Retinal Fluid Segmentation and Detection in Optical Coherence Tomography Images using Fully Convolutional Neural Network

TL;DR

This paper introduces a novel framework combining CNNs and graph-cut algorithms for accurate retinal fluid segmentation and detection in OCT images, aiding diagnosis of retinal diseases.

Contribution

It presents a new method integrating CNNs with graph-cut segmentation and random forest classification for improved fluid detection in retinal OCT images.

Findings

Achieved a mean Dice score of 0.7317 in segmentation.

Attained a mean AUC of 0.985 in detection.

Performed well in both segmentation and detection tasks on RETOUCH database.

Abstract

As a non-invasive imaging modality, optical coherence tomography (OCT) can provide micrometer-resolution 3D images of retinal structures. Therefore it is commonly used in the diagnosis of retinal diseases associated with edema in and under the retinal layers. In this paper, a new framework is proposed for the task of fluid segmentation and detection in retinal OCT images. Based on the raw images and layers segmented 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 leave-one-out cross validation experiments on the RETOUCH database show that our method performs well in both segmentation (mean Dice: 0.7317) and detection (mean AUC: 0.985) tasks.