Drusen Segmentation From Retinal Images via Supervised Feature Learning

Abstract

This paper presents a supervised feature learning method to learn discriminative and compact descriptors for drusen segmentation from retinal images. This method combines generalized low rank approximation of matrices with supervised manifold regularization to learn new features from image patches sampled from retinal images. The learned features are closely related to drusen and potentially free from information that is redundant in distinguishing drusen from background. The learned feature representations are then vectorized and used to train a support vector machine (SVM) classifier. Finally, the obtained SVM classifier is employed to classify the pixels in the test images as drusen or non-drusen. The performance of the proposed method is validated on the STARE and DRIVE databases, where it achieves an average sensitivity/specificity/accuracy of 90.03%/97.06%/96.92% and of 87.41%/94.93%/94.81%, respectively. We also experimentally compare the proposed method with the several representative state-of-the-art drusen segmentation techniques and find that it generates superior accuracy.

Keywords

• Age-related macular degeneration
• drusen segmentation
• feature learning
• retinal images