Optic Disc Segmentation Method Research Articles

Optic disc detection based on fully convolutional network and weighted matrix recovery model.

Eye diseases often affect human health. Accurate detection of the optic disc contour is one of the important steps in diagnosing and treating eye diseases. However, the structure of fundus images is complex, and the optic disc region is often disturbed by blood vessels. Considering that the optic disc is usually a saliency region in fundus images, we propose a weakly-supervised optic disc detection method based on the fully convolution neural network (FCN) combined with the weighted low-rank matrix recovery model (WLRR). Firstly, we extract the low-level features of the fundus image and cluster the pixels using the Simple Linear Iterative Clustering (SLIC) algorithm to generate the feature matrix. Secondly, the top-down semantic prior information provided by FCN and bottom-up background prior information of the optic disc region are used to jointly construct the prior information weighting matrix, which more accurately guides the decomposition of the feature matrix into a sparse matrix representing the optic disc and a low-rank matrix representing the background. Experimental results on the DRISHTI-GS dataset and IDRiD dataset show that our method can segment the optic disc region accurately, and its performance is better than existing weakly-supervised optic disc segmentation methods. Graphical abstract of optic disc segmentation.

DCAE-UNET: IMPROVED OPTIC DISC SEGMENTATION MODEL USING SEMI-SUPERVISED DEEP DILATED CONVOLUTION AUTOENCODER-BASED MODIFIED U-NET

An accurate assessment of the morphological characteristics of the Optic Disc (OD) is essential for the diagnosis of various retinal disorders. It is necessary to segment the OD precisely to detect structural OD changes associated with visual field loss. Although deep learning models are effective for this task, they require extensive labeled datasets, which can be time-consuming and costly. Furthermore, fundus images have multi-scale features, making segmentation challenging. In this study, we present a semi-supervised and transfer learning approach for OD segmentation. Our approach utilizes an improved Dilated Convolutional AutoEncoder (DCAE) and a pre-trained modified U-Net to segment the OD. The DCAE segments the OD using feature similarity from unlabeled images in the Messidor dataset and saves the learned weights. Transfer learning is then applied to reuse the model weights in the U-Net, accelerating training on small datasets such as Drions-DB and Drishti-GS. The network architecture was modified by increasing the layers from 8 to 128 and halving the feature map length and width. To address the multi-scale challenge without inflating the model parameters, we introduce the Dilated Hierarchical Feature Extraction Module (DHFEM), a convolutional module capable of achieving multi-scale feature extraction without increasing model parameters. Additionally, DHFEM incorporates convolutional layers with varying receptive fields, further enhancing the network ability to extract features across multiple scales. Our OD segmentation method outperforms existing algorithms with reduced parameter quantities of 0.4 M. The mean Intersection over Union (mIoU) values are 0.9383 and 0.9629 and inference times of 45 ms and 40 ms for the Drions-DB and Drishti-GS datasets, respectively.

Weak label based Bayesian U-Net for optic disc segmentation in fundus images

Fundus images have been widely used in routine examinations of ophthalmic diseases. For some diseases, the pathological changes mainly occur around the optic disc area; therefore, detection and segmentation of the optic disc are critical pre-processing steps in fundus image analysis. Current machine learning based optic disc segmentation methods typically require manual segmentation of the optic disc for the supervised training. However, it is time consuming to annotate pixel-level optic disc masks and inevitably induces inter-subject variance. To address these limitations, we propose a weak label based Bayesian U-Net exploiting Hough transform based annotations to segment optic discs in fundus images. To achieve this, we build a probabilistic graphical model and explore a Bayesian approach with the state-of-the-art U-Net framework. To optimize the model, the expectation-maximization algorithm is used to estimate the optic disc mask and update the weights of the Bayesian U-Net, alternately. Our evaluation demonstrates strong performance of the proposed method compared to both fully- and weakly-supervised baselines.

