Universal architecture of corneal segmental tomography biomarkers for artificial intelligence-driven diagnosis of early keratoconus

AimsTo develop a comprehensive three-dimensional analyses of segmental tomography (placido and optical coherence tomography) using artificial intelligence (AI).MethodsPreoperative imaging data (MS-39, CSO, Italy) of refractive surgery patients with stable outcomes and diagnosed with asymmetric or bilateral keratoconus (KC) were used. The curvature, wavefront aberrations and thickness distributions were analysed with Zernike polynomials (ZP) and a random forest (RF) AI model. For training and cross-validation, there were groups of healthy (n=527), very asymmetric ectasia (VAE; n=144) and KC (n=454). The VAE eyes were the fellow eyes of KC patients but no further manual segregation of these eyes into subclinical or forme-fruste was performed.ResultsThe AI achieved an excellent area under the curve (0.994), accuracy (95.6%), recall (98.5%) and precision (92.7%) for the healthy eyes. For the KC eyes, the same were 0.997, 99.1%, 98.7% and 99.1%, respectively. For the VAE eyes, the same were 0.976, 95.5%, 71.5% and 91.2%, respectively. Interestingly, the AI reclassified 36 (subclinical) of the VAE eyes as healthy though these eyes were distinct from healthy eyes. Most of the remaining VAE (n=104; forme fruste) eyes retained their classification, and were distinct from both KC and healthy eyes. Further, the posterior surface features were not among the highest ranked variables by the AI model.ConclusionsA universal architecture of combining segmental tomography with ZP and AI was developed. It achieved an excellent classification of healthy and KC eyes. The AI efficiently classified the VAE eyes as ‘subclinical’ and ‘forme-fruste’.

Piezostack deformable mirror with high technological effectiveness

Deformable mirror (DM) is an active element that can change the shape of the surface to compensate for wavefront aberrations. Historically, the development of DMs started from piezostack deformable mirrors (PDM) due to their large stroke, flexibility in actuators geometry, high resonant frequency. However, the cost of PDMs is comparatively high because of their labor-intensive process of manufacturing. In the article innovative design of PDM is presented. The assembling of unconventional PDMs was carried out using piezoceramic combs. This step should allow to decrease number of technological steps, increase spatial resolution of the mirror and thereby reduce the cost of final product.

Ocular wavefront aberrations in acute central serous chorioretinopathy

Background: Central serous chorioretinopathy (CSCR) is a condition of choroidal and retinal pathologies that may affect vision, so we assessed vision by the ocular wavefront in the acute form of CSCR. Methods: This cross-sectional study included 21 cases (16-male, 5-female) of acute onset CSCR was referred to the retina clinic of Nikookari Eye Hospital. Visual acuity and ocular examination with and without pupillary dilation record. Central macular thickness and sub-foveal fluid height of all patients measured by spectral-domain optical coherence tomography (SD-OCT). All of them fulfilled binocular visual function analyzer by Tracy Technology after complete pupillary dilation. The items such as spherical equivalent, total root mean square, total lower-order aberration, total higher-order aberration, defocus, astigmatism, secondary astigmatism, coma, spherical aberration, trefoil, Strehl ratio in point spread function, the average height in the modulation transfer function, and root mean square error registered. Generalized Estimation Equations (GEE) were used to compare two groups of affected CSCR and normal contralateral eyes. Results: The mean uncorrected distance visual acuity in the CSCR eyes is (Decimal Notation) 0.82±0.17 and in the contralateral eyes is 0.95±0.09 (P=0.002). Analysis of macular OCT data CSCR group represents: central foveal thickness 485.9±165.12 μm and mean fluid height 284.3±165.42 μm. The mentioned optical parameters of ocular wavefront aberrations do not have significantly different results in the two groups. Conclusion: Our study showed CSCR reduced uncorrected visual acuity but it did not detect significant ocular wavefront changes in acute CSCR