Automated Quantification of Vitreous Hyperreflective Foci and Vitreous Haze Using Optical Coherence Tomography in Uveitis Patients.

Purpose Development of an automated method to quantify the count of vitreous hyperreflective foci (vHF) and intensity of vitreous haze in uveitis patients by optical coherence tomography (OCT). Methods A method based on deep learning to automatically segment the vHF, vitreous and retinal pigment epithelium (RPE) in OCT was developed using 1,058 scans from 88 OCT volumes of 33 patients with intermediate, posterior or panuveitis. Based on segmented images, the vHF count and the relative intensity of vitreous to RPE (VIT/RPE-relative intensity) was quantified. Dice coefficient and intraclass correlation coefficient (ICC) were calculated between ground truth and the trained network. Results The segmented area of vHF, vitreous and RPE by the deep learning-based model showed good agreement with the clinicians' results, yielding a Dice coefficient of 0.69, 0.99, and 0.88, respectively. The ICC of the vHF count and the VIT/RPE-relative intensity per scan was 0.99 and 1.00, respectively. In eyes of test set, changes in vHF and VIT/RPE-relative intensity during treatment did not show similar patterns. Conclusions Automated segmentation of the vHF, vitreous and RPE in OCT images of uveitis patients was accomplished by a deep learning approach. The vHF count and VIT/RPE-relative intensity could be quantified with high reliability.