Statistical Modeling of Retinal Optical Coherence Tomography Using the Weibull Mixture Model Publisher

Summary: Weibull mixture model for retinal OCT images improved denoising and feature extraction; SVM classification distinguished healthy vs. PED-affected retina. #OCT #MedicalImaging #AIinMedicine

Jorjandi S¹ ; Amini Z² ; Plonka G³ ; Rabbani H²
Source: Biomedical Optics Express Published:2021

Abstract

In this paper, a novel statistical model is proposed for retinal optical coherence tomography (OCT) images. According to the layered structure of the retina, a mixture of six Weibull distributions is proposed to describe the main statistical features of OCT images. We apply Weibull distribution to establish a more comprehensive model but with fewer parameters that has better goodness of fit (GoF) than previous models. Our new model also takes care of features such as asymmetry and heavy-tailed nature of the intensity distribution of retinal OCT data. In order to test the effectiveness of this new model, we apply it to improve the low quality of the OCT images. For this purpose, the spatially constrained Gaussian mixture model (SCGMM) is implemented. Since SCGMM is designed for data with Gaussian distribution, we convert our Weibull mixture model to a Gaussian mixture model using histogram matching before applying SCGMM. The denoising results illustrate the remarkable performance in terms of the contrast to noise ratio (CNR) and texture preservation (TP) compared to other peer methods. In another test to evaluate the efficiency of our proposed model, the parameters and GoF criteria are considered as a feature vector for support vector machine (SVM) to classify the healthy retinal OCT images from pigment epithelial detachment (PED) disease. The confusion matrix demonstrates the impact of the proposed model in our preliminary study on the OCT classification problem. © 2021 Optical Society of America under the terms of the OSA Open Access Publishing Agreement.