Deep learning system for screening AIDS-related cytomegalovirus retinitis with ultra-wide-field fundus images

Kuifang Du; Li Dong; Kai Zhang; Meilin Guan; Chao Chen; Lianyong Xie; Wenjun Kong; Heyan Li; Ruiheng Zhang; Wenda Zhou; Haotian Wu; Hongwei Dong; Wenbin Wei

doi:10.1016/j.heliyon.2024.e30881

Deep learning system for screening AIDS-related cytomegalovirus retinitis with ultra-wide-field fundus images

Heliyon. 2024 May 15;10(10):e30881. doi: 10.1016/j.heliyon.2024.e30881. eCollection 2024 May 30.

Authors

Kuifang Du¹, Li Dong², Kai Zhang³, Meilin Guan¹, Chao Chen¹, Lianyong Xie¹, Wenjun Kong¹, Heyan Li², Ruiheng Zhang², Wenda Zhou², Haotian Wu², Hongwei Dong¹, Wenbin Wei²

Affiliations

¹ Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China.
² 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.
³ Chongqing Chang'an Industrial Group Co. Ltd, Chongqing, China.

Abstract

Background: 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.

Methods: 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.

Results: 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.

Conclusions: 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.

Keywords: AIDS; Cytomegalovirus retinitis; Heat maps; Ultra-wide-field image; deep learning.