IMAGE EVALUATION OF ARTIFICIAL INTELLIGENCE-SUPPORTED OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY IMAGING USING OCT-A1 DEVICE IN DIABETIC RETINOPATHY.

PURPOSE: To investigate the effect of denoise processing by artificial intelligence (AI) on the optical coherence tomography angiography (OCTA) images in eyes with retinal lesions. METHODS: Prospective, observational, cross-sectional study. Optical coherence tomography angiography imaging of a 3 × 3-mm area involving the lesions (neovascularization, intraretinal microvascular abnormality, and nonperfusion area) was performed five times using OCT-HS100 (Canon, Tokyo, Japan). We acquired AI-denoised OCTA images and averaging OCTA images generated from five cube scan data through built-in software. Main outcomes were image acquisition time and the subjective assessment by graders and quantitative measurements of original OCTA images, averaging OCTA images, and AI-denoised OCTA images. The parameters of quantitative measurements were contrast-to-noise ratio, vessel density, vessel length density, and fractal dimension. RESULTS: We studied 56 eyes from 43 patients. The image acquisition times for the original, averaging, and AI-denoised images were 31.87 ± 12.02, 165.34 ± 41.91, and 34.37 ± 12.02 seconds, respectively. We found significant differences in vessel density, vessel length density, fractal dimension, and contrast-to-noise ratio (P < 0.001) between original, averaging, and AI-denoised images. Both subjective and quantitative evaluations showed that AI-denoised OCTA images had less background noise and depicted vessels clearly. In AI-denoised images, the presence of fictional vessels was suspected in 2 of the 35 cases of nonperfusion area. CONCLUSION: Denoise processing by AI improved the image quality of OCTA in a shorter time and allowed more accurate quantitative evaluation.

NONPERFUSION AREA QUANTIFICATION IN BRANCH RETINAL VEIN OCCLUSION: A Widefield Optical Coherence Tomography Angiography Study.

PURPOSE: To precisely quantify retinal nonperfusion areas (NPAs) in branch retinal vein occlusion using widefield optical coherence tomography angiography (OCTA) and examine their association with neovascular complications. METHODS: We enrolled 26 patients with treatment-naïve branch retinal vein occlusion and prospectively examined them for 12 months. After 3 monthly ranibizumab injections to treat macular edema, each patient underwent ultra-widefield (UWF) fluorescein angiography (FA) and OCTA. Ultra-widefield FA was additionally performed at Month 12. For UWF FA, the retinal NPA was measured using the equipment's built-in software. For OCTA, we used panoramic image montaged from 5 single 12 × 12 mm2 images and quantified the retinal NPA using a Gullstrand eye with a grid scale at each patient. Measurements were expressed in terms of actual values and disc area units. RESULTS: The retinal NPAs as measured using single OCTA and panoramic OCTA were significantly associated with that measured using UWF FA (P < 0.001 for both). Retinal neovascularization lesions were observed in 4 (15.4%) of 26 eyes. For patients with accompanying neovascularization, the retinal NPA measured using UWF FA, single OCTA, and panoramic OCTA were 187.9 ± 39.5 mm2 (109.9 ± 21.4 disc area), 34.3 ± 13.7 mm2 (19.9 ± 7.7 disc area), and 106.6 ± 24.5 mm2 (62.4 ± 13.6 disc area), respectively, which were larger than for those without neovascularization (P < 0.001, 0.014, and <0.001, respectively). CONCLUSION: Using widefield OCTA, we could quantify the retinal NPA of eyes with branch retinal vein occlusion. These could serve as valid references to assess the risk of neovascular complications.

Ultrastructure and hemodynamics of microaneurysms in retinal vein occlusion examined by an offset pinhole adaptive optics scanning light ophthalmoscope.

Retinal microaneurysms (MAs) associated with retinal vein occlusions often cause macular edema due to vascular leakage from the MAs, which can lead to severe vision loss. However, studies using conventional imaging modalities have not shown a significant association between MAs and retinal functional changes. The recent technological advancements to the adaptive optics scanning light ophthalmoscope (AOSLO) have enabled real-time observation of the human retinal microvasculature. Additionally, offsetting the confocal aperture in the AOSLO enables the blocking of specular reflection from the inner retina and the enhancement of the image contrast of the retinal capillaries. This study investigated the ultrastructure and hemodynamics of MAs examined by structural images and perfusion maps of the offset pinhole AOSLO and evaluated their associations with vascular leakage on fluorescein angiography. Our results show the diverse configurations of the MAs, some of which are occasionally accompanied by a cap structure on the aneurysmal surface. Moreover, the morphological and hemodynamic changes were significantly associated with vascular leakage.

Usefulness of Denoising Process to Depict Myopic Choroidal Neovascularisation Using a Single Optical Coherence Tomography Angiography Image.

Quality of single optical coherence tomography angiography (OCTA) images of myopic choroidal neovascularisation (mCNV) is poorer than in averaged images, although obtaining averaged images takes much time. This study evaluated the clinical usefulness of novel denoising process for depicting mCNV. This study included 20 eyes of 20 patients with mCNV. Ten en face images taken in a 3 × 3 mm macular cube were obtained from outer-retina-to-choriocapillaris layer. Three image types were prepared for analysis; single images before and after the denoising process accomplished deep learning (single and denoising groups, respectively) and up to 10 images were averaged (averaging group). Pairwise comparisons showed vessel density, vessel length density, and fractal dimension (FD) were higher; whereas, vessel density index (VDI) was lower in single group than in denoising and averaging groups. Detectable CNV indices, contrast-to-nose ratio, and CNV diagnostic scores were higher in denoising and averaging groups than in single group. No significant differences were detected in VDI, FD, or CNV diagnostic scores between denoising and averaging groups. The denoising process can utilise single OCTA images to provide results comparable to averaged OCTA images, which is clinically useful for shortening examination times with quality similar to averaging.