Optic disc segmentation by U-net and probability bubble in abnormal fundus images

Segmenting optic disc (OD) in abnormal fundus images is a challenge task because of many distractions such as illumination variations, blurry boundary, occlusion of retinal vessels and big bright lesions. Data-driven deep learning is effective and robust to illumination variations, blurry boundary and occlusion in the normal fundus images but sensitive to big bright lesions in abnormal images. In this paper, an automatic OD segmentation method fusing U-net with model-driven probability bubble approach is proposed in abnormal fundus images. The probability bubble is conceived according to the position relationship between retinal vessels and OD, and the localization result is fused into the output layer of U-net through calculating the joint probability. The proposed method takes the advantage of the deep learning architecture and improves the architecture’s performance by including the model-driven position constraint when lack of sufficient training data. Experiments show that the proposed method successfully removes the distraction of bright lesions in abnormal fundus images and obtains a satisfying OD segmentation on three public databases: Kaggle, MESSIDOR and NIVE, and it outperforms existing methods with a very high accuracy.

A color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images

Retinal disorders are a severe health threat for older adults because they may lead to vision loss and blindness. Diabetic patients are particularly prone to suffer from Diabetic Retinopathy. Identifying relevant structural components in color fundus images like the optic disc (OD) is crucial to diagnose retinal diseases. Automatic OD detection is complex because of its location in an area where blood vessels converge, and color distribution is uneven. Several image processing techniques have been developed for OD detection so far, but vessel segmentation is sometimes required, increasing computational complexity and time. Moreover, precise OD segmentation methods utilize complex algorithms that need special hardware or extensive labeled datasets. We propose an OD detection approach based on the Modern Portfolio Theory of Markowitz to generate an innovative color fusion model. Specifically, the training phase calculates the optimal weights for each color channel. A fusion of weighted color channels is then applied in the testing phase. This approach acts as a powerful and real-time preprocessing stage. We use four heterogeneous datasets to validate the presented methodology. Three out of four datasets are publicly available (i.e., DRIVE, Messidor, and HRF), and the last corresponds to an in–house dataset acquired from Hospital Universitari Sant Joan de Reus (Spain). Two different segmentation methods are presented and compared with state-of-the-art computer vision techniques to analyze the model performance. An outstanding accuracy and overlap above 0.9 and 80%, respectively, and a minimal execution time of 0.05 s are reached. Therefore, our model could be integrated into daily clinical practice to accelerate the diagnosis of Diabetic Retinopathy due to its simplicity, performance, and speed.

Optic Disc Segmentation Using Attention-Based U-Net and the Improved Cross-Entropy Convolutional Neural Network.

Medical image segmentation is an important part of medical image analysis. With the rapid development of convolutional neural networks in image processing, deep learning methods have achieved great success in the field of medical image processing. Deep learning is also used in the field of auxiliary diagnosis of glaucoma, and the effective segmentation of the optic disc area plays an important assistant role in the diagnosis of doctors in the clinical diagnosis of glaucoma. Previously, many U-Net-based optic disc segmentation methods have been proposed. However, the channel dependence of different levels of features is ignored. The performance of fundus image segmentation in small areas is not satisfactory. In this paper, we propose a new aggregation channel attention network to make full use of the influence of context information on semantic segmentation. Different from the existing attention mechanism, we exploit channel dependencies and integrate information of different scales into the attention mechanism. At the same time, we improved the basic classification framework based on cross entropy, combined the dice coefficient and cross entropy, and balanced the contribution of dice coefficients and cross entropy loss to the segmentation task, which enhanced the performance of the network in small area segmentation. The network retains more image features, restores the significant features more accurately, and further improves the segmentation performance of medical images. We apply it to the fundus optic disc segmentation task. We demonstrate the segmentation performance of the model on the Messidor dataset and the RIM-ONE dataset, and evaluate the proposed architecture. Experimental results show that our network architecture improves the prediction performance of the base architectures under different datasets while maintaining the computational efficiency. The results render that the proposed technologies improve the segmentation with 0.0469 overlapping error on Messidor.

A new optic disc segmentation method using a modified Dolph-Chebyshev matched filter

In this paper, a novel algorithm for automatic optic disc segmentation on fundus images is presented. In the proposed algorithm, a modified Dolph-Chebyshev type I function matched filter is utilized to detect optic disc boundary candidates. Subsequently, the Circular Hough Transform and B-spline approximation are employed to obtain the final optic disc boundary. The matched filter, Circular Hough Transform and B-spline approximation work on a localized region of interest that is obtained based on three independent methods: template-based, vessels density map-based, and maximum entropy-based methods. The performance of the proposed algorithm is evaluated using fundus images from the MESSIDOR and DRIVE datasets. From the experiments, it can be observed that the proposed algorithm successfully locates optic discs with an average success rate of above 99%. Also, the proposed algorithm can achieve best scores in terms of Area Overlap, Dices coefficient, Accuracy, and False Positive Fraction, which makes the algorithm suitable for practical applications such as an automatic detection tool for retinal diseases.

