目的:本研究旨在开发和评估一种基于深度学习的模型,该模型可以自动测量植入式Collamer晶状体(ICL)手术候选人的术前超声生物显微镜(UBM)图像上的前节(AS)参数。
方法:术前共从武汉大学人民医院眼科中心接受ICL手术的321例患者中获取1164张全景UBM图像(武汉,中国)开发成像数据库。首先,利用UNet++网络自动分割AS组织,如角膜晶状体和虹膜。此外,开发了图像处理技术和几何定位算法来自动识别瞳孔直径(PD)的解剖标志(AL),前房深度(ACD),角度-角度距离(ATA),和沟-沟距离(STS)。根据后两个过程的结果,PD,ACD,ATA,STS是可以测量的。同时,来自黄石爱尔眼科医院的294张图像的外部数据集用于进一步评估模型在其他中心的性能。最后,来自外部测试集的100个随机图像的子集被选择与高级专家比较模型的性能。
结果:无论是内部测试数据集还是外部测试数据集,使用手动标签作为参考标准,模型的平均骰子系数超过0.880。此外,ALs坐标的类内相关系数(ICC)均大于0.947,ALs在250μm内的欧氏距离分布百分比超过95.24%。虽然PD的ICC,ACD,ATA,STS大于0.957,此外,PD的平均相对误差(ARE),ACD,ATA,STS低于2.41%。就人与机器的性能而言,模型和高级专家进行的测量之间的ICC均大于0.931.
结论:基于深度学习的模型可以使用ICL候选的UBM图像来测量AS参数,并表现出与高级眼科医生相似的表现。
OBJECTIVE: This study aimed to develop and evaluate a deep learning-based model that could automatically measure anterior segment (AS) parameters on preoperative ultrasound biomicroscopy (UBM) images of implantable Collamer lens (ICL) surgery candidates.
METHODS: A total of 1164 panoramic UBM images were preoperatively obtained from 321 patients who received ICL surgery in the Eye Center of Renmin Hospital of Wuhan University (Wuhan,
China) to develop an imaging database. First, the UNet++ network was utilized to segment AS tissues automatically, such as corneal lens and iris. In addition, image processing techniques and geometric localization algorithms were developed to automatically identify the anatomical landmarks (ALs) of pupil diameter (PD), anterior chamber depth (ACD), angle-to-angle distance (ATA), and sulcus-to-sulcus distance (STS). Based on the results of the latter two processes, PD, ACD, ATA, and STS can be measured. Meanwhile, an external dataset of 294 images from Huangshi Aier Eye Hospital was employed to further assess the model\'s performance in other center. Lastly, a subset of 100 random images from the external test set was chosen to compare the performance of the model with senior experts.
RESULTS: Whether in the internal test dataset or external test dataset, using manual labeling as the reference standard, the models achieved a mean Dice coefficient exceeding 0.880. Additionally, the intra-class correlation coefficients (ICCs) of ALs\' coordinates were all greater than 0.947, and the percentage of Euclidean distance distribution of ALs within 250 μm was over 95.24%.While the ICCs for PD, ACD, ATA, and STS were greater than 0.957, furthermore, the average relative error (ARE) of PD, ACD, ATA, and STS were below 2.41%. In terms of human versus machine performance, the ICCs between the measurements performed by the model and those by senior experts were all greater than 0.931.
CONCLUSIONS: A deep learning-based model could measure AS parameters using UBM images of ICL candidates, and exhibited a performance similar to that of a senior ophthalmologist.