Recently, end-to-end deep neural networks-based glaucoma diagnosis approaches have been gaining much attention. However, the feature extractor and classier in these approaches are trained together, which is known as coadaptation. Therefore, the feature distribution in them should adapt to particular decision boundaries. To learn generic data representations and improve the generalization ability of the model, this paper designs a three-stage framework for glaucoma diagnosis. In the first stage, preprocessing is utilized to extract the Region of Interesting around the Optic Disc to reduce the computational cost and nonobjective interference. In the second stage, Deep Sparse Autoencoder is designed to learn hybrid features between the deep features and the original features, which could improve the effectiveness of final high-level feature expression. Meanwhile, L1 regularization is introduced and applied on the hybrid features to obtain deep features with high complementarity under small sample problem. In the third stage, the obtained generic feature representations are fed into different classifiers, in which Support Vector Machine classifier achieves the best diagnosis performance. The proposed approach is evaluated on two publicly available databases. Extensive experimental results indicate that our approach outperforms the state-of-the-art approaches with the accuracy of 96.00%, 97.00% and Area Under Curve of 96.94%, 98.28% for REFUGE and Drishti-GS1 databases, respectively.

As one of the most effective feature learning methods, Nonnegative Matrix Factorization (NMF) has been widely used in many scientific fields, such as computer vision, data mining, and bioinformatics. However, NMF is an unsupervised method that cannot fully utilize the label information of data. Thus, its performance is limited in some recognition and classification problems. To remedy this shortcoming, this paper proposes a Semisupervised Discriminative NMF (SDNMF) method. First, we design a Soft-Labeled NMF (SLNMF) model by introducing a soft-label matrix-based regression term into the original NMF, so that the relationship between the soft-label matrix and low-dimensional features can be constructed to improve the discriminative ability of low-dimensional features. Second, to effectively estimate the soft-label matrix, a Label Propagation (LP) model is adopted to fully explore the spatial distribution relationship between the labeled and unlabeled samples. Third, an Adaptive Graph Learning (AGL) model is proposed to exploit the geometric relationship of samples well, which could enhance the performance of LP. Finally, the above three models (i.e., SLNMF, LP, and AGL) are integrated into a unified framework for effective feature learning, which can not only effectively explore the structural relationship matrix between data, but also predict the labels for unknown samples. Moreover, an iterative optimization algorithm is presented to solve our objective function. The convergence and computational complexity analysis of the proposed SDNMF method are also provided. Extensive experiments are conducted on several standard data sets. Compared with related methods, the experimental results verify that the proposed SDNMF method achieves better performance.

Glaucoma is an eye disease that leads to irreversible vision loss. Accurate Optic Disc (OD) and Optic Cup (OC) segmentation can effectively facilitate ophthalmologist in glaucoma diagnosis. Recently, a series of deep learning approaches attain promising performance in OD and OC segmentation but still face the challenge to precisely segment OC boundary with enhanced computational efficiency. To address this issue, we propose a novel network named Robust Multiscale Feature Extraction with Depthwise Separable Convolution (RMSDSC-Net), which can better solve the challenging tradeoff between segmentation performance and network cost. The proposed RMSDSC-Net is mainly composed of Multiscale Input (MSI), Depthwise Separable Convolution Unit (DSCU), Dilated Convolution Block (DCB), and External Residual Connection (ERC). First, the introduction of MSI can reduce the information loss due to the pooling layers used in the network for capturing rich feature representations. Next, to enhance segmentation performance and computational efficiency, this paper designs DSCU and DCB modules to avoid spatial information loss from minor details of the image and preserve more high-level semantic features. Finally, this paper develops ERC established between the encoding layers and decoding layers to minimize the feature degradation problem. Hence, a high segmentation performance can be achieved using a shallow network. To evaluate the performance of the proposed network, extensive experiments have been enforced on two publicly available databases, DRISHTI-GS and REFUGE. Our approach outperforms the state-of-the-art approaches with the Dice Coefficient of (0.978, 0.919) and (0.965, 0.910) for OD and OC segmentation on DRISHTI-GS and REFUGE databases, respectively. As a result, the proposed approach has a strong potential in analyzing fundus images for glaucoma diagnosis.