Automated Method for Optic Disc Detection and Elimination in Digital Fundus Images

Localizing, segmenting and eliminating the optic disc region of a fundus image is a prerequisite task in the automatic investigation of a number of retinal diseases such as Diabetic retinopathy, Glaucoma, Macular Edema, etc. Accurate detection of optic disc is a challenging task due to a number of reasons. Optic disc in most fundus images does not exhibit clear disc boundaries and there are number of blood vessels crossing it. An important task in automated retinal image analysis system is the detection and elimination of optic disc because the lesion regions in diabetic retinopathy closely resemble the color and texture of an optic disc. Hence, eliminating the optic disc region can improve the performance of diabetic retinopathy detection. The proposed work presents a novel method for optic disc segmentation which is not restricted by the location of the optic disc on the retina. The proposed algorithm localizes the position of the optic disc that is independent of its location and dynamically finds its center. The proposed method is tested on images from DRISHTI-GS, DIARETDB1, DRIONS-DB and DRIVE databases based on morphological operation and finding the largest connected component. The precision values of segmentation for digital fundus images from DRISHTI-GS, DIARETDB1, DRIONS-DB, and DRIVE databases are 0.98, 0.99, 0.98 and 0.99 respectively using the proposed method. The algorithm has yielded consistent high values of precision and recall indicating its robustness and efficiency.

An automated early diabetic retinopathy detection through improved blood vessel and optic disc segmentation

This paper presents an automated early diabetic retinopathy detection scheme from color fundus images through improved segmentation strategies for optic disc and blood vessels. The red lesions, microaneurysms and hemorrhages are the earliest signs of diabetic retinopathy. This paper essentially proposes improved techniques for microaneurysm as well as hemorrhages detection, which eventually contribute in the overall improvement in the early detection of diabetic retinopathy. The proposed method consists of five stages- pre-processing, detection of blood vessels, segmentation of optic disc, localization of fovea, feature extraction and classification. Mathematical morphology operation is used for pre-processing and blood vessel detection. Watershed transform is used for optic disc segmentation. The main contribution of this model is to propose an improved blood vessel and optic disc segmentation methods. Radial basis function neural network is used for classification of the diseases. The parameters of radial basis function neural network are trained by the features of microaneurysm and hemorrhages. The accuracy of the proposed algorithm is evaluated based on sensitivity and specificity, which are 87% and 93% respectively.

An Optic Disc Segmentation Method Based on Active Contour Tracking

An Optic Disc Segmentation Method Based on Active Contour Tracking

Saliency‐Based Segmentation of Optic Disc in Retinal Images

Accurate segmentation of Optic disc (OD) is significant for the automation of retinal analysis and retinal diseases screening. This paper proposes a novel optic disc segmentation method based on the saliency. It includes two stages: optic disc location and saliency-based segmentation. In the location stage, the OD is detected using a matched template and the density of the vessels. In the segmentation stage, we treat the OD as the salient object and formulate it as a saliency detection problem. To measure the saliency of a region, the boundary prior and the connectivity prior are exploited. Geodesic distance to the window boundary is computed to measure the cost the region spends to reach the window boundary. After a threshold and ellipse fitting, we obtain the OD. Experimental results on two public databases for OD segmentation show that the proposed method achieves thestate-of-the-art performance.

PCA-based localization approach for segmentation of optic disc.

The optic disc is the origin of the optic nerve, where the axons of retinal ganglion cells join together. The size, shape and contour of optic disc are used for classification and identification of retinal diseases. Automatic detection of eye disease requires development of an efficient algorithm. This paper proposes an efficient method for optic disc segmentation and detection for the diagnosis of retinal diseases. The methodology involves optic disc localization, blood vessel inpainting and optic disc segmentation. Localization is based on principal component analysis, and segmentation is based on Markov random field segmentation. In order to get reasonable background images, blood vessel inpainting is done before segmentation. The proposed method tested with two standard databases MESSIDOR and DRIVE, and achieved an average overlapping score of 92.41, 92.17%, respectively; also validation experiments were done with one local database from Venu Eye Hospital, New Delhi, and obtained an average overlapping score of 91%. An efficient algorithm is developed for detecting optic disc using principal component analysis-based localization and Markov random field segmentation. The comparison with alternative method yielded results that demonstrate the superiority of the proposed algorithm for optic disc detection.

