Artificial intelligence-powered surgical scene analysis in minimally invasive adrenal surgery: integrated recognition of anatomy, tools and phases
- 2 July 2026
- journal article
- Published by Springer Nature in Updates in Surgery
Abstract
This retrospective feasibility study aimed to develop an artificial intelligence-powered surgical model capable of recognizing key anatomical structures, tools, and surgical phases during minimally invasive adrenal surgery, and to assess its clinical applicability. The system has potential to enhance procedural safety and support training for adrenal operations, which are performed relatively infrequently. Video recordings from 20 laparoscopic transabdominal adrenalectomies (10 from each side; 2011-2025) were retrospectively analyzed. Surgical frames were annotated for tools, actions, anatomy, and surgical phases to build the dataset. A ResNet-50-based multi-head cross-attention network with dedicated heads for tools, actions, targets, and phases was developed. Laterality was incorporated through feature-wise linear modulation, and class imbalance was handled using weighted loss. Performance was assessed on a balanced test set using top-accuracy and mean average precision with 5-fold cross-validation. A total of 10,747 frames were labeled with 53,152 annotations across 9 tool categories, 7 surgical actions, 13 anatomical targets, and 6 phases. The model achieved top-1 accuracies of 67.6% for tools, 86.2% for actions, 70.0% for targets, and 60.3% for phases. Top-3 accuracies increased to 93.8%, 94.2%, 90.9%, and 95.3%, respectively. Mean average precision values were 64.2% for tools, 62.4% for actions, 46.8% for targets, and 66.4% for phases. The developed model demonstrated the feasibility of recognizing surgical instruments, actions, and key anatomical structures in adrenal surgery. These results may represent an initial step toward future systems capable of automated surgical scene analysis in minimally invasive adrenalectomy.Keywords
This publication has 23 references indexed in Scilit:
- Deep Learning–Based Real-Time Ureter Identification in Laparoscopic Colorectal SurgeryDiseases of the Colon & Rectum, 2024
- Artificial Intelligence for context-aware surgical guidance in complex robot-assisted oncological procedures: An exploratory feasibility studyEuropean Journal of Surgical Oncology, 2023
- Real-time vascular anatomical image navigation for laparoscopic surgery: experimental studySurgical Endoscopy, 2022
- Rendezvous: Attention mechanisms for the recognition of surgical action triplets in endoscopic videosMedical Image Analysis, 2022
- Artificial Intelligence for Surgical SafetyAnnals of Surgery, 2020
- Learning Human-Object Interactions by Graph Parsing Neural Networks2018
- Fifteen years of adrenalectomies: impact of specialty training and operative volumeSurgery, 2018
- Each procedure matters: threshold for surgeon volume to minimize complications and decrease cost associated with adrenalectomySurgery, 2018
- Endocrine surgery: Where are we today? A national survey of young endocrine surgeonsSurgery, 2010
- The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studiesThe Lancet, 2007