Human-Like Artificial Intelligent System for Predicting Invasion Depth of Esophageal Squamous Cell Carcinoma Using Magnifying Narrow-Band Imaging Endoscopy: A Retrospective Multicenter Study

Abstract

INTRODUCTION: Endoscopic evaluation is crucial for predicting the invasion depth of esophagus squamous cell carcinoma (ESCC) and selecting appropriate treatment strategies. Our study aimed to develop and validate an interpretable artificial intelligence–based invasion depth prediction system (AI-IDPS) for ESCC. METHODS: We reviewed the PubMed for eligible studies and collected potential visual feature indices associated with invasion depth. Multicenter data comprising 5,119 narrow-band imaging magnifying endoscopy images from 581 patients with ESCC were collected from 4 hospitals between April 2016 and November 2021. Thirteen models for feature extraction and 1 model for feature fitting were developed for AI-IDPS. The efficiency of AI-IDPS was evaluated on 196 images and 33 consecutively collected videos and compared with a pure deep learning model and performance of endoscopists. A crossover study and a questionnaire survey were conducted to investigate the system's impact on endoscopists' understanding of the AI predictions. RESULTS: AI-IDPS demonstrated the sensitivity, specificity, and accuracy of 85.7%, 86.3%, and 86.2% in image validation and 87.5%, 84%, and 84.9% in consecutively collected videos, respectively, for differentiating SM2-3 lesions. The pure deep learning model showed significantly lower sensitivity, specificity, and accuracy (83.7%, 52.1% and 60.0%, respectively). The endoscopists had significantly improved accuracy (from 79.7% to 84.9% on average, P = 0.03) and comparable sensitivity (from 37.5% to 55.4% on average, P = 0.27) and specificity (from 93.1% to 94.3% on average, P = 0.75) after AI-IDPS assistance. DISCUSSION: Based on domain knowledge, we developed an interpretable system for predicting ESCC invasion depth. The anthropopathic approach demonstrates the potential to outperform deep learning architecture in practice.

Novel milestones for early esophageal carcinoma: From bench to bed

“…With the aid of the AI system, leading endoscopists more accurately diagnosed both IPCL subtypes and depth of invasion. Zhang et al [ 114 ] developed an AI-based invasion depth prediction system (AI-IDPS) for ESCC utilizing invasion depth-related features. In terms of image verification, the AI-IDPS demonstrated a sensitivity, specificity, and accuracy of 85.7%, 86.3%, and 86.2%, respectively, in diagnosing SM2-3 lesions.…”

The Use of Artificial Intelligence in Gastroenterology: A Glimpse Into the Present

“…When I think about AI, I am struck by its potential to enhance both the care we deliver and the additional time we may save while providing that care. In this special issue, you'll find examples of how AI may be able to improve diagnostic accuracy, whether it's computer-aided diagnosis of in situ colon polyps ( 1 ), real-time detection of Helicobacter pylori infection ( 2 ), or determining the invasion depth of esophageal squamous cell carcinoma ( 3 ). AI can also improve patient access to GI diagnostics, as some technologies may become more easily utilized by primary care providers or allied health professionals.…”