Deep Learning-based System and AIDS-related Cytomegalovirus Retinitis
Study Details
Study Description
Brief Summary
Ophthalmological screening for cytomegalovirus retinitis (CMVR) for HIV/AIDS patients is important. However, the manual screening with fundus imaging is laborious and subjective.
Deep learning (DL) system has been developed for the automated detection of various eye diseases with high accuracy and efficiency, including diabetic retinopathy, glaucoma, age-related macular degeneration (AMD), papilledema, lattice degeneration and retinal breaks, from ocular fundus photographs. UWF imaging is a relatively new imaging modality for DL system but has also shown extraordinary talents in automatic retinal analysis With the press for routine CMVR screening in AIDS patients and the great capacity of DL system, the use of deep learning (DL) system to AIDS-related CMVR with Ultra-Widefield (UWF) fundus images is promising.
The investigators previously developed a DL system to detect AIDS-related CMVR. For further evaluating the applicability of the DL system, a prospective dataset is needed.
Condition or Disease | Intervention/Treatment | Phase |
---|---|---|
|
Study Design
Arms and Interventions
Arm | Intervention/Treatment |
---|---|
Active CMVR The UWF images of cytomegalovirus retinitis (CMVR) included various patterns: hemorrhagic necrotizing lesion, granular lesion, frosted branch angiitis, and optic neuropathy lesion. Active CMVR lesion was defined as obvious opacity (mild, moderate, severe, very severe) |
|
Inactive CMVR Inactive CMVR lesion was defined as a lack of opacity or questionable/equivocal activity. |
|
Non-CMVR The non-CMVR images included normal retina and other retinopathies such as HIV-related microvascular retinopathy, diabetic retinopathy, retinal detachment, vitreous hemorrhage. |
Outcome Measures
Primary Outcome Measures
- Evaluating the applicability of the DL system to identify AIDS-related CMVR [April 2021]
The investigators compared the performance between two trained (senior and junior) retinal ophthalmologists with the DL system. A senior retinal ophthalmologist and a junior retinal ophthalmologist were asked to independently screen the UWF images in the prospective dataset. Accuracy, sensitivity and specificity were used to evaluate the performance.
Eligibility Criteria
Criteria
Inclusion Criteria:
The UWF images from HIV/AIDS patients.
Exclusion Criteria:
-
The UWF images would be excluded if all three human graders gave different diagnosis.
-
The UWF images with poor quality would be excluded.
Contacts and Locations
Locations
Site | City | State | Country | Postal Code | |
---|---|---|---|---|---|
1 | Beijing Youan Hospital, Capital Medical University | Beijing | Beijing | China | 100069 |
Sponsors and Collaborators
- Kuifang Du
- Beijing Tongren Hospital
Investigators
- Study Director: Kui-Fang Du, Beijing YouAn Hospital
- Study Director: Li Dong, Beijing Tongren Hospital
- Principal Investigator: Kai Zhang, Beijing Tongren Hospital
- Principal Investigator: Chao Chen, Beijing YouAn Hospital
- Principal Investigator: Lian-Yong Xie, Beijing YouAn Hospital
- Principal Investigator: Wen-Jun Kong, Beijing YouAn Hospital
- Principal Investigator: Hong-Wei Dong, Beijing YouAn Hospital
- Principal Investigator: He-Yan Li, Beijing Tongren Hospital
- Principal Investigator: Rui-Heng Zhang, Beijing Tongren Hospital
- Principal Investigator: Wen-Da Zhou, Beijing Tongren Hospital
- Principal Investigator: Hao-Tian Wu, Beijing Tongren Hospital
- Study Chair: Wen-Bin Wei, Beijing Tongren Hospital
Study Documents (Full-Text)
None provided.More Information
Publications
None provided.- 20210331001