Deep-learning based multiclass retinal fluid segmentation and detection in optical coherence tomography images using a fully convolutional neural network

•A novel deep learning based framework was proposed for multiclass retinal fluid segmentation and detection in OCT images. A fully convolutional neural network was applied for fluid segmentation followed by a random forest classifier to improve the accuracy.•Additional pixel-wise spatial information from layer segmentation was introduced for fully convolutional neural network based fluid segmentation followed by random forest classification to rule out false positive regions and determine the fluid presence in each volume.•The proposed framework won the first place in the Retinal OCT Fluid Challenge in the 2017 Medical Image Computing and Computer Assisted InterventionsConference (MICCAI) on both segmentation and detection tasks. As a non-invasive imaging modality, optical coherence tomography (OCT) can provide micrometer-resolution 3D images of retinal structures. These images can help reveal disease-related alterations below the surface of the retina, such as the presence of edema, or accumulation of fluid which can distort vision, and are an indication of disruptions in the vasculature of the retina. In this paper, a new framework is proposed for multiclass fluid segmentation and detection in the retinal OCT images. Based on the intensity of OCT images and retinal layer segmentations provided by a graph-cut algorithm, a fully convolutional neural network was trained to recognize and label the fluid pixels. Random forest classification was performed on the segmented fluid regions to detect and reject the falsely labeled fluid regions. The proposed framework won the first place in the MICCAI RETOUCH challenge in 2017 on both the segmentation performance (mean Dice: 0.7667) and the detection performance (mean AUC: 1.00) tasks. [Display omitted]