Automated Segmentation and Quantification of Drusen in Fundus and Optical Coherence Tomography Images for Detection of ARMD

Abstract

Age-related macular degeneration (ARMD) is one of the most common retinal syndromes that occurs in elderly people. Different eye testing techniques such as fundus photography and optical coherence tomography (OCT) are used to clinically examine the ARMD-affected patients. Many researchers have worked on detecting ARMD from fundus images, few of them also worked on detecting ARMD from OCT images. However, there are only few systems that establish the correspondence between fundus and OCT images to give an accurate prediction of ARMD pathology. In this paper, we present fully automated decision support system that can automatically detect ARMD by establishing correspondence between OCT and fundus imagery. The proposed system also distinguishes between early, suspect and confirmed ARMD by correlating OCT B-scans with respective region of the fundus image. In first phase, proposed system uses different B-scan based features along with support vector machine (SVM) to detect the presence of drusens and classify it as ARMD or normal case. In case input OCT scan is classified as ARMD, region of interest from corresponding fundus image is considered for further evaluation. The analysis of fundus image is performed using contrast enhancement and adaptive thresholding to detect possible drusens from fundus image and proposed system finally classified it as early stage ARMD or advance stage ARMD. The proposed system is tested on local data set of 100 patients with100 fundus images and 6800 OCT B-scans. Proposed system detects ARMD with the accuracy, sensitivity, and specificity ratings of 98.0, 100, and 97.14%, respectively.

Validation of a Novel Automated Algorithm to Measure Drusen Volume and Area Using Swept Source Optical Coherence Tomography Angiography

“…Quantitative measurements characterizing the health of the RPE and, in particular, the drusen burden can clearly play an important role in better understanding different pathologies and the effects of treatment. A number of different approaches have been proposed to produce automated drusen burden measurements from OCT datasets, 12,[18][19][20][30][31][32] including a few recent algorithms involving aspects of convolutional neural networks. [30][31][32] Although it is difficult to compare precisely the performance of the different algorithms in the literature, at this time, the RPE elevation algorithm commercially available on the Cirrus SD-OCT instrument is clearly the best understood and most widely used one.…”

“…A number of different approaches have been proposed to produce automated drusen burden measurements from OCT datasets, 12,[18][19][20][30][31][32] including a few recent algorithms involving aspects of convolutional neural networks. [30][31][32] Although it is difficult to compare precisely the performance of the different algorithms in the literature, at this time, the RPE elevation algorithm commercially available on the Cirrus SD-OCT instrument is clearly the best understood and most widely used one. In this study, we evaluated the performance of a novel automated RPE elevation algorithm developed for the Plex Elite SS-OCTA instrument by comparing drusen volume and area measurements to those obtained using the algorithm on the Cirrus SD-OCT instrument, which is the only RPE elevation algorithm cleared by the FDA.…”

Screening und Management retinaler Erkrankungen mittels digitaler Medizin

“…Abb. 2; [22]), Drusen [13,28], die Fovea [14] oder Abhebungen des retinalen Pigmentepithels [25]. Fürdasdiabetische Makulaödem wurde ein analoges Prognosemodell auf Basis von 629 Patienten in der Protocol T-Studie erstellt, das ebenfalls eine hohe Korrelation vom Ausmaß an intraretinaler Flüssigkeit mit der Visusprognose (also dem Visus am Ende der Nachbeobachtungsphase) aufzeigte [11].…”

U-Net with Spatial Pyramid Pooling for Drusen Segmentation in Optical Coherence Tomography

“…Related work In recent years, deep learning based and non deep learning based methods were applied on this task [3,4,5,6,7]. Generally it has been shown that deep learning based methods, namely convolutional neural networks (CNN), outperform the previous cost-function based models [3,6,7].…”