Automatic Segmentation and Intuitive Visualisation of the Epiretinal Membrane in 3D OCT Images Using Deep Convolutional Approaches

Abstract

Epiretinal Membrane (ERM) is a disease caused by a thin layer of scar tissue that is formed on the surface of the retina. When this membrane appears over the macula, it can cause distorted or blurred vision. Although normally idiopathic, its presence can also be indicative of other pathologies such as diabetic macular edema or vitreous haemorrhage. ERM removal surgery can preserve more visual acuity the earlier it is performed. For this purpose, we present a fully automatic segmentation system that can help the clinicians to determine the ERM presence and location over the eye fundus using 3D Optical Coherence Tomography (OCT) volumes. The proposed system uses a convolutional neural network architecture to classify patches of the retina surface. All the 2D OCT slices of the 3D OCT volume of a patient are combined to produce an intuitive colour map over the 2D fundus reconstruction, providing a visual representation of the presence of ERM which therefore facilitates the diagnosis and treatment of this relevant eye disease. A total of 2.428 2D OCT slices obtained from 20 OCT 3D volumes was used in this work. To validate the designed methodology, several representative experiments were performed. We obtained satisfactory results with a Dice Coefficient of 0.826 ± 0.112 and a Jaccard Index of 0.714 ± 0.155, proving its applicability for diagnosis purposes. The proposed system also demonstrated its simplicity and competitive performance with respect to other state-of-the-art approaches.

Interpretable Detection of Epiretinal Membrane from Optical Coherence Tomography with Deep Neural Networks

“…We implemented not only standardized horizontal OCT scans but also vertical and oblique oriented ones. In addition to treating ERM detection as a classification task as in this study, segmentation algorithms have also been trained to detect ERMs [16,17,18]. Some of these works have primarily is the author/funder, who has granted medRxiv a license to display the preprint in (which was not certified by peer review) focused on the detection of the internal limiting membrane (ILM), which might be erroneous in eyes with a visible vitreous or posterior vitreous limiting membrane -as regularly seen in patients with ERM.…”

“…For medical reasons, it is similarly important to detect early and low-grade stages of ERMs. Finally, some studies have reported success in automatically segmenting ERMs via DNNs trained on small data sets [16, 17, 18].…”

Does imbalance in chest X-ray datasets produce biased deep learning approaches for COVID-19 screening?

“…The final dataset for each experiment where we will study the sex and age factors was divided into mutually exclusive subsets, being (60%, 20%, and 20%) for training, validation, and testing, respectively. Regarding the training, we started from the DenseNet-161 model pre-trained with the ImageNet [27] dataset, making use of the transfer learning strategy, but modifying the output layer to adapt it to our specific classification problem. In this way, the training process will be more efficient due to the faster convergence of the training and validation curves.…”

Automatic Segmentation and Visualisation of the Epirretinal Membrane in OCT Scans Using Densely Connected Convolutional Networks

“…In this work, we present an automatic methodology for the segmentation of the ERM in OCT volumes by using deep learning. This methodology consists of three phases, corresponding to the detection of the region of interest, the segmentation of the ERM via the classification of window samples of the ILM, and the visualisation and post-processing of the segmentation map [7]. This process produces a representation of the ERM presence and absence over the eye fundus in the form of a 2D colour map.…”