我们的目的是建立一个人工智能(AI)模型,以在内窥镜入路中识别甲状旁腺,并将其与高级和初级外科医生的视觉估计进行比较。
共标记了来自166个内镜甲状腺切除术视频的1,700张甲状旁腺图像。来自20个其他全长视频的数据被用作独立的外部队列。YOLOV3,更快的R-CNN,级联算法被用于深度学习,并选择最优算法进行独立的外部队列分析。最后,识别率,初始识别时间,和PTAIR(甲状旁腺识别人工智能模型)的跟踪周期,初级外科医生,和资深外科医生进行了比较。
FasterR-CNN算法在优化每种算法的超参数后显示出最佳平衡,并更新为PTAIR。精度,召回率,PTAIR的F1评分为88.7%,92.3%,90.5%,分别。在独立的外部队列中,PTAIR的甲状旁腺识别率,资深外科医生,初级外科医生占96.9%,87.5%,71.9%,分别。此外,PTAIR比高级外科医生提前3.83秒识别甲状旁腺(p=0.008),跟踪期比高级外科医生长62.82秒(p=0.006)。
PTAIR可以在特定训练策略下实现早期识别和全职跟踪。PTAIR的识别率高于初级外科医生,与高级外科医生相似。这样的系统可以用于改善手术结果并且还用于加速初级外科医生的教育。
3喉镜,132:2516-2523,2022.
We aimed to establish an artificial intelligence (AI) model to identify
parathyroid glands during endoscopic approaches and compare it with senior and junior surgeons\' visual estimation.
A total of 1,700 images of
parathyroid glands from 166 endoscopic thyroidectomy videos were labeled. Data from 20 additional full-length videos were used as an independent external cohort. The YOLO V3, Faster R-CNN, and Cascade algorithms were used for deep learning, and the optimal algorithm was selected for independent external cohort analysis. Finally, the identification rate, initial recognition time, and tracking periods of PTAIR (Artificial Intelligence model for
Parathyroid gland Recognition), junior surgeons, and senior surgeons were compared.
The Faster R-CNN algorithm showed the best balance after optimizing the hyperparameters of each algorithm and was updated as PTAIR. The precision, recall rate, and F1 score of the PTAIR were 88.7%, 92.3%, and 90.5%, respectively. In the independent external cohort, the
parathyroid identification rates of PTAIR, senior surgeons, and junior surgeons were 96.9%, 87.5%, and 71.9%, respectively. In addition, PTAIR recognized
parathyroid glands 3.83 s ahead of the senior surgeons (p = 0.008), with a tracking period 62.82 s longer than the senior surgeons (p = 0.006).
PTAIR can achieve earlier identification and full-time tracing under a particular training strategy. The identification rate of PTAIR is higher than that of junior surgeons and similar to that of senior surgeons. Such systems may have utility in improving surgical outcomes and also in accelerating the education of junior surgeons.
3 Laryngoscope, 132:2516-2523, 2022.