1 January 2017 in Journal of Korean Medical Science
Eo DR, et al. J Korean Med Sci. 2017 Mar;32(3):522-527. https://doi.org/10.3346/jkms.2017.32.3.522
1 September 2013 in American Journal of Ophthalmology
4 September 2018 in Translational Vision Science & Technology
Purpose: We investigate the measurable range of subfoveal choroidal thickness (SFCT) with conventional spectral domain optical coherence tomography (SD-OCT) in normal healthy eyes. Methods: All subjects underwent an SD-OCT horizontal line scan centered at the fovea with standard and enhanced depth imaging (EDI) techniques. Two independent observers manually measured SFCT on standard and EDI-OCT images, if two choroidal borders were identified. The rate of successful measurement with standard OCT was evaluated. Inter- and intraclass correlation coefficients and Bland-Altman plots were used for analysis. Results: OCT images of 724 normal healthy eyes from 374 subjects were evaluated. Although the inner choroidal border was identified on all OCT images, the outer choroidal border was identified on 378 of 724 (52.2%) conventional OCT images. Mean SFCT of all study eyes measured by EDI-OCT images was 292.6 ± 94.0. The number of successful measurements with conventional OCT was 100%, 87.5%, 48.1%, 33.0%, and 0%, in the SFCT ranges of 360 μm, respectively. The accumulated rate of successful measurement with conventional OCT was 100%, 96.4%, and 82.2% in the SFCT ranges of ≤240, ≤280, and ≤320 μm, respectively. Two protocols showed good inter-correlation of SFCT, when SFCT were measurable in both scans. Conclusions: SFCT can be measured by conventional OCT in eyes with thin choroid, and the measured value shows high agreement with those measured by EDI-OCT. In such eyes, conventional OCT can be used potentially to evaluate the retina and choroid. Translational Relevance: In eyes with a thin choroid, conventional OCT can be used potentially to evaluate the retina and choroid with high agreement with EDI-OCT.
22 January 2024 in Scientific Reports
We propose a hybrid technique that employs artificial intelligence (AI)-based segmentation and machine learning classification using multiple features extracted from the foveal avascular zone (FAZ)—a retinal biomarker for Alzheimer’s disease—to improve the disease diagnostic performance. Imaging data of optical coherence tomography angiography from 37 patients with Alzheimer’s disease and 48 healthy controls were investigated. The presence or absence of brain amyloids was confirmed using amyloid positron emission tomography. In the superficial capillary plexus of the angiography scans, the FAZ was automatically segmented using an AI method to extract multiple biomarkers (area, solidity, compactness, roundness, and eccentricity), which were paired with clinical data (age and sex) as common correction variables. We used a light-gradient boosting machine (a light-gradient boosting machine is a machine learning algorithm based on trees utilizing gradient boosting) to diagnose Alzheimer’s disease by integrating the corresponding multiple radiomic biomarkers. Fivefold cross-validation was applied for analysis, and the diagnostic performance for Alzheimer’s disease was determined by the area under the curve. The proposed hybrid technique achieved an area under the curve of $$72.2\pm 4.2$$ %, outperforming the existing single-feature (area) criteria by over 13%. Furthermore, in the holdout test set, the proposed technique exhibited a 14% improvement compared to single features, achieving an area under the curve of 72.0± 4.8%. Based on these facts, we have demonstrated the effectiveness of our technology in achieving significant performance improvements in FAZ-based Alzheimer’s diagnosis research through the use of multiple radiomic biomarkers (area, solidity, compactness, roundness, and eccentricity).
1 January 2012 in Korean Journal of Ophthalmology
Kong M, et al. Korean J Ophthalmol. 2012 Dec;26(6):428-431. https://doi.org/10.3341/kjo.2012.26.6.428