Artificial Intelligence-Assisted Detection of Tracheoesophageal Fistula during Thoracoscopic Esophageal Atresia Repair: Comparison with Pediatric Surgeons and Real-Time Clinical Deployment.
Oct 2026· Journal of Pediatric Surgery· Vol 62, pp.
163559
· 0 citations· 13 references
Medicine
TL;DR
These findings support prospective, multi-institutional evaluation of AI assistance for pediatric thoracoscopic navigation and training.
Abstract
Background
Artificial intelligence (AI) applied to surgical video is often evaluated by model performance alone, leaving clinical usefulness uncertain. We evaluated a U-Net-derived semantic segmentation model as an assistive tool for identifying the tracheoesophageal fistula (TEF) during thoracoscopic esophageal atresia repair.
Methods
The model was trained on 7,287 annotated frames from 26 surgical videos and evaluated by four-fold case-based cross-validation and an independent five-case test set. Forty-eight pediatric surgeons (7 experts and 41 novices) completed paired video-based identification tasks with and without AI assistance and a separate frame-based segmentation task. AI-on/off comparisons used surgeon-level medians. Real-time deployment was assessed in two operations.
Results
The median cross-validation Dice coefficient was 0.628. In clip-based testing, AI identified the TEF faster than experts and novices (1.05 versus 2.87 and 6.92 s). Among novices, median identification time was 263 (190-453) vs. 390 (272-555) frames (AI-on vs. AI-off; P < 0.001), and confidence was 4 (4-5) vs. 3 (3-4) (P < 0.001). Among experts, median identification time was 186 (174-201) vs. 172 (157-196) frames (P = 0.22), and confidence was 5 (5-5) vs. 5 (4-5) (P = 0.031). In the controlled frame task, AI achieved a higher Dice coefficient (0.881) than experts (0.803) and novices (0.780). Real-time overlay was technically feasible in two cases without observed AI-related adverse events.
Conclusions
These findings support prospective, multi-institutional evaluation of AI assistance for pediatric thoracoscopic navigation and training.
The developed model provides an objective, automated hemorrhage metric that is aligned with expert skill ratings and operative behavior during laparoscopic cholecystectomy, and may serve as a potential adjunct for postoperative, competency-based feedback rather than as a stand-alone measure of surgical skill.
Zhi-Xiang Chen, X. Zeng, Hao-Yuan Qiu et al.· Journal of Surgical Research· 0 citations
BACKGROUND
Automated surgical phase recognition may convert routinely recorded robotic surgery videos into objective workflow metrics, but its clinical interpretability in complex robotic pediatric and hepatobiliary procedures remains unclear.
METHODS
In this retrospective proof-of-concept study, we developed and int...
AI-based BPC was associated with ESSQS-based surgical proficiency in LH, and this objective, scalable, high-specificity metric may help flag procedures warranting expert review and timely feedback, particularly in low-difficulty cases.
OBJECTIVE
Oropharyngeal tumors with a propensity for submucosal spread can be difficult to detect and delineate during endoscopy. To facilitate their detection, we developed an Artificial Intelligence (AI) algorithm to segment tumors and other anatomically significant structures within the oropharynx.
STUDY DESIGN
Mo...
Anita Rau, Nikita Bedi, S. Yeung-Levy et al.· Otolaryngology Head & Neck S...· 0 citations