Macular holes are blinding conditions, where a hole develops in the central part of retina, resulting in reduced central vision. The prognosis and treatment options are related to a number of variables, including the macular hole size and shape. High-resolution spectral domain optical coherence tomography allows precise imaging of the macular hole geometry in three dimensions, but the measurement of these by human observers is time-consuming and prone to high inter- and intra-observer variability, being characteristically measured in 2-D rather than 3-D. We introduce several novel techniques to automatically retrieve accurate 3-D measurements of the macular hole, including: surface area, base area, base diameter, top area, top diameter, height, and minimum diameter. Specifically, we introduce a multi-scale 3-D level set segmentation approach based on a state-of-the-art level set method, and we introduce novel curvature-based cutting and 3-D measurement procedures. The algorithm is fully automatic, and we validate our extracted measurements both qualitatively and quantitatively, where our results show the method to be robust across a variety of scenarios. Our automated processes are considered a significant contribution for clinical applications.

The ELM height varies widely in idiopathic macular hole. It is higher in eyes where the hole is wider and also when the hole itself is higher. For holes of less than 400 μm in width, a lower ELM height is a strong independent predictor of a good postoperative outcome.

ObjectiveFull-thickness macular holes (MH) are classified principally by size, which is one of the strongest predictors of anatomical and visual success. Using a three-dimensional (3D) automated image processing algorithm, we analysed optical coherence tomography (OCT) images of 104 MH of patients, comparing MH dimensions and morphology with clinician-acquired two-dimensional measurements.Methods and AnalysisAll patients underwent a high-density central horizontal scanning OCT protocol. Two independent clinicians measured the minimum linear diameter (MLD) and maximum base diameter. OCT images were also analysed using an automated 3D segmentation algorithm which produced key parameters including the respective maximum and minimum diameter of the minimum area (MA) of the MH, as well as volume and surface area.ResultsUsing the algorithm-derived values, MH were found to have significant asymmetry in all dimensions. The minima of the MA were typically approximately 90° to the horizontal, and differed from their maxima by 55 μm. The minima of the MA differed from the human-measured MLD by a mean of nearly 50 μm, with significant interobserver variability. The resultant differences led to reclassification using the International Vitreomacular Traction Study Group classification in a quarter of the patients (p=0.07).ConclusionMH are complex shapes with significant asymmetry in all dimensions. We have shown how 3D automated analysis of MH describes their dimensions more accurately and repeatably than human assessment. This could be used in future studies investigating hole progression and outcome to help guide optimum treatments.

PurposeTo assess the accuracy of B-scan ultrasound (U/S) in diagnosing cases of acute fundus obscuring vitreous hemorrhage (FOVH) using a standardized scan protocol and dedicated ophthalmic ultrasonographer.MethodsConsecutive patients presenting with acute FOVH of unknown cause, between January 2013 and December 2014, were prospectively recruited. Patients underwent a scan performed by a dedicated ultrasonographer, utilizing a systematic scan sequence and using an ocular specific U/S device. The U/S findings were compared to the findings during vitrectomy or after spontaneous hemorrhage clearance.ResultsFifty-eight eyes (58 patients) were included. An underlying rhegmatogenous retinal detachment (RRD) and retinal tears without RRD were reported in nine and 14 patients, respectively. Nineteen of these patients underwent vitrectomy, and the other four underwent laser retinopexy or cryopexy alone. An additional six patients with suspected but uncertain retinal tears underwent vitrectomy, during which tears were confirmed in three, two had retinal vessel avulsions, and one had retinal new vessels. There was “complete” agreement between the B-scan findings and clinical findings in 78% of patients, “partial” agreement in 19%, and agreement was not tested in 3%. When the agreement was “partial”, the disagreements did not affect patient management. The sensitivity was 100% for the detection of RRD, and for the detection of new retinal tears in patients without retinal detachment.ConclusionB-scan U/S scan was highly sensitive in identifying the pathology in acute FOVH. Our results show an improvement from previously reported results, likely related to the standardized scan protocol and dedicated ophthalmic ultrasonographer.

This paper investigates the application of deep convolutional neural networks with prohibitively small datasets to the problem of macular edema segmentation. In particular, we investigate several different heavily regularized architectures. We find that, contrary to popular belief, neural architectures within this application setting are able to achieve close to humanlevel performance on unseen test images without requiring large numbers of training examples. Annotating these 3D datasets is difficult, with multiple criteria required. It takes an experienced clinician two days to annotate a single 3D image, whereas our trained model achieves similar performance in less than a second. We found that an approach which uses targeted dataset augmentation, alongside architectural simplification with an emphasis on residual design, has acceptable generalization performance -despite relying on fewer than 15 training examples.