Optic disc segmentation based on variational model with multiple energies

Accurate and reliable optic disc (OD) segmentation is important for retinal image analysis and retinal disease screening. This paper presents a novel method to automatically segment OD in fundus images based on variational model with multiple energies. Firstly, a sparse coding based technique is designed to localize the OD center, based on which an initial boundary curve is then estimated by a circular Hough transform. Next, OD segmentation is regarded as an energy minimization problem, and a variational model integrating three energy terms is proposed to evolve the curve to the OD boundary. In the proposed model, the first term, named phase-based boundary energy, is designed to attract the evolution curve to the OD boundary, even the one with low contrast; the second term, named PCA-based shape energy, constraints the evolution curve to a common OD shape, which can suppress the negative effect of bright interferences, e.g., the bright lesions and myelinated nerve fibers, in OD segmentation; the last one is the region energy, which drives the evolution curve to the boundary of the homogeneous regions and hence improve the robustness of the model to the noises boundary and the initial position of evolution curve. The proposed OD segmentation method is evaluated on three public available databases, i.e., the MESSIDOR, ONHSD and DRIONS databases, and the experimental results demonstrate that the proposed method outperforms the state-of-the art techniques.

An Accurate Optic Disc Segmentation from Peripapillary Atrophy Incident Retinal Images

Glaucoma detection system analyses the retinal images. This system gives vital information about presence of Glaucoma, the second largest cause of blindness. Usually the Glaucoma patients have large Cup-to-Disc ratio (CDR), inspection of CDR of Optic Disc is crucial of any Glaucoma detection system. Therefore accurate segmentation Optic Disc (OD) and Cup are critical in the formulation of CDR. Current work focuses on OD segmentation to develop an efficient Glaucoma detection system. A serious difficulty arises in OD segmentation in retinal images having inhomogenities due to Peripapillary Atrophy (PPA) and fuzzy boundaries. So this paper proposes a OD Segmentation method that takes care of fuzzy boundaries and inhomogenity presenting in the retinal images. At First, The matched filter with Cauchy kernel is applied to extract blood vessels. Then Vessel Directional Matched filter(VDM) is used to locate the centre of the optic disc approximately followed by Vessel Inpainting to erase the vasculature in the OD region. Finally a LBF energy based active contour model is formulated that embeds edge and region based information in the newly formulated locally computed signed pressure force(SPF) function , to segment OD. The obtained results indicate that the proposed OD segmentation outperforms many existing methods.

Retina image–based optic disc segmentation

The change of optic disc can be used to diagnose many eye diseases, such as glaucoma, diabetic retinopathy and macular degeneration. Moreover, retinal blood vessel pattern is unique for human beings even for identical twins. It is a highly stable pattern in biometric identification. Since optic disc is the beginning of the optic nerve and main blood vessels in retina, it can be used as a reference point of identification. Therefore, optic disc segmentation is an important technique for developing a human identity recognition system and eye disease diagnostic system. This article hence presents an optic disc segmentation method to extract the optic disc from a retina image. The experimental results show that the optic disc segmentation method can give impressive results in segmenting the optic disc from a retina image.

A self-adaptive distance regularized level set evolution method for optical disk segmentation.

The optic disc (OD) is one of the important anatomic structures on the retina, the changes of which shape and area may indicate disease processes, thus needs computerized quantification assistance. In this study, we proposed a self-adaptive distance regularized level set evolution method for OD segmentation without the periodically re-initializing steps in the level set function execution to a signed distance function during the evolution. In that framework, preprocessing of an image was performed using Fourier correlation coefficient filtering to obtain initial boundary as the beginning contour, then, an accurate boundary of the optic disc was obtained using the self-adaptive distance regularized level set evolution method. One hundred eye fundus color numerical images from public database were selected to validate our algorithm. Therefore, we believe that such automatic OD segmentation method could assist the ophthalmologist to segment OD more efficiently, which is of significance for future computer-aided early detection of glaucoma and retinopathy diseases.