Eyes with thinner CCT and eyes with higher IOP are more predisposed to have lower CH. Refractive surgeons should, from a biomechanical viewpoint, take not only CCT but also IOP into consideration before performing keratorefractive surgery.

ObjectiveTo evaluate the diagnostic accuracy of keratoconus using deep learning of the colour-coded maps measured with the swept-source anterior segment optical coherence tomography (AS-OCT).DesignA diagnostic accuracy study.SettingA single-centre study.ParticipantsA total of 304 keratoconic eyes (grade 1 (108 eyes), 2 (75 eyes), 3 (42 eyes) and 4 (79 eyes)) according to the Amsler-Krumeich classification, and 239 age-matched healthy eyes.Main outcome measuresThe diagnostic accuracy of keratoconus using deep learning of six colour-coded maps (anterior elevation, anterior curvature, posterior elevation, posterior curvature, total refractive power and pachymetry map).ResultsDeep learning of the arithmetical mean output data of these six maps showed an accuracy of 0.991 in discriminating between normal and keratoconic eyes. For single map analysis, posterior elevation map (0.993) showed the highest accuracy, followed by posterior curvature map (0.991), anterior elevation map (0.983), corneal pachymetry map (0.982), total refractive power map (0.978) and anterior curvature map (0.976), in discriminating between normal and keratoconic eyes. This deep learning also showed an accuracy of 0.874 in classifying the stage of the disease. Posterior curvature map (0.869) showed the highest accuracy, followed by corneal pachymetry map (0.845), anterior curvature map (0.836), total refractive power map (0.836), posterior elevation map (0.829) and anterior elevation map (0.820), in classifying the stage.ConclusionsDeep learning using the colour-coded maps obtained by the AS-OCT effectively discriminates keratoconus from normal corneas, and furthermore classifies the grade of the disease. It is suggested that this will become an aid for improving the diagnostic accuracy of keratoconus in daily practice.Clinical trial registration number000034587.

ABSTRACT.Purpose: To investigate the intraocular pressure (IOP) and corneal biomechanical properties of normal and normal-tension glaucoma (NTG) eyes. Methods: This study included 83 normal and 83 NTG eyes. We measured corneal-compensated IOP (IOPcc), Goldmann-correlated IOP (IOPg), corneal resistance factor (CRF), corneal hysteresis (CH) and central corneal thickness (CCT) three times each for normal and NTG eyes using an Ocular Response Analyzer (ORA). Results: No significant difference in CCT was seen between normal eyes (541.4 ± 26.8 lm) and NTG eyes (535.4 ± 24.9 lm; p = 0.16). IOPcc was significantly higher in NTG eyes (16.1 ± 2.6 mmHg) than in normal eyes (15.1 ± 2.9 mmHg; p = 0.01), while IOPg was significantly lower in NTG eyes (14.1 ± 2.7 mmHg) than in normal eyes (15.1 ± 3.0 mmHg; p = 0.04). CRF and CH were significantly lower in NTG eyes (CRF, 8.9 ± 1.5 mmHg; CH, 9.2 ± 1.3 mmHg) than in normal eyes (CRF, 10.6 ± 1.4 mmHg; CH, 10.8 ± 1.3 mmHg; p < 0.0001 each). Conclusion: IOPcc was significantly higher in NTG eyes than in normal eyes. The ORA may be useful for distinguishing between the IOPcc of NTG eyes with normal IOP and that of normal eyes. In addition, the ORA enables CRF and CH to be measured in vivo, and weakness of the lamina cribrosa may be clinically inferred from the fact that CRF and CH were reduced in NTG eyes in our study. Low CRF and CH may be clues to the pathology of NTG.

Both IOPcc and IOP(G) measured with ORA were less affected by the amount of corneal astigmatism, and the GAT-IOP readings were significantly higher in eyes with greater corneal astigmatism, suggesting that IOPcc as well as IOP(G) may be helpful for accurate IOP measurements in eyes with some corneal astigmatism.