Search

Detecting clinical keratoconus (KCN) poses a challenging and time-consuming task. During the diagnostic process, ophthalmologists are required to review demographic and clinical ophthalmic examinations in order to make an accurate diagnosis. This study aims to develop and evaluate the accuracy of deep convolutional neural network (CNN) models for the detection of keratoconus (KCN) using corneal topographic maps. We retrospectively collected 1758 corneal images (978 normal and 780 keratoconus) from 1010 subjects of the KCN group with clinically evident keratoconus and the normal group with regular astigmatism. To expand the dataset, we developed a model using Variational Auto Encoder (VAE) to generate and augment images, resulting in a dataset of 4000 samples. Four deep learning models were used to extract and identify deep corneal features of original and synthesized images. We demonstrated that the utilization of synthesized images during training process increased classification performance. The overall average accuracy of the deep learning models ranged from 99% for VGG16 to 95% for EfficientNet-B0. All CNN models exhibited sensitivity and specificity above 0.94, with the VGG16 model achieving an AUC of 0.99. The customized CNN model achieved satisfactory results with an accuracy and AUC of 0.97 at a much faster processing speed compared to other models. In conclusion, the DL models showed high accuracy in screening for keratoconus based on corneal topography images. This is a development toward the potential clinical implementation of a more enhanced computer-aided diagnosis (CAD) system for KCN detection, which would aid ophthalmologists in validating the clinical decision and carrying out prompt and precise KCN treatment. [ABSTRACT FROM AUTHOR]

Introduction: In thyroid eye disease (TED), all ocular components and adnexa such as extraocular muscles, orbital adipose tissues, eyelids, and tear glands could be affected. This study aimed to study the orbital biomechanical parameters in patients with TED, in terms of differences with healthy individuals and correlation with clinical findings, using Corvis ST (CST, Oculus Wetzlar). Materials and methods: In this study, 26 consecutive patients with TED were recruited. Demographic data were collected, and patients with TED were assessed for exophthalmos, intraocular pressure, and clinical activity score. Biomechanical response parameters of one randomly-chosen eye of each patient, including whole eye movement length (WEMl) and time (WEMt), were evaluated by the CST, and data were compared between patients and age- and gender-matched healthy controls. Results: The mean age was 39.88 ± 11.61 years old for patients with TED and 34.38 ± 8.57 years old for the healthy subjects. Nine out of 26 patients with TED and nine of 26 healthy individuals were male. The median duration of thyroid disease was 36 (IQR 54) months and the median duration of thyroid ophthalmopathy was 27 (IQR 27) months. Four out of 26 patients (7.7%) had active disease. The mean WEMl was 206.15 ± 61.58 µm in the TED group and 254.23 ± 64.01 μm in the healthy group, the difference of which was statistically significant (p = 0.008). The median of WEMt was 20.90 (1.15) msec in the TED group and 21.45 (0.93) msec in the healthy group (p < 0.001). Also, the mean of WEMl and WEMt were lower in patients with active disease compared to patients with quiescent disease. Conclusion: The CST-derived WEMl was significantly smaller in patients with thyroid eye disease compared to normal subjects. The WEMl and WEMt were relatively shorter in the patients with active TED compared to the patients with quiescent TED, although small numbers of patients with active TED limits took a statistically significant conclusion. WEMl and WEMt might be useful in evaluating the compliance of the orbit in patients with TED. [ABSTRACT FROM AUTHOR]

Purpose: To compare optical and visual performances of two one-piece aspherical implanted intraocular lenses (IOLs) following phacoemulsification cataract surgery in a contralateral eye study. Methods: In this prospective randomized parallel-group study, 25 patients with bilateral age-related cataract were implanted in one eye with the EnVista IOL (MX60, Bausch & Lomb Corporations, Rochester, NY, USA) and the Acrysof IQ IOL (Acrysof IQ SN60WF, Alcon Surgical Laboratories, Fort Worth, TX, USA) in the other eye. Uncorrected and corrected distance visual acuity (UDVA, CDVA), refractive status, higher-orders aberrations (HOAs) in 5 and 6 mm pupil size, contrast sensitivity (CS) with and without glare, color vision status, and patient satisfaction were assessed in the two eyes at 1 and 3 months after surgery. Results: There was no significant difference in CDVA (P > 0.99), UDVA (P = 0.46), spherical equivalent refractive error (P = 0.63), CS with and without glare across different spatial frequencies, color vision, and root mean square (RMS) of aberrometric values between the two IOLs after 3-month follow-up. Spherical aberration with 5 and 6 mm pupil sizes (P = 0.02) and horizontal coma with a 6 mm pupil size (P < 0.001) were lower with the EnVista IOL. Patient's satisfaction showed no cases of dissatisfaction, and most patients were highly or moderately satisfied with both IOLs. Conclusion: The visual and optical performance of eyes implanted with the EnVista IOL or the Acrysof IQ IOL was similar, although the aberration profile differed. [ABSTRACT FROM AUTHOR]

