Although the risk of intraoperative complications of laparoscopic donor nephrectomy (LDN) is now acceptably low, the work continues to minimise technical mishaps during this ‘high stakes’ surgery. In this study, we aim to demonstrate the pilot use of a patented proprietary deep learning (DL)-based computer vision (CV) to automatically recognise key anatomical structures and prevent intraoperative injuries, which is especially crucial during the learning curve. 6828 images manually annotated by pixels were selected from 16 surgical videos (National University Hospital, NUH) for training as ground truth, and 1757 annotated images from 4 separate surgical videos were used for validation. This ensured a balanced validation ratio of nearly 20% for each label (spleen, left kidney, renal artery, renal vein, and ureter). The YOLO (you only look once) v11x DL network ( https://docs.ultralytics.com/models/yolo11/ ), known for its speed and accuracy in real-time detection, was adapted to train our model. For further optimisation, it uses a sophisticated loss function which incorporates the accuracy of each pixel in segmentation tasks (binary cross-entropy loss), compares the predicted bounding box coordinates against ground truth (bounding box loss), and emphasises the importance of difficult-to-detect labels (distribution focal loss). Metrics were calculated using the following formulas, based on true positives (TP), false positives (FP), and false negatives (FN): Precision: TP / (TP + FP), Recall: TP / (TP + FN), F1 Score: 2 * (Precision * Recall) / (Precision + Recall). High precision minimises false positives, which could disrupt surgical workflows, while high recall ensures comprehensive detection, minimising false negatives that could affect patient safety. F1 serves as the harmonic mean of recall and precision. Quantitative evaluation of the validation dataset using the hold-out validation method yielded promising performance metrics and prospective evaluation was performed on a video from another surgeon (JC) and institution (National Taiwan University) and also in real-time in NUH. Our pilot study demonstrates an innovative machine learning design’s ability to accurately identify vital anatomical structures in LDN. This is a crucial first step for further artificial intelligence (AI)-guided applications such as intra-operative guidance, education, and post-hoc operative analysis and operative standards evaluation.
Ong et al. (Thu,) studied this question.