Li Fangting, Zhang Xiaoyue, Yang Kangyi, Qin Jiayin, Lv Bin, Lv Kun, Ma Yao, Sun Xingzhi, Ni Yuan, Xie Guotong, Wu Huijuan
Department of Ophthalmology, Peking University People's Hospital, Beijing, China.
Beijing Key Laboratory of Ocular Disease and Optometry Science, Peking University People's Hospital, Beijing, China.
BMJ Open Ophthalmol. 2025 Jan 20;10(1):e001600. doi: 10.1136/bmjophth-2023-001600.
To develop an artificial intelligence algorithm to automatically identify the anterior segment structures and assess multiple parameters of primary angle closure disease (PACD) in ultrasound biomicroscopy (UBM) images.
Development and validation of an artificial intelligence algorithm for UBM images.
2339 UBM images from 592 subjects were collected for algorithm development. A multitissue segmentation model based on deep learning was developed for automatic identification of anterior segments and localisation of scleral spur. Then, measurement of the typical angle parameters was performed from the predicted results, including angle-opening distance at 500 µm (AOD 500), trabecular-ciliary angle (TCA) and iris area. We then collected 222 UBM images from 45 subjects in two centres for model validation.
The multitissue identification model established in this study reached mean Intersection over Union (IoU) of 0.98, 0.98 and 0.98 on cornea segmentation, iris segmentation and ciliary body segmentation and a mean error distance of 1.07 pixels on scleral spur localisation. Our model got a mean IoU of 0.98, 0.98 and 0.99 on cornea segmentation, iris segmentation and ciliary body segmentation and a mean error distance of 0.49 pixels on scleral spur localisation in open-angle images and received 0.98, 0.98, 0.978 and 1.42 pixels respectively in angle-closure images. The mean differences between automatic and manual measurement of the angle parameters were 3.07 μm of AOD, 3.34 degrees of TCA and 0.05 mm of iris area.
The automatic method of multitissue identification for PACD eyes developed was feasible, and the automatic measurement of angle parameters was reliable.
开发一种人工智能算法，以在超声生物显微镜（UBM）图像中自动识别眼前节结构并评估原发性闭角型青光眼（PACD）的多个参数。
用于UBM图像的人工智能算法的开发与验证。
收集了来自592名受试者的2339张UBM图像用于算法开发。开发了一种基于深度学习的多组织分割模型，用于自动识别眼前节和定位巩膜突。然后，根据预测结果测量典型的房角参数，包括500μm处的房角开放距离（AOD 500）、小梁-睫状体夹角（TCA）和虹膜面积。随后，在两个中心收集了来自45名受试者的222张UBM图像用于模型验证。
本研究建立的多组织识别模型在角膜分割、虹膜分割和睫状体分割上的平均交并比（IoU）分别达到0.98、0.98和0.98，在巩膜突定位上的平均误差距离为1.07像素。在开角图像中，我们的模型在角膜分割、虹膜分割和睫状体分割上的平均IoU分别为0.98、0.98和0.99，在巩膜突定位上的平均误差距离为0.49像素；在闭角图像中，分别为0.98、0.98、0.978和1.42像素。房角参数自动测量与手动测量的平均差异为AOD 3.07μm、TCA 3.34度和虹膜面积0.05mm²。
所开发的用于PACD眼的多组织自动识别方法是可行的，房角参数的自动测量是可靠的。
