AUTOMATED DETECTION OF VITRITIS USING ULTRAWIDE-FIELD FUNDUS PHOTOGRAPHS AND DEEP LEARNING.

BACKGROUND/PURPOSE: Evaluate the performance of a deep learning algorithm for the automated detection and grading of vitritis on ultrawide-field imaging. METHODS: Cross-sectional noninterventional study. Ultrawide-field fundus retinophotographs of uveitis patients were used. Vitreous haze was defined according to the six steps of the Standardization of Uveitis Nomenclature classification. The deep learning framework TensorFlow and the DenseNet121 convolutional neural network were used to perform the classification task. The best fitted model was tested in a validation study. RESULTS: One thousand one hundred eighty-one images were included. The performance of the model for the detection of vitritis was good with a sensitivity of 91%, a specificity of 89%, an accuracy of 0.90, and an area under the receiver operating characteristics curve of 0.97. When used on an external set of images, the accuracy for the detection of vitritis was 0.78. The accuracy to classify vitritis in one of the six Standardization of Uveitis Nomenclature grades was limited (0.61) but improved to 0.75 when the grades were grouped into three categories. When accepting an error of one grade, the accuracy for the six-class classification increased to 0.90, suggesting the need for a larger sample to improve the model performances. CONCLUSION: A new deep learning model based on ultrawide-field fundus imaging that produces an efficient tool for the detection of vitritis was described. The performance of the model for the grading into three categories of increasing vitritis severity was acceptable. The performance for the six-class grading of vitritis was limited but can probably be improved with a larger set of images.

Anterior Chamber Cytology Confirms the Diagnosis of T-cell Prolymphocytic Leukemia Masquerading as Viral Retinal Necrosis.

PURPOSE: To describe a case of T-cell prolymphocytic leukemia (T-PLL) masquerading as viral retinal necrosis (VRN). CASE PRESENTATION: A 75-year-old-man with a history of T-PLL in complete remission complained of an acute vision loss in his right and only eye. Ophthalmic examination demonstrated the presence of anterior chamber cells, mild vitritis, and peripheral retinal whitening with intraretinal hemorrhages evocative of VRN. While the anterior chamber tap came back negative for HSV, VZV, and CMV, cytology performed on the aqueous humor described the presence of leukemic cells. CONCLUSION: T-PLL can rarely masquerade as a viral retinal necrosis. Diagnostic work-up should therefore always rule out the infectious causes of retinitis. Anterior chamber tap can sometimes prove useful in the diagnosis of T-PLL even in the absence of a hypopyon, avoiding the need for vitrectomy.

Multimodality Approach to the Diagnosis and Assessment of Uveitic Macular Edema.

Purpose: To provide an overview of the role of multimodality approach to the diagnosis and assessment of uveitic macular edema (UME). Methods: Review of literature. Results: Optical coherence tomography (OCT) has become the gold standard in the detection, quantification, monitoring of treatment, and determination of prognosis in UME. Fluorescein angiography provides essential information on blood-retinal barrier disruption as a result of intraocular inflammation and allows detection of associated retinal ischemia and neovascularization. Dye-less OCT angiography can reveal the presence of various qualitative and quantitative retinal microvascular changes mostly involving the deep capillary plexus. Reading acuity and retinal sensitivity assessed by microperimetry represent sensitive measures for visual dysfunction in UME and may supplement distance visual acuity in the follow-up of patients with UME. Conclusion: Conventional and new imaging modalities and ancillary tests complement each other in the diagnosis, assessment, and monitoring of patients with UME.