High Blood Cytomegalovirus Load Suggests Cytomegalovirus Retinitis in HIV/AIDS Patients: A Cross-Sectional Study

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

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.

CMV Retinitis in Wiskott Aldrich Syndrome

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.