Abstract
We introduce a method based on Gaussian mixture model (GMM) clustering and level-set to automatically detect intraretina fluid on diabetic retinopathy (DR) from spectral domain optical coherence tomography (SD-OCT) images in this paper. First, each B-scan is segmented using GMM clustering. The original clustering results are refined using location and thickness information. Then, the spatial information among every consecutive five B-scans is used to search potential fluid. Finally, the improved level-set method is used to obtain the accurate boundaries. The high sensitivity and accuracy demonstrated here show its potential for detection of fluid.
Highlights
Diabetic retinopathy (DR) is one of the main microvascular complications of diabetes, and is the leading cause of vision loss in many developed countries.[1]
The volume of intraretinal °uid is used as a primary factor for guiding these injections, especially by subjective estimation based on limited spectral domain optical coherence tomography (SDOCT) slices, which potentially leads to substantial inconsistency in treatment
As the proposed method is based on unsupervised clustering, we added the comparison with classical unsupervised clustering — K-means clustering combined with level-set and the FCM–level-set method.[36]
Summary
Diabetic retinopathy (DR) is one of the main microvascular complications of diabetes, and is the leading cause of vision loss in many developed countries.[1] About half of all patients with DR will develop diabetic macular edema (DME). DME is the most common cause of vision loss among people with DR and it can occur at any stage of the disease course[1] and is characterized by the growth of blood vessels from choroid into the macular region. Early discovery and treatment of DME is imperative. Accurate segmentation of the °uid in the retina has an important role in the diagnosis of these diseases.[3,4]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have