observer Variation
Narrow-band imaging
medicine.diagnostic_test
business.industry
Significant difference
Optical Imaging
Gastroenterology
Reproducibility of Results
Middle Aged
Endoscopy
030220 oncology & carcinogenesis
030211 gastroenterology & hepatology
Female
Radiology
Esophageal Squamous Cell Carcinoma
Neural Networks
Computer
business
Precancerous Conditions
Zdroj: Gastrointestinal endoscopy. 91(2)
ISSN: 1097-6779
Popis: Background and Aims Diagnosing esophageal squamous cell carcinoma (SCC) depends on individual physician expertise and may be subject to interobserver variability. Therefore, we developed a computerized image-analysis system to detect and differentiate esophageal SCC. Methods A total of 9591 nonmagnified endoscopy (non-ME) and 7844 ME images of pathologically confirmed superficial esophageal SCCs and 1692 non-ME and 3435 ME images from noncancerous lesions or normal esophagus were used as training image data. Validation was performed using 255 non-ME white-light images, 268 non-ME narrow-band images/blue-laser images, and 204 ME narrow-band images/blue-laser images from 135 patients. The same validation test data were diagnosed by 15 board-certified specialists (experienced endoscopists). Results Regarding diagnosis by non-ME with narrow-band imaging/blue-laser imaging, the sensitivity, specificity, and accuracy were 100%, 63%, and 77%, respectively, for the artificial intelligence (AI) system and 92%, 69%, and 78%, respectively, for the experienced endoscopists. Regarding diagnosis by non-ME with white-light imaging, the sensitivity, specificity, and accuracy were 90%, 76%, and 81%, respectively, for the AI system and 87%, 67%, and 75%, respectively, for the experienced endoscopists. Regarding diagnosis by ME, the sensitivity, specificity, and accuracy were 98%, 56%, and 77%, respectively, for the AI system and 83%, 70%, and 76%, respectively, for the experienced endoscopists. There was no significant difference in the diagnostic performance between the AI system and the experienced endoscopists. Conclusions Our AI system showed high sensitivity for detecting SCC by non-ME and high accuracy for differentiating SCC from noncancerous lesions by ME.
Databáze: OpenAIRE
Externí odkaz: