Deep Learning-Based Estimation of Implantable Collamer Lens Vault Using Optical Coherence Tomography.

PURPOSE: To develop and validate a deep learning neural network for automated measurement of implantable collamer lens (ICL) vault using anterior segment optical coherence tomography (AS-OCT). DESIGN: Cross-sectional retrospective study. METHODS: A total of 2647 AS-OCT scans were used from 139 eyes of 82 subjects who underwent ICL surgery in 3 different centers. Using transfer learning, a deep learning network was trained and validated for estimating the ICL vault on OCT. A trained operator separately reviewed all OCT scans and measured the central vault using a built-in caliper tool. The model was then separately tested on 191 scans. A Bland-Altman plot was constructed and the mean absolute percentage error (MAPE), mean absolute error (MAE), root mean squared error (RMSE), Pearson correlation coefficient (r), and determination coefficient (R2) were calculated to evaluate the strength and validity of the model. RESULTS: On the test set, the model achieved a MAPE of 3.42%, an MAE of 15.82 µm, a RMSE of 18.85 µm, a Pearson correlation coefficient r of +0.98 (P < .00001), and a coefficient of determination R2 of +0.96. There was no significant difference between the vaults of the test set labeled by the technician vs those estimated by the model: 478 ± 95 µm vs 475 ± 97 µm, respectively, P = .064). CONCLUSIONS: Using transfer learning, our deep learning neural network was able to accurately compute the ICL vault from AS-OCT scans, overcoming the limitations of an imbalanced data set and limited training data. Such an algorithm can assist the postoperative assessment in ICL surgery.

Efficacy of progressive thickness intrastromal corneal ring segments in the treatment of duck phenotype keratoconus.

PURPOSE: To evaluate clinical outcomes in patients with asymmetric duck phenotype keratoconus implanted with asymmetric progressive thickness intrastromal corneal ring segments (PT-ICRS, Keraring AS, Mediphacos, Belo Horizonte, Brazil), and to demonstrate improved visual acuity and symmetry in corneal flattening. METHODS: This single-center, retrospective, observational study evaluated the clinical outcomes at 1, 3, and 6 months after implantation of PT-ICRS in patients with duck phenotype keratoconus. After creating the intrastromal tunnel with a femtosecond laser, one 160-degree arc length PT-ICRS, either 150/250 µm or 200/300 µm, was implanted. Changes in uncorrected distance visual acuity (UDVA), corrected distance visual acuity (CDVA), manifest refraction (MR), manifest refraction spherical equivalent (MRSE), mean keratometry (Kmean), maximum keratometry (Kmax), Coma@5mm, and manifest and topographical astigmatism were documented. RESULTS: The study cohort included 23 eyes of 17 patients with a mean age of 24.6 years. From baseline to 6 months following implantation, mean UDVA improved from 0.70 logarithm of the minimum angle of resolution (logMAR) (20/100 Snellen) to 0.22 logMAR (20/33 Snellen), CDVA improved from 0.33 logMAR (20/42 Snellen) to 0.14 logMAR (20/27 Snellen), the mean sphere and MRSE decreased from -1.05 diopters (D) and -2.70 D to -0.25 D and -0.80 D, respectively, and the Kmean and Kmax improved from 46.5 D and 53.7 D to 44.6 D and 48.7 D, respectively. CONCLUSIONS: The Keraring AS ICRS offers a safe, effective means of improving visual acuity while reducing refractive error, mean and max keratometry, and aberrations in patients with duck phenotype keratoconus.

Immunologic Rejection Episodes After Deep Anterior Lamellar Keratoplasty: Incidence and Risk Factors.

PURPOSE: To assess the rejection episode rate after deep anterior lamellar keratoplasty (DALK) and to identify associated risk factors. METHODS: This retrospective review of 251 primary DALK procedures performed by 14 surgeons at a single center between February 2008 and November 2015 evaluated the rejection episode rate and associated risk factors using Kaplan-Meier survival and proportional hazards analyses, which took the length of follow-up into consideration. RESULTS: Transplant indications were keratoconus or ectasia after laser refractive surgery (n = 170, 68%), corneal opacity (n = 72, 28%), and other anterior corneal disease (n = 9, 4%). The median recipient age was 46 years. The overall rejection episode rate was 14% with 18-month median follow-up and a 7-week median postoperative corticosteroid duration. In univariate analysis, increased risk of rejection episodes was associated with younger recipient age [relative risk (RR): 2.1, 95% confidence interval (CI): 1.4-5.2], African American race (RR: 2.1, 95% CI: 1.1-4.1), and use of manual trephination (compared with the femtosecond laser) for the side-cut incisions (RR: 2.7, 95% CI: 1.4-5.2). In multivariate analysis, the combined effect of patient age and race (P = 0.0012) and the side-cut method (P = 0.021) were each significant risk factors. CONCLUSIONS: This study demonstrates the substantial rate of rejection episodes that can be induced by corneal stroma in DALK and suggests that postoperative topical corticosteroids should be continued longer than the study's 7-week median and that young African Americans need higher-dose, longer-duration topical corticosteroids. The association between the side-cut method and rejection risk merits further investigation.

A year of cornea in review: 2013.

PURPOSE: The goal of this study was to provide an update of significant corneal literature published in 2013. DESIGN: This study is a systematic literature review. METHODS: We conducted a systematic review of the English-language literature published from January 1, 2013, to December 31, 2013, using the following PubMed search and Medical Subject Headings terms: cornea transplantation, keratoplasty, Descemet membrane endothelial keratoplasty, Descemet stripping endothelial keratoplasty, cross linking, pre-Descemet's layer, Rho-associated kinase, keratoprosthesis, infectious keratitis, corneal dystrophy, corneal astigmatism, and keratoconus. RESULTS: This review summarizes relevant and innovative original articles, review articles, and novel techniques from the following journals: American Journal of Ophthalmology, British Journal of Ophthalmology, Cornea, Graefe's Archive for Clinical and Experimental Ophthalmology, Investigative Ophthalmology & Visual Science, JAMA Ophthalmology, Journal of Cataract and Refractive Surgery, Journal of Refractive Surgery, and Ophthalmology. Case reports, abstracts, letters to the Editor, and unpublished work were excluded, as well as articles e-published ahead of print in 2012 that were discussed in the previous review. One hundred twenty-seven articles met the criteria for this review. CONCLUSIONS: This review summarizes significant cornea-related literature from 2013.

Long-term follow-up and complications of stripping descemet membrane without placement of graft in eyes with Fuchs endothelial dystrophy.

PURPOSE: The aim of this study was to describe the clinical course in Fuchs dystrophy where the central Descemet membrane was removed and not replaced with donor tissue. METHODS: Three patients with Fuchs endothelial dystrophy had descemetorhexis without endothelial keratoplasty. RESULTS: In each case, endothelial cells repopulated the majority of the descemetorhexis area within about 4 months, but 1 localized area failed to repopulate, which led to persistent focal edema and associated symptoms. In each case, the area that was successfully repopulated with endothelium was smooth, whereas the area that did not repopulate successfully had an irregular surface, which seemed to be caused by localized stromal roughening from the descemetorhexis. In case 2, Descemet membrane endothelial keratoplasty was performed without removing the repopulated endothelial cells, and the graft did not stick despite repeated rebubbling, so it was replaced 3 months later. The regraft adhered after stripping off the repopulated endothelial cells before inserting the new graft. CONCLUSIONS: Despite considerable surgeon experience and care exercised while performing the descemetorhexis, some roughening of the posterior stroma seemed to impede repopulation by host endothelial cells in a localized area and led to chronic corneal inflammation when a graft was not implanted. The prolonged corneal edema and associated symptoms resulted in a less desirable postoperative course compared with the rapid corneal clearing regularly achieved with Descemet membrane endothelial keratoplasty.