Development and quantitative assessment of deep learning-based image enhancement for optical coherence tomography.

PURPOSE: To develop a deep learning-based framework to improve the image quality of optical coherence tomography (OCT) and evaluate its image enhancement effect with the traditional image averaging method from a clinical perspective. METHODS: 359 normal eyes and 456 eyes with various retinal conditions were included. A deep learning framework with high-resolution representation was developed to achieve image quality enhancement for OCT images. The quantitative comparisons, including expert subjective scores from ophthalmologists and three objective metrics of image quality (structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR) and contrast-to-noise ratio (CNR)), were performed between deep learning method and traditional image averaging. RESULTS: With the increase of frame count from 1 to 20, our deep learning method always obtained higher SSIM and PSNR values than the image averaging method while importing the same number of frames. When we selected 5 frames as inputs, the local objective assessment with CNR illustrated that the deep learning method had more obvious tissue contrast enhancement than averaging method. The subjective scores of image quality were all highest in our deep learning method, both for normal retinal structure and various retinal lesions. All the objective and subjective indicators had significant statistical differences (P < 0.05). CONCLUSION: Compared to traditional image averaging methods, our proposed deep learning enhancement framework can achieve a reasonable trade-off between image quality and scanning times, reducing the number of repeated scans.

THE INCIDENCE, CHARACTERISTICS, MANAGEMENT, PROGNOSIS, AND CLASSIFICATION OF BREAKTHROUGH VITREOUS HEMORRHAGE SECONDARY TO POLYPOIDAL CHOROIDAL VASCULOPATHY.

PURPOSE: To describe breakthrough vitreous hemorrhage secondary to polypoidal choroidal vasculopathy (PCV). METHODS: Patients with the diagnosis of PCV from January 2005 to March 2020 at Peking Union Medical College Hospital were retrospectively reviewed, cases with breakthrough vitreous hemorrhage were analyzed. Subgroup analysis was conducted regarding pachychoroid PCV and nonpachychoroid PCV. RESULTS: Among 722 PCV patients (834 eyes), 103 eyes with breakthrough vitreous hemorrhage (12.4%) were included. Pars plana vitrectomy and proper further interventions could significantly improve the best-corrected visual acuity from logMAR 2.15 ± 0.48 (Snellen 20/2825) to 1.65 ± 0.67 (20/893). Hemorrhagic retinal detachment, baseline central macular thickness, and best-corrected visual acuity were factors associated with final best-corrected visual acuity (P < 0.05). In the pachychoroid PCV group, patients were younger, all had hemorrhagic pigment epithelial detachment, with a higher prevalence of choroidal vascular hyperpermeability and hemorrhagic retinal detachment, thicker subfoveal choroidal thickness, and thinner central macular thickness; besides, the initial pars plana vitrectomy were more complicated, more additional surgeries had to be performed. More eyes in the nonpachychoroid PCV group had received anti-vascular endothelial growth factor or photodynamic therapy, mostly fibrovascular pigment epithelial detachment, the best-corrected visual acuity and the status of the fellow eye were significantly worse. For the final ocular status, more eyes in nonpachychoroid PCV group were taking anti-vascular endothelial growth factor monotherapy, whereas more eyes in pachychoroid PCV group were stable. The choroidal parameters of these two groups were all significantly different. CONCLUSION: Breakthrough vitreous hemorrhage is a troublesome complication of PCV. Pars plana vitrectomy and additional interventions are required for better prognosis. Vitreous hemorrhage secondary to pachychoroid PCV or nonpachychoroid PCV have different characteristics and prognosis.