Comparative study on artificial intelligence systems for detecting early esophageal squamous cell carcinoma between narrow-band and white-light imaging

BACKGROUND Non-magnifying endoscopy with narrow-band imaging (NM-NBI) has been frequently used in routine screening of esophagus squamous cell carcinoma (ESCC). The performance of NBI for screening of early ESCC is, however, significantly affected by operator experience. Artificial intelligence may be a unique approach to compensate for the lack of operator experience. AIM To construct a computer-aided detection (CAD) system for application in NM-NBI to identify early ESCC and to compare it with our previously reported CAD system with endoscopic white-light imaging (WLI). METHODS A total of 2167 abnormal NM-NBI images of early ESCC and 2568 normal images were collected from three institutions (Zhongshan Hospital of Fudan University, Xuhui Hospital, and Kiang Wu Hospital) as the training dataset, and 316 pairs of images, each pair including images obtained by WLI and NBI (same part), were collected for validation. Twenty endoscopists participated in this study to review the validation images with or without the assistance of the CAD systems. The diagnostic results of the two CAD systems and improvement in diagnostic efficacy of endoscopists were compared in terms of sensitivity, specificity, accuracy, positive predictive value, and negative predictive value. RESULTS The area under receiver operating characteristic curve for CAD-NBI was 0.9761. For the validation dataset, the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of CAD-NBI were 91.0%, 96.7%, 94.3%, 95.3%, and 93.6%, respectively, while those of CAD-WLI were 98.5%, 83.1%, 89.5%, 80.8%, and 98.7%, respectively. CAD-NBI showed superior accuracy and specificity than CAD-WLI (P = 0.028 and P ≤ 0.001, respectively), while CAD-WLI had higher sensitivity than CAD-NBI (P = 0.006). By using both CAD-WLI and CAD-NBI, the endoscopists could improve their diagnostic efficacy to the highest level, with accuracy, sensitivity, and specificity of 94.9%, 92.4%, and 96.7%, respectively. CONCLUSION The CAD-NBI system for screening early ESCC has higher accuracy and specificity than CAD-WLI. Endoscopists can achieve the best diagnostic efficacy using both CAD-WLI and CAD-NBI.

[1]  David S. Melnick,et al.  International evaluation of an AI system for breast cancer screening , 2020, Nature.

[2]  Y. Zhong,et al.  Using deep learning system in endoscopy for screening of early esophageal squamous cell carcinoma (with video). , 2019, Gastrointestinal endoscopy.

[3]  Rong Lin,et al.  Gastroenterologist-level Identification of Small Bowel Diseases and Normal Variants by Capsule Endoscopy Using a Deep-learning Model. , 2019, Gastroenterology.

[4]  Jing Cheng,et al.  Application of convolutional neural network in the diagnosis of the invasion depth of gastric cancer based on conventional endoscopy. , 2019, Gastrointestinal endoscopy.

[5]  E. Vazquez-Sequeiros,et al.  Rate of missed oesophageal cancer at routine endoscopy and survival outcomes: A multicentric cohort study , 2019, United European gastroenterology journal.

[6]  Eric J Topol,et al.  High-performance medicine: the convergence of human and artificial intelligence , 2019, Nature Medicine.

[7]  Jie Xu,et al.  The practical implementation of artificial intelligence technologies in medicine , 2019, Nature Medicine.

[8]  Bin Sun,et al.  Computer-assisted diagnosis of early esophageal squamous cell carcinoma using narrow-band imaging magnifying endoscopy , 2018, Endoscopy.

[9]  K. Mori,et al.  Real-Time Use of Artificial Intelligence in Identification of Diminutive Polyps During Colonoscopy , 2018, Annals of Internal Medicine.

[10]  Zhonghu He,et al.  Efficacy of endoscopic screening for esophageal cancer in China (ESECC): design and preliminary results of a population-based randomised controlled trial , 2018, Gut.

[11]  Henry Horng-Shing Lu,et al.  Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis. , 2017, Gastroenterology.

[12]  W. Bernardo,et al.  Narrow band imaging versus lugol chromoendoscopy to diagnose squamous cell carcinoma of the esophagus: a systematic review and meta-analysis , 2017, BMC Cancer.

[13]  Zhi-Feng Chen,et al.  Long-Term Follow-Up of a Community Assignment, One-Time Endoscopic Screening Study of Esophageal Cancer in China. , 2015, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[14]  J. Ferlay,et al.  Global incidence of oesophageal cancer by histological subtype in 2012 , 2014, Gut.

[15]  Masatsugu Shiba,et al.  Usefulness of Non-Magnifying Narrow-Band Imaging in Screening of Early Esophageal Squamous Cell Carcinoma: A Prospective Comparative Study Using Propensity Score Matching , 2014, The American Journal of Gastroenterology.

[16]  N. Uedo,et al.  Prospective evaluation of narrow-band imaging endoscopy for screening of esophageal squamous mucosal high-grade neoplasia in experienced and less experienced endoscopists. , 2010, Diseases of the esophagus : official journal of the International Society for Diseases of the Esophagus.

[17]  Hisao Tajiri,et al.  Early detection of superficial squamous cell carcinoma in the head and neck region and esophagus by narrow band imaging: a multicenter randomized controlled trial. , 2010, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[18]  Pei-Jen Lou,et al.  Transnasal endoscopy with narrow-band imaging and Lugol staining to screen patients with head and neck cancer whose condition limits oral intubation with standard endoscope (with video). , 2009, Gastrointestinal endoscopy.

[19]  Yasushi Sano,et al.  Narrow band imaging: a new diagnostic approach to visualize angiogenesis in superficial neoplasia. , 2005, Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association.

[20]  M. Fujishiro,et al.  Diagnostic outcomes of esophageal cancer by artificial intelligence using convolutional neural networks. , 2019, Gastrointestinal endoscopy.

[21]  Bing Hu,et al.  Real-time automated diagnosis of precancerous lesion and early esophageal squamous cell carcinoma using a deep learning model (with videos). , 2019, Gastrointestinal endoscopy.