Department of Radiology, Sheba Medical Center, Tel-Hashomer, Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel.
Department of General Surgery and Transplantation, Sheba Medical Center, Tel-Hashomer, Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel.
Langenbecks Arch Surg. 2022 Dec;407(8):3553-3560. doi: 10.1007/s00423-022-02674-7. Epub 2022 Sep 7.
Intraoperative ultrasonography (IOUS) of the liver is a crucial adjunct in every liver resection and may significantly impact intraoperative surgical decisions. However, IOUS is highly operator dependent and has a steep learning curve. We describe the design and assessment of an artificial intelligence (AI) system to identify focal liver lesions in IOUS.
IOUS images were collected during liver resections performed between November 2020 and November 2021. The images were labeled by radiologists and surgeons as normal liver tissue versus images that contain liver lesions. A convolutional neural network (CNN) was trained and tested to classify images based on the labeling. Algorithm performance was tested in terms of area under the curves (AUCs), accuracy, sensitivity, specificity, F1 score, positive predictive value, and negative predictive value.
Overall, the dataset included 5043 IOUS images from 16 patients. Of these, 2576 were labeled as normal liver tissue and 2467 as containing focal liver lesions. Training and testing image sets were taken from different patients. Network performance area under the curve (AUC) was 80.2 ± 2.9%, and the overall classification accuracy was 74.6% ± 3.1%. For maximal sensitivity of 99%, the classification specificity is 36.4 ± 9.4%.
This study provides for the first time a proof of concept for the use of AI in IOUS and show that high accuracy can be achieved. Further studies using high volume data are warranted to increase accuracy and differentiate between lesion types.
术中超声（IOUS）是肝切除术的重要辅助手段，可能会显著影响术中手术决策。然而，IOUS 高度依赖于操作者，并且具有陡峭的学习曲线。我们描述了一种人工智能（AI）系统的设计和评估，用于识别 IOUS 中的局灶性肝病变。
在 2020 年 11 月至 2021 年 11 月期间进行的肝切除术中采集 IOUS 图像。这些图像由放射科医生和外科医生标记为正常肝组织与包含肝病变的图像。然后基于这些标记训练和测试卷积神经网络（CNN）来对图像进行分类。算法性能通过曲线下面积（AUC）、准确性、敏感性、特异性、F1 分数、阳性预测值和阴性预测值进行测试。
总体而言，该数据集包含 16 名患者的 5043 张 IOUS 图像。其中，2576 张标记为正常肝组织，2467 张标记为含有局灶性肝病变。训练和测试图像集来自不同的患者。网络性能的 AUC 为 80.2±2.9%，整体分类准确性为 74.6±3.1%。为了达到 99%的最大敏感性，分类特异性为 36.4±9.4%。
这项研究首次提供了在 IOUS 中使用 AI 的概念验证，并表明可以实现高精度。需要进一步使用大容量数据的研究来提高准确性并区分病变类型。
