Retinabeteiligung bei hämatologischen Erkrankungen

The Role of Funduscopy in Severe Thrombocytopenia: A Prospective Study

PURPOSE

Platelet transfusions for patients suffering from severe thrombocytopenia are regulated by clinical bleedings and platelet counts. The aim of this study was to assess the prevalence of retinal hemorrhage in patients with hematologic and oncologic malignancies and severe thrombocytopenia, and to determine the benefit of systematic funduscopic examination in this setting.

MATERIALS AND METHODS

Hospitalized patients with hematologic and oncologic malignancies having a platelet count less than 25,000 per µL underwent indirect ophthalmoscopy. The prevalence of retinal hemorrhage and its correlation with different patients' characteristics were determined. The decision to transfuse platelets or not following bedside indirect ophthalmoscopy was left at the discretion of the treating physician.

RESULTS

A total of 34 severe thrombocytopenic patients were included in the study. The prevalence of retinal hemorrhage was detected in 10 patients (29.4%). No significant correlation was found between the occurrence of retinal hemorrhage and age, platelet count or thrombocytopenia etiology (P >0.05). No significant difference was found concerning the rate of transfusion between those with and without retinal hemorrhage.

CONCLUSION

According to our statistical results, retinal hemorrhage is a frequent finding in severely thrombocytopenic patients. Early detection may lead to an increase in the platelet transfusion threshold from to 30,000 per µL offering additional protection against spontaneous bleedings. Funduscopy is a safe and easy exam to perform systematically in patients with severe thrombocytopenia.

[Retinal tumors in adults: Part 2 nonvascular tumors of retina and retinal pigment epithelium]

Retinal tumors are a heterogeneous group of congenital and acquired lesions. In the second part of the article retinocytic and glial cell tumors of the retina, tumors of the retinal pigment epithelium, malignant tumors, such as lymphomas and metastases are presented. In benign and malignant tumors visual symptoms, such as exudative retinal detachment occur, which often lead to irreversible visual impairments. Because visual symptoms are often a manifestation of systemic diseases, the ophthalmologist plays an important role in the accurate and early diagnosis of retinal tumors. This article reviews the most important clinical and diagnostic features of retinal tumors in adults, the systemic associations and the literature on currently available treatment strategies.

Development and Evaluation of a Deep Learning System for Screening Retinal Hemorrhage Based on Ultra-Widefield Fundus Images

Purpose

To develop and evaluate a deep learning (DL) system for retinal hemorrhage (RH) screening using ultra-widefield fundus (UWF) images.

Methods

A total of 16,827 UWF images from 11,339 individuals were used to develop the DL system. Three experienced retina specialists were recruited to grade UWF images independently. Three independent data sets from 3 different institutions were used to validate the effectiveness of the DL system. The data set from Zhongshan Ophthalmic Center (ZOC) was selected to compare the classification performance of the DL system and general ophthalmologists. A heatmap was generated to identify the most important area used by the DL model to classify RH and to discern whether the RH involved the anatomical macula.

Results

In the three independent data sets, the DL model for detecting RH achieved areas under the curve of 0.997, 0.998, and 0.999, with sensitivities of 97.6%, 96.7%, and 98.9% and specificities of 98.0%, 98.7%, and 99.4%. In the ZOC data set, the sensitivity of the DL model was better than that of the general ophthalmologists, although the general ophthalmologists had slightly higher specificities. The heatmaps highlighted RH regions in all true-positive images, and the RH within the anatomical macula was determined based on heatmaps.

Conclusions

Our DL system showed reliable performance for detecting RH and could be used to screen for RH-related diseases.

Translational Relevance

As a screening tool, this automated system may aid early diagnosis and management of RH-related retinal and systemic diseases by allowing timely referral.