This document is a correction notice for an article titled "Computer-aided diagnosis of keratoconus through VAE-augmented images using deep learning" published in Scientific Reports. The correction addresses an error in the spelling of one of the authors' names, Samira Hassanzadeh, which was incorrectly given as Samira Hasanzadeh. The original article has been corrected. The authors of the article are Zhila Agharezaei, Reza Firouzi, Samira Hassanzadeh, Siamak Zarei-Ghanavati, Kambiz Bahaadinbeigy, Amin Golabpour, Reyhaneh Akbarzadeh, Laleh Agharezaei, Mohamad Amin Bakhshali, Mohammad Reza Sedaghat, and Saeid Eslami. [Extracted from the article]

Purpose: To compare the safety, operating time, postoperative ocular signs, symptoms, overall patient satisfaction, complications rate and recurrence rate of autologous fibrin glue (AFG) and nylon suturing (NS) for attaching conjunctival autografts in pterygium surgery.Methods: A prospective, randomized, interventional study was performed among 120 patients (120 eyes) with primary pterygium. Superior conjunctival autograft was harvested and transferred on to bare sclera after pterygium excision. For attaching the autograft, AFG (n = 60 eyes) and NS (n = 60 eyes) were used. The patients were followed up for 12 months. The groups were compared for the safety, operative time, postoperative ocular signs, symptoms, overall patient satisfaction, recurrence and complications rate.Results: All conjunctival autografts in both groups were successfully attached. The average operating time for the AFG group was significantly shorter (P < 0.001). Postoperative symptoms were fewer for the AFG group than the suture group. After 12 months of follow-up, no recurrence was reported for the AFG group, but 8.3% of patients experienced recurrence in the NS group.Conclusions: Our study demonstrated the superiority of AFG to NS in saving operating time and elimination of recurrence without any complications in pterygium surgery. AFG can obviate the need for suturing and increases the viability of tissue flaps. Additional studies are necessary to determine the long-term effects considering factors such as primary or recurrent status of pterygium, age and sex of patient, dose and duration of treatment for mitomycin C. [ABSTRACT FROM AUTHOR]

Purpose: To compare differences in the endothelial cells before and after photorefractive keratectomy (PRK) for myopia with refractive error graded mitomycin C (MMC) application.Methods: In a prospective randomized clinical trial, forty-eight myopic patients referred to Khatam-al-Anbia Eye Hospital, Mashhad, Iran, for PRK. Patients were treated with PRK by a Bausch and Lomb Technolas 217z excimer laser (Bausch and Lomb, Rochester, NY). MMC was applied after PRK 5 s for each diopter of spherical equivalent myopic refractive error corrected. The manifest refraction, visual acuity, MMC treatment length, corneal pachymetry and specular microscopy were evaluated preoperatively and at 1 and 6 months postoperatively.Results: A total of 48 cases (96 eyes, 68.75% female) were treated, with a mean age of 26.70 ± 4.89 years (range, 18-34 years). Postoperative cell density, cell size and polymegathism did not significantly change. On the other hand, standard deviation (SD) of cell size (P = 0.008), pleomorphism (P = 0.003) and coefficient of variation (CV) (P = 0.016) were significantly increased. None of these parameters was related to the length of MMC application. Corneal thickness decreased significantly after the operation but it increased 6 months postoperatively compared with the first month (P < 0.001).Conclusion: MMC application for PRK in myopia can affect the endothelial cells, but in early follow-ups, it does not affect the cell density or size. Cell size was changed but it was obvious not in mean cell size, but in SD and CV. MMC time below the 30 s was not significant on endothelial cell changes. [ABSTRACT FROM AUTHOR]

The goal of this study was to compare differences in the mean angle kappa and its intercepts before and after photorefractive keratectomy (PRK) for myopia. In a prospective controlled study, myopic patients were treated with aspheric wavefront-guided (personalized) PRK with a Bausch & Lomb Technolas 217z excimer laser. The manifest refraction, visual acuity, and angle kappa were evaluated preoperatively and at 1 and 6 months postoperatively. The same operator performed all angle kappa measurements using Orbscan IIz. A total of 48 cases (96 eyes, 68.75 % female) with a mean age of 26.70 ± 4.89 years (18-34 years) were treated. The preoperative and postoperative mean angle kappa values were not significantly different (4.97 ± 1.24 vs 4.99 ± 1.10 at 6 months). The average horizontal distance ( x-intercept) between the visual axis and pupillary axis intersection on the corneal surface measured before surgery (−0.562 ± 0.074 mm) did not significantly differ from the values measured at 1 and 6 months after surgery (−0.559 ± 0.048 and −0.554 ± 0.055 mm, respectively). Similarly, the average vertical distance ( y-intercept) values did not differ before and at 1 and 6 months after surgery (0.156 ± 0.225, 0.142 ± 0.040, and 0.149 ± 0.33 mm, respectively). No differences in the angle kappa or its corneal intercepts were observed between pre- and post-PRK. This finding implies that PRK does not change the corneal vertex locations. [ABSTRACT FROM AUTHOR]

The article discusses the case of a 35-year-old woman diagnosed with acute infectious interface keratitis after undergoing deep anterior lamellar keratoplasty (DALK) for keratoconus, caused by Klebsiella pneumoniae. The culture of the donor sclerocorneal rim showed contamination of a Gram-negative bacillus and microbiological analysis of the excised donor graft confirmed presence of K. pneumoniae. It is suggested that these risks be considered in selecting low-quality donor corneas for DALK.