Differential diagnosis of CMV retinitis

Cytomegalovirus Retinitis: Clinical Manifestations, Diagnosis and Treatment

Cytomegalovirus (CMV) retinitis is the most common eye disease associated with CMV infection in immunocompromised individuals. The CMVR may initially be asymptomatic; however, relatively mild vitreous inflammation at the onset may be an important differential point from other diseases in HIV patients. Fundus photography, CD4 T-cell count, and telemedicine could be used to screen and monitor the high-risk population, particularly in resource-limited regions. Retinitis generally starts in the peripheral retina and advances toward the posterior pole, which could develop to the characteristic "pizza pie" appearance marked by central retinal necrosis and intraretinal hemorrhage. CMVR causes vision loss if left untreated, and early antiviral therapy significantly reduces the risk of vision loss. Alongside traditional antiviral treatments, immunotherapies including CMV-specific adoptive T-cell therapy and CMV immunoglobulin (CMVIG) are emerging as promising treatment options due to their favorable tolerability and reduced mortality. This review comprehensively examines CMV retinitis, encompassing the clinical features, differential diagnosis, laboratory tests, and updated treatment strategies to inform clinical management.

Multitask Deep Learning for Joint Detection of Necrotizing Viral and Noninfectious Retinitis From Common Blood and Serology Test Data

Purpose

Necrotizing viral retinitis is a serious eye infection that requires immediate treatment to prevent permanent vision loss. Uncertain clinical suspicion can result in delayed diagnosis, inappropriate administration of corticosteroids, or repeated intraocular sampling. To quickly and accurately distinguish between viral and noninfectious retinitis, we aimed to develop deep learning (DL) models solely using noninvasive blood test data.

Methods

This cross-sectional study trained DL models using common blood and serology test data from 3080 patients (noninfectious uveitis of the posterior segment [NIU-PS] = 2858, acute retinal necrosis [ARN] = 66, cytomegalovirus [CMV], retinitis = 156). Following the development of separate base DL models for ARN and CMV retinitis, multitask learning (MTL) was employed to enable simultaneous discrimination. Advanced MTL models incorporating adversarial training were used to enhance DL feature extraction from the small, imbalanced data. We evaluated model performance, disease-specific important features, and the causal relationship between DL features and detection results.

Results

The presented models all achieved excellent detection performances, with the adversarial MTL model achieving the highest receiver operating characteristic curves (0.932 for ARN and 0.982 for CMV retinitis). Significant features for ARN detection included varicella-zoster virus (VZV) immunoglobulin M (IgM), herpes simplex virus immunoglobulin G, and neutrophil count, while for CMV retinitis, they encompassed VZV IgM, CMV IgM, and lymphocyte count. The adversarial MTL model exhibited substantial changes in detection outcomes when the key features were contaminated, indicating stronger causality between DL features and detection results.

Conclusions

The adversarial MTL model, using blood test data, may serve as a reliable adjunct for the expedited diagnosis of ARN, CMV retinitis, and NIU-PS simultaneously in real clinical settings.

Automated Cytomegalovirus Retinitis Screening in Fundus Images

This work proposes an automated algorithms for classifying retinal fundus images as cytomegalovirus retinitis (CMVR), normal, and other diseases. Adaptive wavelet packet transform (AWPT) was used to extract features. The retinal fundus images were transformed using a 4-level Haar wavelet packet (WP) transform. The first two best trees were obtained using Shannon and log energy entropy, while the third best tree was obtained using the Daubechies-4 mother wavelet with Shannon entropy. The coefficients of each node were extracted, where the feature value of each leaf node of the best tree was the average of the WP coefficients in that node, while those of other non-leaf nodes were set to zero. The feature vector was classified using an artificial neural network (ANN). The effectiveness of the algorithm was evaluated using ten-fold cross-validation over a dataset consisting of 1,011 images (310 CMVR, 240 normal, and 461 other diseases). In testing, a dataset consisting of 101 images (31 CMVR, 24 normal, and 46 other diseases), the AWPT-based ANN had sensitivities of 90.32%, 83.33%, and 91.30% and specificities of 95.71%, 94.81%, and 92.73%. In conclusion, the proposed algorithm has promising potential in CMVR screening, for which the AWPT-based ANN is applicable with scarce data and limited resources.

