Department of Pediatric Surgery, Saitama Children's Medical Center, Saitama, Japan.
Department of Pediatric Surgery, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.
J Laparoendosc Adv Surg Tech A. 2021 Dec;31(12):1412-1419. doi: 10.1089/lap.2021.0318. Epub 2021 Nov 5.
Diagnosing pediatric appendicitis by ultrasonography (US) is difficult because US requires significant training and skill. We evaluated whether artificial intelligence (AI) can augment US. Among 70 abdominal ultrasound videos containing 85-347 images each, 50 were used to train the AI neural network. Each video was categorized based on the detection percentage and percent accuracy: most (>50%), partial (10-50%), and none (<10%). Test 1 involved verification of appendix detection by AI using the remaining 20 videos. Test 2 involved the evaluation of the effect of AI utilization on pediatricians. From 50 videos, 6914 images were used to train the AI network. In test 1, 3 pediatric surgeons judged 10 (50.0%), 4 (20.0%), and 6 (30.0%) videos as "most," "partial," and "none," respectively, regarding the detection percentage; 7 (35.0%), 7 (35.0%), and 6 (30.0%) videos were judged, respectively, concerning the percent accuracy. Five (83.3%) of six test videos with a scan area depth of 8 cm were judged as "none" for both detection and accuracy. In test 2, six videos were also judged as "none" for both categories, showing a negative effect on the participants (5 pediatric residents and 5 pediatric intensive-emergency fellows), but the other categories showed little negative effect. Appendicitis in a shallow US scan area can be easily identified with AI support. Even with the detection of a partial appendicitis shadow, AI is still helpful. However, if AI does not detect appendicitis at all, examiners may be negatively affected.
超声（US）诊断小儿阑尾炎比较困难，因为它需要大量的培训和技能。我们评估了人工智能（AI）是否可以增强 US。在包含 85-347 张图像的 70 个腹部超声视频中，50 个用于训练 AI 神经网络。每个视频都根据检测百分比和准确率百分比进行分类：大多数（>50%）、部分（10-50%）和无（<10%）。测试 1 涉及使用其余 20 个视频验证 AI 对阑尾的检测。测试 2 涉及评估 AI 利用对儿科医生的影响。从 50 个视频中，使用 6914 张图像来训练 AI 网络。在测试 1 中，3 名儿科外科医生分别对 10 个（50.0%）、4 个（20.0%）和 6 个（30.0%）视频的检测百分比进行了判断，分别为“大多数”、“部分”和“无”；分别对 7 个（35.0%）、7 个（35.0%）和 6 个（30.0%）视频的准确率进行了判断。在扫描深度为 8cm 的 6 个测试视频中，有 5 个（83.3%）被判断为在检测和准确性方面均为“无”。在测试 2 中，对于这两个类别，也有 6 个视频被判断为“无”，这对参与者（5 名儿科住院医师和 5 名儿科重症急救医师）产生了负面影响，但其他类别几乎没有负面影响。在有 AI 支持的情况下，较浅的 US 扫描区域的阑尾炎可以很容易地识别。即使检测到部分阑尾炎阴影，AI 仍然有帮助。然而，如果 AI 根本没有检测到阑尾炎，检查者可能会受到负面影响。
