Du Kuifang, Dong Li, Zhang Kai, Guan Meilin, Chen Chao, Xie Lianyong, Kong Wenjun, Li Heyan, Zhang Ruiheng, Zhou Wenda, Wu Haotian, Dong Hongwei, Wei Wenbin
Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China.
Beijing Tongren Eye Centre, Beijing Key Laboratory of Intraocular Tumour Diagnosis and Treatment, Beijing Ophthalmology & Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
Heliyon. 2024 May 15;10(10):e30881. doi: 10.1016/j.heliyon.2024.e30881. eCollection 2024 May 30.
Ophthalmological screening for cytomegalovirus retinitis (CMVR) for HIV/AIDS patients is important to prevent lifelong blindness. Previous studies have shown good properties of automated CMVR screening using digital fundus images. However, the application of a deep learning (DL) system to CMVR with ultra-wide-field (UWF) fundus images has not been studied, and the feasibility and efficiency of this method are uncertain.
In this study, we developed, internally validated, externally validated, and prospectively validated a DL system to detect AIDS-related from UWF fundus images from different clinical datasets. We independently used the InceptionResnetV2 network to develop and internally validate a DL system for identifying active CMVR, inactive CMVR, and non-CMVR in 6960 UWF fundus images from 862 AIDS patients and validated the system in a prospective and an external validation data set using the area under the curve (AUC), accuracy, sensitivity, and specificity. A heat map identified the most important area (lesions) used by the DL system for differentiating CMVR.
The DL system showed AUCs of 0.945 (95 % confidence interval [CI]: 0.929, 0.962), 0.964 (95 % CI: 0.870, 0.999) and 0.968 (95 % CI: 0.860, 1.000) for detecting active CMVR from non-CMVR and 0.923 (95 % CI: 0.908, 0.938), 0.902 (0.857, 0.948) and 0.884 (0.851, 0.917) for detecting active CMVR from non-CMVR in the internal cross-validation, external validation, and prospective validation, respectively. Deep learning performed promisingly in screening CMVR. It also showed the ability to differentiate active CMVR from non-CMVR and inactive CMVR as well as to identify active CMVR and inactive CMVR from non-CMVR (all AUCs in the three independent data sets >0.900). The heat maps successfully highlighted lesion locations.
Our UWF fundus image-based DL system showed reliable performance for screening AIDS-related CMVR showing its potential for screening CMVR in HIV/AIDS patients, especially in the absence of ophthalmic resources.
对艾滋病毒/艾滋病患者进行巨细胞病毒性视网膜炎（CMVR）的眼科筛查对于预防终身失明至关重要。先前的研究表明，使用数字眼底图像进行自动CMVR筛查具有良好的效果。然而，深度学习（DL）系统在超宽视野（UWF）眼底图像用于CMVR方面尚未得到研究，且该方法的可行性和效率尚不确定。
在本研究中，我们开发了一个DL系统，并进行了内部验证、外部验证和前瞻性验证，以从不同临床数据集中的UWF眼底图像检测与艾滋病相关的情况。我们独立使用InceptionResnetV2网络开发并在内部验证了一个DL系统，用于在来自862例艾滋病患者的6960张UWF眼底图像中识别活动性CMVR、非活动性CMVR和非CMVR，并使用曲线下面积（AUC）、准确率、敏感性和特异性在前瞻性和外部验证数据集中对该系统进行验证。热图确定了DL系统用于区分CMVR的最重要区域（病变）。
DL系统在内部交叉验证、外部验证和前瞻性验证中，从非CMVR中检测活动性CMVR的AUC分别为0.945（95%置信区间[CI]：0.929，0.962）、0.964（95%CI：0.870，0.999）和0.968（95%CI：0.860，1.000），从非CMVR中检测活动性CMVR的AUC分别为0.923（95%CI：0.908，0.938）、0.902（0.857，0.948）和0.884（0.851，0.917）。深度学习在筛查CMVR方面表现出良好前景。它还显示出能够区分活动性CMVR与非CMVR和非活动性CMVR，以及从非CMVR中识别活动性CMVR和非活动性CMVR（三个独立数据集中的所有AUC均>0.900）。热图成功突出了病变位置。
我们基于UWF眼底图像的DL系统在筛查与艾滋病相关的CMVR方面表现出可靠性能，显示出其在艾滋病毒/艾滋病患者中筛查CMVR的潜力，尤其是在缺乏眼科资源的情况下。
