Automated identification of retinal vessels using a multiscale directional contrast quantification (MDCQ) strategy

Automated segmentation of the optic disc from fundus images using an asymmetric deep learning network

Accurate segmentation of the optic disc (OD) regions from color fundus images is a critical procedure for computer-aided diagnosis of glaucoma. We present a novel deep learning network to automatically identify the OD regions. On the basis of the classical U-Net framework, we define a unique sub-network and a decoding convolutional block. The sub-network is used to preserve important textures and facilitate their detections, while the decoding block is used to improve the contrast of the regions-of-interest with their background. We integrate these two components into the classical U-Net framework to improve the accuracy and reliability of segmenting the OD regions depicted on color fundus images. We train and evaluate the developed network using three publicly available datasets (i.e., MESSIDOR, ORIGA, and REFUGE). The results on an independent testing set (n=1,970 images) show a segmentation performance with an average Dice similarity coefficient (DSC), intersection over union (IOU), and Matthew's correlation coefficient (MCC) of 0.9377, 0.8854, and 0.9383 when trained on the global field-of-view images, respectively, and 0.9735, 0.9494, and 0.9594 when trained on the local disc region images. When compared with the other three classical networks (i.e., the U-Net, M-Net, and Deeplabv3) on the same testing datasets, the developed network demonstrates a relatively higher performance.

A review of machine learning methods for retinal blood vessel segmentation and artery/vein classification

The eye affords a unique opportunity to inspect a rich part of the human microvasculature non-invasively via retinal imaging. Retinal blood vessel segmentation and classification are prime steps for the diagnosis and risk assessment of microvascular and systemic diseases. A high volume of techniques based on deep learning have been published in recent years. In this context, we review 158 papers published between 2012 and 2020, focussing on methods based on machine and deep learning (DL) for automatic vessel segmentation and classification for fundus camera images. We divide the methods into various classes by task (segmentation or artery-vein classification), technique (supervised or unsupervised, deep and non-deep learning, hand-crafted methods) and more specific algorithms (e.g. multiscale, morphology). We discuss advantages and limitations, and include tables summarising results at-a-glance. Finally, we attempt to assess the quantitative merit of DL methods in terms of accuracy improvement compared to other methods. The results allow us to offer our views on the outlook for vessel segmentation and classification for fundus camera images.

A coarse-to-fine deep learning framework for optic disc segmentation in fundus images

Accurate segmentation of the optic disc (OD) depicted on color fundus images may aid in the early detection and quantitative diagnosis of retinal diseases, such as glaucoma and optic atrophy. In this study, we proposed a coarse-to-fine deep learning framework on the basis of a classical convolutional neural network (CNN), known as the U-net model, to accurately identify the optic disc. This network was trained separately on color fundus images and their grayscale vessel density maps, leading to two different segmentation results from the entire image. We combined the results using an overlap strategy to identify a local image patch (disc candidate region), which was then fed into the U-net model for further segmentation. Our experiments demonstrated that the developed framework achieved an average intersection over union (IoU) and a dice similarity coefficient (DSC) of 89.1% and 93.9%, respectively, based on 2,978 test images from our collected dataset and six public datasets, as compared to 87.4% and 92.5% obtained by only using the sole U-net model. The comparison with available approaches demonstrated a reliable and relatively high performance of the proposed deep learning framework in automated OD segmentation.

Retinal Vascular Imaging in Vascular Cognitive Impairment: Current and Future Perspectives

Vascular cognitive disorders are heterogeneous and increasingly recognized entities with intricate correlation to neurodegenerative conditions. Retinal vascular analysis is a noninvasive approach to study cerebrovascular pathology, with promise to assist particularly during early disease phases. In this article, we have systematically summarized the current understanding, potential applications, and inevitable limitations of retinal vascular imaging in patients with vascular cognitive impairment. In addition, future directions in the field with support from automated technology using deep learning methods and their existing challenges are emphasized.

Significant Enhancement of Segmentation Efficiency of Retinal Images Using Texture-Based Gabor Filter Approach Followed by Optimization Algorithm

Considering Retinal image as textured image, its texture based segmentation is required to identify the presence of retinal diseases. This pre-processing is important in automatic detection system for recognizing the abnormality present in the retinal images. Likewise, the proposed system mainly focused on diabetic retinopathy disease caused into eye –retina, generally leads to eye-blindness. Inspired from robust human's texture based segmentation capability, a mathematical model of the eye was formulated. A texture based Gabor filter was applied to get the output feature helping in detecting the abnormality and deriving statistical properties, further used in segmentation and classification. This work deals with the better separation of various clusters of Gabor filter output features, in order to get better segmentation efficiency. This was also followed by formalizing an objective function to tune filter parameters with Gradient descent and further Genetic Algorithm. This paper showed both qualitative and quantitative segmentation results with improved efficiency.