Cytomegalovirus Retinitis Screening Using Machine Learning Technology

Abstract

Propose: A screening protocol for cytomegalovirus retinitis (CMVR) by fundus photography was generated, and the diagnostic accuracy of machine learning technology for CMVR screening in HIV patients was investigated.Methods: One hundred sixty-five eyes of 90 HIV-positive patients were enrolled and evaluated for CMVR with binocular indirect ophthalmoscopy. Then, a single central field of the fundus image was recorded from each eye. All images were then interpreted by both machine learning models, generated by using the Keras application, and by a third-year ophthalmology resident. Diagnostic performance of CMVR screening using a machine learning model and the third-year ophthalmology resident were analyzed and compared.Results: Machine learning model, Keras application (VGG16), provided 68.8% (95% confidence interval [CI] = 50%-83.9%) sensitivity and 100% (95% CI = 97.2%-100%) specificity. The program provided accuracy of 93.94%. However, the sensitivity and specificity for the third-year ophthalmology grading were 67.7% (95% CI = 48.6%-83.3%) and 98.4% (95% CI = 94.5%-99.8%). The accuracy for CMVR classification was 89.70%. When considering for sight-threatening retinitis in Zone 1 and excluded Zones 2 and 3, the machine learning model provided high sensitivity of 88.2% (95% CI = 63.6%-98.5%) and high specificity of 100% (95% CI = 97.2%-100%).Conclusion: This study demonstrated the benefit of the machine learning model VGG16, which provided high sensitivity and specificity for detecting sight-threatening CMVR in HIVpositive patients. This model is a useful tool for ophthalmologists in clinical practice for preventing blindness from CMVR, especially during the Coronavrus Disease 2019 pandemic.

Application of artificial intelligence system for screening multiple fundus diseases in Chinese primary healthcare settings: a real-world, multicentre and cross-sectional study of 4795 cases

“… 15 In addition to AMD, 16 GON, 17 DR 18 and major blinding fundus diseases, Srisuriyajan et al developed an AI system with high sensitivity and specificity in screening cytomegalovirus retinitis, which is a great threat to the vision of HIV-positive patients. 19 Moreover, AI revealed high performances in predicting postoperative visual prognosis after ERM 20 and MH surgeries. 21 Furthermore, as an accessible extension of the brain and the only window for observing small vessels in vivo , 22 the retina can detect Alzheimer’s disease 23 and cardiovascular diseases 24 in addition to fundus diseases.…”

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

“…Kingkosol and colleagues proposed an artificial neural network (ANN) for automated CMVR screening in immunodeficient patients using digital fundus images [ 28 ]. Srisuriyajan and colleagues proposed a CNN for automated CMVR screening using digital fundus images [ 29 ]. Ong et al developed a multi-task learning model to detect necrotizing viral retinitis, including CMVR from common blood and serology tests (varicella-zoster virus immunoglobulin M (IgM), CMV IgM, and lymphocyte count).…”

Polypoidal Choroidal Vasculopathy: Updates on Risk Factors, Diagnosis, and Treatments

“…Recently, deep learning (DL), a new subset of AI, has been found to surpass the performance of traditional machine learning for detecting DR with a sensitivity and specificity of ≥ 95% in many studies. 66 DL was validated for other retinal diseases, including AMD, 67 retinal vein occlusion, 68 cytomegaloviral retinitis, 69 etc., with high performances.…”