1
|
Du K, Dong L, Zhang K, Guan M, Chen C, Xie L, Kong W, Li H, Zhang R, Zhou W, Wu H, Dong H, Wei W. Deep learning system for screening AIDS-related cytomegalovirus retinitis with ultra-wide-field fundus images. Heliyon 2024; 10:e30881. [PMID: 38803983 PMCID: PMC11128864 DOI: 10.1016/j.heliyon.2024.e30881] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2023] [Revised: 05/03/2024] [Accepted: 05/07/2024] [Indexed: 05/29/2024] Open
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.
Collapse
Affiliation(s)
- Kuifang Du
- Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Li Dong
- 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
| | - Kai Zhang
- Chongqing Chang'an Industrial Group Co. Ltd, Chongqing, China
| | - Meilin Guan
- Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Chao Chen
- Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Lianyong Xie
- Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Wenjun Kong
- Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Heyan Li
- 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
| | - Ruiheng Zhang
- 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
| | - Wenda Zhou
- 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
| | - Haotian Wu
- 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
| | - Hongwei Dong
- Department of Ophthalmology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Wenbin Wei
- 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
| |
Collapse
|
2
|
Luo J, Peng J, Zhao PQ, Fei P. CMV Retinitis in Wiskott Aldrich Syndrome. Ocul Immunol Inflamm 2023; 31:134-141. [PMID: 34878956 DOI: 10.1080/09273948.2021.1995762] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/27/2023]
Abstract
PURPOSE Wiskott-Aldrich syndrome (WAS) is an X-linked recessive disease whose optimal curative treatment is hematopoietic stem cell transplantation (HSCT). Patients with WAS may suffer from cytomegalovirus retinitis (CMVR) which can cause vision loss. This study is to report the progression and prognosis of patients with WAS and CMVR. METHODS A retrospective case series of ten patients with WAS and CMVR before and after HSCT who were referred to the Ophthalmology Department of Xinhua Hospital from June 2018 to February 2021. Progression and prognosis were recorded. RESULTS Five patients were diagnosed with CMVR before receiving HSCT at a median age of 10.5 months (range: 4-23 months). Eight patients developed CMVR post-transplantation with a median interval from HSCT of 3.5 months (range: 1-9 months). CONCLUSION Regular fundus examinations and prompt treatments in patients with WAS are therefore crucial before they receiving HSCT or approximately 3.5 months after HSCT until complete reconstitution of immune function.
Collapse
Affiliation(s)
- Jia Luo
- Xinhua Hospital, Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Jie Peng
- Xinhua Hospital, Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Pei-Quan Zhao
- Xinhua Hospital, Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Ping Fei
- Xinhua Hospital, Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| |
Collapse
|