Department of Ophthalmology, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Microelectronics CAD Center, Hangzhou Dianzi University, Hangzhou, China.
Br J Ophthalmol. 2024 Jun 20;108(7):999-1004. doi: 10.1136/bjo-2022-322953.
Ultrasound imaging is suitable for detecting and diagnosing ophthalmic abnormalities. However, a shortage of experienced sonographers and ophthalmologists remains a problem. This study aims to develop a multibranch transformer network (MBT-Net) for the automated classification of multiple ophthalmic diseases using B-mode ultrasound images.
Ultrasound images with six clinically confirmed categories, including normal, retinal detachment, vitreous haemorrhage, intraocular tumour, posterior scleral staphyloma and other abnormalities, were used to develop and evaluate the MBT-Net. Images were derived from five different ultrasonic devices operated by different sonographers and divided into training set, validation set, internal testing set and temporal external testing set. Two senior ophthalmologists and two junior ophthalmologists were recruited to compare the model's performance.
A total of 10 184 ultrasound images were collected. The MBT-Net got an accuracy of 87.80% (95% CI 86.26% to 89.18%) in the internal testing set, which was significantly higher than junior ophthalmologists (95% CI 67.37% to 79.16%; both p<0.05) and lower than senior ophthalmologists (95% CI 89.45% to 92.61%; both p<0.05). The micro-average area under the curve of the six-category classification was 0.98. With reference to comprehensive clinical diagnosis, the measurements of agreement were almost perfect in the MBT-Net (kappa=0.85, p<0.05). There was no significant difference in the accuracy of the MBT-Net across five ultrasonic devices (p=0.27). The MBT-Net got an accuracy of 82.21% (95% CI 78.45% to 85.44%) in the temporal external testing set.
The MBT-Net showed high accuracy for screening and diagnosing multiple ophthalmic diseases using only ultrasound images across mutioperators and mutidevices.
超声成像是检测和诊断眼部异常的理想选择。然而，经验丰富的超声技师和眼科医生的短缺仍然是一个问题。本研究旨在开发一种多分支变压器网络（MBT-Net），用于使用 B 型超声图像对多种眼科疾病进行自动分类。
使用 6 种临床确诊类别（包括正常、视网膜脱离、玻璃体积血、眼内肿瘤、后巩膜葡萄肿和其他异常）的超声图像来开发和评估 MBT-Net。图像来自 5 种不同的超声设备，由不同的超声技师操作，并分为训练集、验证集、内部测试集和时间外部测试集。招募了 2 名资深眼科医生和 2 名初级眼科医生来比较模型的性能。
共收集了 10184 张超声图像。MBT-Net 在内部测试集中的准确率为 87.80%（95%置信区间为 86.26%至 89.18%），明显高于初级眼科医生（95%置信区间为 67.37%至 79.16%；均 p<0.05），低于资深眼科医生（95%置信区间为 89.45%至 92.61%；均 p<0.05）。6 类分类的微平均曲线下面积为 0.98。参考综合临床诊断，MBT-Net 的一致性测量值几乎为完美（kappa=0.85，p<0.05）。MBT-Net 在 5 种超声设备中的准确率没有显著差异（p=0.27）。MBT-Net 在时间外部测试集中的准确率为 82.21%（95%置信区间为 78.45%至 85.44%）。
MBT-Net 仅使用多操作员和多设备的超声图像即可实现多种眼科疾病的筛查和诊断，准确率高。
