Automatic segmentation of abnormal capillary nonperfusion regions in optical coherence tomography angiography images using marker-controlled watershed algorithm

Abstract

Diabetic retinopathy (DR) is one of the most complications of diabetes. It is a progressive disease leading to significant vision loss in the patients. Abnormal capillary nonperfusion (CNP) regions are one of the important characteristics of DR increasing with its progression. Therefore, automatic segmentation and quantification of abnormal CNP regions can be helpful to monitor the patient's treatment process. We propose an automatic method for segmentation of abnormal CNP regions on the superficial and deep capillary plexuses of optical coherence tomography angiography (OCTA) images using the marker-controlled watershed algorithm. The proposed method has three main steps. In the first step, original images are enhanced using the vesselness filter and then foreground and background marker images are computed. In the second step, abnormal CNP region candidates are segmented using the marker-controlled watershed algorithm, and in the third step, the candidates are modeled using an undirected weighted graph and finally, by applying merging and removing procedures correct abnormal CNP regions are identified. The proposed method was evaluated on a dataset with 36 normal and diabetic subjects using the ground truth obtained by two observers. The results show the proposed method outperformed some of the state-of-the-art methods on the superficial and deep capillary plexuses according to the most important metrics.

An unsupervised hierarchical approach for automatic intra‐retinal cyst segmentation in spectral‐domain optical coherence tomography images

“…Intra‐retinal cystoids are efficiently visualized using spectral‐domain optical coherence tomography (SD‐OCT) imaging system. Spectral‐domain optical coherence tomography is a noninvasive imaging technique that provides two‐dimensional (2D) and three‐dimensional (3D) high‐resolution images from morphological changes of the retina caused by disorders like macular edema 4–6 . In this scope, different vendors are available for image acquisition which provides SD‐OCT images with a various resolution, noise level, and different intensity variations so that currently automatic IRC segmentation on images obtained from different vendors is a challenging task.…”

Hyperspectral optical coherence tomography for in vivo visualization of melanin in the retinal pigment epithelium

“…For this study, the watershed segmentation method was utilized to overcome this limitation. Although a well‐established technique in image segmentation , the application of the watershed transformation to OCT data is relatively new . This method is, however, sensitive to speckle.…”

Estimating Aboveground Carbon Stock at the Scale of Individual Trees in Subtropical Forests Using UAV LiDAR and Hyperspectral Data

“…In this study, a CHM-based watershed segmentation algorithm was used to delineate tree crowns, which had been successfully used for individual tree segmentation in many studies [43][44][45][46][47][48]. The procedure of CHM-based watershed segmentation (Figure 3) is presented in detail by Chen et al [44].…”