Automatic optic disc detection using low-rank representation based semi-supervised extreme learning machine

Optic disc detection plays an important role in developing automatic screening systems for diabetic retinopathy. Several supervised learning-based approaches have been proposed for optic disc detection. However, these approaches demand that the input training examples are completely labelled. Essentially, in medical image analysis, it is difficult to prepare several training samples which were given reliable class labels due to the fact that manually labelling data is very expensive. Moreover, retinal images such as complex vessels structures in the optic disc constituting nonlinear relationships in high-dimensional observation space, which cannot work well by traditional linear classifiers. In this study, a novel approach named low-rank representation based semi-supervised extreme learning machine (LRR-SSELM) is proposed for automated optic disc detection. Our model has the following advantages. First, it detects the optic disc from the viewpoint of semi-supervised learning and overcomes the problem there are small portion of labelled samples. Second, a nonlinear classifier is introduced into our model to fully explore the nonlinear data. Third, the local and global structures of original data can be greatly persevered by low-rank representation (LRR). The performance of the proposed method is validated on three publicly available databases, DIARETDB0, DIARETDB1 and Messidor. The experimental results indicate the advantages and effectiveness of the proposed approach.