Computer-aided diagnosis (CAD) of retinal pathologies is a current active area in medical image analysis. Due to the increasing use of retinal optical coherence tomography (OCT) imaging technique, a CAD system in retinal OCT is essential to assist ophthalmologist in the early detection of ocular diseases and treatment monitoring. This paper presents a novel CAD system based on a multi-scale convolutional mixture of expert (MCME) ensemble model to identify normal retina, and two common types of macular pathologies, namely, dry age-related macular degeneration (AMD), and diabetic macular edema (DME). The proposed MCME modular model is a data-driven neural structure which employs a new cost function for discriminative and fast learning of image features by applying convolutional neural networks (CNNs) on multiple-scale sub-images. MCME maximizes the likelihood function of the training dataset and ground truth by considering a mixture model, which tries to also model the joint interaction between individual experts by using a correlated multivariate component for each expert module instead of only modeling the marginal distributions by independent Gaussian components. Two different macular OCT datasets from Heidelberg devices were considered for the evaluation of the method, i.e., a local dataset of OCT images of 148 subjects and a public dataset of 45 OCT acquisitions. For comparison purpose, we performed a wide range of classification measures to compare the results with the best configurations of the MCME method. With the MCME model of 4 scale-dependent experts, the precision rate of 98.86%, and the area under the ROC curve (AUC) of 0.9985 were obtained on average.

The introduction of enhanced depth imaging optical coherence tomography (EDI-OCT) has provided the advantage of in vivo cross-sectional imaging of the choroid, similar to the retina, with standard commercially available spectral domain (SD) OCT machines. A texture-based algorithm is introduced in this paper for fully automatic segmentation of choroidal images obtained from an EDI system of Heidelberg 3D OCT Spectralis. Dynamic programming is utilized to determine the location of the retinal pigment epithelium (RPE). Bruch’s membrane (BM) (the blood-retina barrier which separates the RPE cells of the retina from the choroid) can be segmented by searching for the pixels with the biggest gradient value below the RPE. Furthermore, a novel method is proposed to segment the choroid-sclera interface (CSI), which employs the wavelet based features to construct a Gaussian mixture model (GMM). The model is then used in a graph cut for segmentation of the choroidal boundary. The proposed algorithm is tested on 100 EDI OCTs and is compared with manual segmentation. The results showed an unsigned error of 2.48 ± 0.32 pixels for BM extraction and 9.79 ± 3.29 pixels for choroid detection. It implies significant improvement of the proposed method over other approaches likek-means and graph cut methods.

To review characteristics of open-globe injuries presented to Farabi Eye Hospital, a large referral center for serious ocular injury in the capital city of Iran. A retrospective review of 2,340 open-globe injury patients during a 5-year period was performed. Data about any patient that was diagnosed as open-globe injury were collected from medical records. Of 2,340 patients, 1,904 (81.4%) were men. Mean age was 22.44 +/- 16.65 years (range, 4 months to 90 years). Seventy-five percent of cases were younger than 30 years, with a peak of 5 years. There were 561 patients who had an intraocular foreign body (24.7%). In patients younger than 16 years, a knife was the most prevalent cause (22%); in patients younger than 7 years, knives accounted for 33.6% of trauma etiology; and in patients more than 16 years, a projectile metallic foreign body was the most common cause, accounting for 27% of open-globe injuries. Endophthalmitis developed in 5.1% (117 cases). Factors that had a positive association with severity of ocular injury were visual acuity lower than 20/200 at admission, endophthalmitis, double perforation, and laceration length. According to Ocular Trauma Scoring, there was better visual prognosis in younger age groups, male sex, and intraocular foreign body groups. The rate of enucleation or evisceration was 5.3% (126 cases). We had a low sympathetic ophthalmia rate of 0.08%. The most prevalent trauma etiology is a projectile metallic foreign body in adults and a knife injury in children. Compared with other previous epidemiologic studies, we had younger patients, lower enucleations, and sympathetic ophthalmia.

Purpose: To study predisposing factors of endophthalmitis in patients with open-globe injury. Methods: All 2,340 patients with open-globe injury admitted to our center over 5 years were studied retrospectively, and patients with endophthalmitis were compared with other patients. Results: The number of endophthalmitis cases among patients with open-globe injury was 117 eyes, accounting for an incidence of 5.1%. The risk of endophthalmitis was significantly higher among male patients with pure corneal injuries (6.8%), intraocular foreign bodies (9.3%), traumatic lens rupture (7.1%), trauma resulting from needles (22.2%), and shorter lacerations. The existence of hyphema or iris prolapse was associated with lower rates of endophthalmitis. The mean gap between injury time and operation time was longer in the endophthalmitis group (2.1 ± 1.8 vs. 1.1 ± 1.3 days). Patients with endophthalmitis had significantly lower ocular trauma scores compared with other patients. Conclusion: Posttraumatic endophthalmitis is more likely among patients with open-globe injury that are needle related and among those who have intraocular foreign bodies, traumatic lens rupture, smaller wounds, or wounds exclusively in the cornea. Lower ocular trauma scores in this group of patients with penetrating trauma indicated a greater risk of poor visual prognosis. Therefore, it is suggested that necessary measures and immediate treatment be undertaken in high-risk patients.

The Journal of Biomedical Optics (JBO) publishes peer-reviewed papers on the use of novel optical systems and techniques for improved health care and biomedical research.