这项工作的目的是开发一种深度学习（DL）系统，利用眼B-快速准确地筛查眼内肿瘤（IOT）、视网膜脱离（RD）、玻璃体出血（VH）和后巩膜葡萄肿（PSS）。扫描超声图像。使用来自五个临床确诊类别的超声图像，包括玻璃体出血、视网膜脱离、眼内肿瘤、后巩膜葡萄肿和正常眼睛，来开发和评估细粒度分类系统（双路径病变注意网络） ，DPLA-网）。图像来自五个中心，由不同的超声医师扫描，并按 7:1:2 的比例分为训练集、验证集和测试集。招募了两名高级眼科医生和四名初级眼科医生来评估该系统的性能。这项多中心横断面研究在中国六家医院进行。共采集超声图像6054张； 4758张图像用于系统的训练和验证，1296张图像用作测试集。 DPLA-Net 在测试集中实现了 0.943 的平均准确率，IOT 的曲线下面积为 0.988，RD 为 0.997，PSS 为 0.994，VH 为 0.988，正常为 0.993。在 DPLA-Net 的帮助下，四位初级眼科医生的准确率从 0.696（95% 置信区间 [CI] 0.684-0.707）提高到 0.919（95% CI 0.912-0.926，p< 0.001），并且用于对每张图像进行分类的时间从 16.84 ± 2.34 秒减少到 10.09 ± 1.79 秒。所提出的 DPLA-Net 在使用跨多个中心的 B 扫描超声图像对多种眼科疾病进行筛查和分类方面表现出很高的准确性。此外，该系统可以提高眼科医生分类的效率。© 2024。作者。

The aim of this work is to develop a deep learning (DL) system for rapidly and accurately screening for intraocular tumor (IOT), retinal detachment (RD), vitreous hemorrhage (VH), and posterior scleral staphyloma (PSS) using ocular B-scan ultrasound images.Ultrasound images from five clinically confirmed categories, including vitreous hemorrhage, retinal detachment, intraocular tumor, posterior scleral staphyloma, and normal eyes, were used to develop and evaluate a fine-grained classification system (the Dual-Path Lesion Attention Network, DPLA-Net). Images were derived from five centers scanned by different sonographers and divided into training, validation, and test sets in a ratio of 7:1:2. Two senior ophthalmologists and four junior ophthalmologists were recruited to evaluate the system's performance.This multi-center cross-sectional study was conducted in six hospitals in China. A total of 6054 ultrasound images were collected; 4758 images were used for the training and validation of the system, and 1296 images were used as a testing set. DPLA-Net achieved a mean accuracy of 0.943 in the testing set, and the area under the curve was 0.988 for IOT, 0.997 for RD, 0.994 for PSS, 0.988 for VH, and 0.993 for normal. With the help of DPLA-Net, the accuracy of the four junior ophthalmologists improved from 0.696 (95% confidence interval [CI] 0.684-0.707) to 0.919 (95% CI 0.912-0.926, p < 0.001), and the time used for classifying each image reduced from 16.84 ± 2.34 s to 10.09 ± 1.79 s.The proposed DPLA-Net showed high accuracy for screening and classifying multiple ophthalmic diseases using B-scan ultrasound images across mutiple centers. Moreover, the system can promote the efficiency of classification by ophthalmologists.© 2024. The Author(s).