111 UTILIZATION OF ARTIFICIAL INTELLIGENCE IN MINIMALLY INVASIVE RIGHT ADRENALECTOMY: RECOGNITION OF ANATOMICAL LANDMARKS WITH DEEP LEARNING

Le résumé fourni par la source

Abstract Background The primary surgical approach for removing adrenal masses is minimally invasive adrenalectomy. Recognition of anatomical landmarks during surgery is critical for minimizing complications. Artificial intelligence-based tools can be utilized to create real-time surgical navigation systems. Methods In this experimental feasibility study, intraoperative videos of 20 patients who underwent minimally invasive right adrenalectomy in a tertiary care center between 2011 and 2023 were analyzed and used to develop an artificial intelligence-based anatomical landmark recognition system. Semantic segmentation of the liver, the inferior vena cava (IVC), and the right adrenal gland was performed. Fifty random images per patient during the dissection phase were extracted. The experiments on the annotated images were performed on two state-of-the-art segmentation models named U-Net and SwinUNETR. The dataset was split into training and validation subsets with an 80:20 distribution. The models were trained with the Dice-Cross Entropy loss function, and the dice similarity coefficient (DSC) was calculated for the predictions on the validation subset. Results Out of 20 videos, 1000 images were extracted, and anatomical landmarks (liver, IVC, and right adrenal gland) were annotated. Randomly distributed 800 and 200 images were selected for the training and the validation subsets, respectively. Our benchmark results show that the transformer-based SwinUNETR model achieved 78.37%, and the U-Net model with the EfficientNet-0 backbone achieved 77.95% DSC scores on a three-region prediction task. Conclusions Artificial intelligence-based systems can predict anatomical landmarks with high performance in minimally invasive right adrenalectomy. Such tools can be used to create real-time navigation systems during surgery in the near future.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.