Unravelling the Gordian knot: diagnostic dilemma in an HIV-positive patient with neurological involvement

We report a case of a 40-year-old seropositive-HIV patient with a CD4 count of 120 who presented with fever, severe headache and neck stiffness. Suspecting a case of tubercular meningitis (TBM; as tuberculosis is the commonest opportunistic infection in HIV/AIDS patients in India), a lumbar puncture was performed and a cerebrospinal fluid study revealed TBM. The patient was started on combination antitubercular drug therapy from directly observed treatment, short course (DOTS) (Cat 1 regimen) along with pyridoxine 40 mg/day and adjunctive corticosteroid therapy. However, despite adequate antitubercular therapy for 4 weeks, the patient did not show any improvement in his clinical condition. On the contrary, in the process he developed cytomegalovirus (CMV) retinitis. So we question our learned readers if the coinfection of Mycobacterium tuberculosis and CMV should be implicated for the failure to respond to isolated antitubercular therapy contrary to our expectation.

Review for disease of the year: differential diagnosis of ocular toxoplasmosis

The diagnosis of ocular toxoplasmosis is mainly clinical, based in the presence of focal necrotizing retinochoroiditis often associated with a preexistent chorioretinal scar, and variable involvement of the vitreous, retinal blood vessels, optic nerve, and anterior segment of the eye. Recognition of this clinical spectrum of toxoplasmic retinochoroiditis is crucial, but other infectious, noninfectious, and neoplastic entities should also be considered in the differential diagnosis. Investigations such as serological tests, polymerase chain reaction of ocular fluids, and assessment of intraocular antibody synthesis are helpful in uncertain cases. This article provides an overview of the differential diagnosis of ocular toxoplasmosis, focusing on the most important entities to be considered and emphasizing distinctive features of each one of them in the clinical setting. Ocular toxoplasmosis has multiple clinical manifestations, which partially overlap with those of other entities and these should be carefully considered when making the differential diagnosis, particularly in less typical cases.

Fundus autofluorescence changes in cytomegalovirus retinitis

PURPOSE

The purpose of this study was to describe fundus autofluorescence imaging features of cytomegalovirus (CMV) retinitis and to correlate fundus autofluorescence features with clinical activity.

METHODS

A retrospective case series was undertaken to evaluate nine eyes of six patients with active CMV retinitis. Patients were evaluated with a comprehensive ophthalmic examination, fundus autofluorescence imaging, and fundus photography. Oral valganciclovir, intravitreal ganciclovir, intravitreal foscarnet, or an ganciclovir implant was administered as clinically indicated.

RESULTS

In all nine eyes with active CMV retinitis, a hyperautofluorescent signal on fundus autofluorescence imaging was correlated spatially with the border of advancing CMV retinitis. Stippled areas of alternating hyperautofluorescence and hypoautofluorescence were observed in regions of retinal pigment epithelium atrophy from prior CMV retinitis. In three eyes with subtle CMV reactivation, a hyperautofluorescent border was helpful in the detection and localization of active CMV retinitis. In another patient, diffuse, punctate hyperautofluorescence after intravitreal ganciclovir and foscarnet was a concern for medication-related toxicity.

CONCLUSION

Fundus autofluorescence imaging was valuable in highlighting areas of active CMV retinitis in all patients in this series, including two patients with subtle clinical features. Fundus autofluorescence may be useful as an adjunctive imaging modality for the detection of CMV activity and aid in our understanding of the structural changes during episodes of CMV retinitis.