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

BackgroundGlaucoma is the leading cause of irreversible vision loss. Accurate Optic Disc (OD) and Optic Cup (OC) segmentation is beneficial for glaucoma diagnosis. In recent years, deep learning has achieved remarkable performance in OD and OC segmentation. However, OC segmentation is more challenging than OD segmentation due to its large shape variability and cryptic boundaries that leads to performance degradation when applying the deep learning models to segment OC. Moreover, the OD and OC are segmented independently, or pre-requirement is necessary to extract the OD centered region with pre-processing procedures.MethodsIn this paper, we suggest a one-stage network named EfficientNet and Attention-based Residual Depth-wise Separable Convolution (EARDS) for joint OD and OC segmentation. In EARDS, EfficientNet-b0 is regarded as an encoder to capture more effective boundary representations. To suppress irrelevant regions and highlight features of fine OD and OC regions, Attention Gate (AG) is incorporated into the skip connection. Also, Residual Depth-wise Separable Convolution (RDSC) block is developed to improve the segmentation performance and computational efficiency. Further, a novel decoder network is proposed by combining AG, RDSC block and Batch Normalization (BN) layer, which is utilized to eliminate the vanishing gradient problem and accelerate the convergence speed. Finally, the focal loss and dice loss as a weighted combination is designed to guide the network for accurate OD and OC segmentation.Results and discussionExtensive experimental results on the Drishti-GS and REFUGE datasets indicate that the proposed EARDS outperforms the state-of-the-art approaches. The code is available at https://github.com/M4cheal/EARDS.

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.

With the rapid development of high tech, Internet of Things (IoT) and artificial intelligence (AI) achieve a series of achievements in the healthcare industry. Among them, automatic glaucoma diagnosis is one of them. Glaucoma is second leading cause of blindness in the world. Although many automatic glaucoma diagnosis approaches have been proposed, they still face the following two challenges. First, the data acquisition of diseased images is extremely expensive, especially for disease with low occurrence, leading to the class imbalance. Second, large-scale labeled data are hard to obtain in medical image domain. The aforementioned challenges limit the practical application of these approaches in glaucoma diagnosis. To address these disadvantages, this paper proposes an unsupervised anomaly detection framework based on sparse principal component analysis (SPCA) for glaucoma diagnosis. In the proposed approach, we just employ the one-class normal (nonglaucoma) images for training, so the class imbalance problem can be avoided. Then, to distinguish the glaucoma (abnormal) images from the normal images, a feature set consisting of segmentation-based features and image-based features is extracted, which can capture the shape and textural changes. Next, SPCA is adopted to select the effective features from the feature set. Finally, with the usage of the extracted effective features, glaucoma diagnosis can be automatically accomplished via introducing the T 2 statistic and the control limit, overcoming the issue of insufficient labeled samples. Extensive experiments are carried out on the two public databases, and the experimental results verify the effectiveness of the proposed approach.

No abstract