Department of Breast Surgery, Gifu University Hospital, 1-1 Yanagido, Gifu, 501-1194, Japan.
Department of Gastroenterological Surgery Pediatric Surgery, Gifu University, Graduate School of Medicine, 1-1 Yanagido, Gifu, 501-1194, Japan.
World J Surg Oncol. 2024 Jan 2;22(1):2. doi: 10.1186/s12957-023-03286-1.
Breast ultrasound (US) is useful for dense breasts, and the introduction of artificial intelligence (AI)-assisted diagnoses of breast US images should be considered. However, the implementation of AI-based technologies in clinical practice is problematic because of the costs of introducing such approaches to hospital information systems (HISs) and the security risk of connecting HIS to the Internet to access AI services. To solve these problems, we developed a system that applies AI to the analysis of breast US images captured using a smartphone.
Training data were prepared using 115 images of benign lesions and 201 images of malignant lesions acquired at the Division of Breast Surgery, Gifu University Hospital. YOLOv3 (object detection models) was used to detect lesions on US images. A graphical user interface (GUI) was developed to predict an AI server. A smartphone application was also developed for capturing US images displayed on the HIS monitor with its camera and displaying the prediction results received from the AI server. The sensitivity and specificity of the prediction performed on the AI server and via the smartphone were calculated using 60 images spared from the training.
The established AI showed 100% sensitivity and 75% specificity for malignant lesions and took 0.2 s per prediction with the AI sever. Prediction using a smartphone required 2 s per prediction and showed 100% sensitivity and 97.5% specificity for malignant lesions.
Good-quality predictions were obtained using the AI server. Moreover, the quality of the prediction via the smartphone was slightly better than that on the AI server, which can be safely and inexpensively introduced into HISs.
乳腺超声（US）对于致密型乳腺很有用，应该考虑引入人工智能（AI）辅助诊断乳腺 US 图像。然而，由于将这些方法引入医院信息系统（HIS）的成本以及将 HIS 连接到互联网以访问 AI 服务的安全风险，基于人工智能的技术在临床实践中的实施存在问题。为了解决这些问题，我们开发了一种应用人工智能分析使用智能手机拍摄的乳腺 US 图像的系统。
使用来自岐阜大学医院乳腺外科的 115 张良性病变图像和 201 张恶性病变图像准备了训练数据。使用 YOLOv3（目标检测模型）检测 US 图像上的病变。开发了一个图形用户界面（GUI）来预测 AI 服务器。还开发了一个智能手机应用程序，用于用其摄像头捕获 HIS 显示器上显示的 US 图像，并显示从 AI 服务器接收到的预测结果。使用从训练中留出的 60 张图像计算了在 AI 服务器和智能手机上进行的预测的灵敏度和特异性。
建立的 AI 对恶性病变的灵敏度为 100%，特异性为 75%，在 AI 服务器上进行预测的时间为 0.2 秒。使用智能手机进行预测需要 2 秒，对恶性病变的灵敏度为 100%，特异性为 97.5%。
使用 AI 服务器获得了高质量的预测。此外，智能手机上的预测质量略优于 AI 服务器，可安全且经济地引入 HIS。
