Robust Retinal Vessel Segmentation via Locally Adaptive Derivative Frames in Orientation Scores

Abstract

This paper presents a robust and fully automatic filter-based approach for retinal vessel segmentation. We propose new filters based on 3D rotating frames in so-called orientation scores, which are functions on the Lie-group domain of positions and orientations [Formula: see text]. By means of a wavelet-type transform, a 2D image is lifted to a 3D orientation score, where elongated structures are disentangled into their corresponding orientation planes. In the lifted domain [Formula: see text], vessels are enhanced by means of multi-scale second-order Gaussian derivatives perpendicular to the line structures. More precisely, we use a left-invariant rotating derivative (LID) frame, and a locally adaptive derivative (LAD) frame. The LAD is adaptive to the local line structures and is found by eigensystem analysis of the left-invariant Hessian matrix (computed with the LID). After multi-scale filtering via the LID or LAD in the orientation score domain, the results are projected back to the 2D image plane giving us the enhanced vessels. Then a binary segmentation is obtained through thresholding. The proposed methods are validated on six retinal image datasets with different image types, on which competitive segmentation performances are achieved. In particular, the proposed algorithm of applying the LAD filter on orientation scores (LAD-OS) outperforms most of the state-of-the-art methods. The LAD-OS is capable of dealing with typically difficult cases like crossings, central arterial reflex, closely parallel and tiny vessels. The high computational speed of the proposed methods allows processing of large datasets in a screening setting.

Retinal Vessels Segmentation Techniques and Algorithms: A Survey

“…Conversely, other retinal anatomical structures have high contrast to other background tissues but with indistinct features in comparison with abnormal structures; optic disc and exudates lesions represent typical examples. All these challenges, in terms of medical image processing, make the classical segmentation techniques such as Sobel operators [26], Prewitt operators [27], gradient operators [28], and Robert and Krish differential operations [29] inefficient This challenge opens the room for a field of research specialized in detecting and segmenting thin (filamentary) retinal vascular structures, as in [18][19][20][21][22][23][24][25]. Secondly, Vessels identification in pathological retinal images faces a tension between accurate vascular structure extraction and false responses near pathologies (such as hard and soft exudates, hemorrhages, microaneuryms and cotton wool spots) and other nonvascular structures (such as optic disc and fovea region).…”

“…(a) (b) This challenge opens the room for a field of research specialized in detecting and segmenting thin (filamentary) retinal vascular structures, as in [18][19][20][21][22][23][24][25]. Secondly, Vessels identification in pathological retinal images faces a tension between accurate vascular structure extraction and false responses near pathologies (such as hard and soft exudates, hemorrhages, microaneuryms and cotton wool spots) and other nonvascular structures (such as optic disc and fovea region).…”

Retinal vascular segmentation using superpixel‐based line operator and its application to vascular topology estimation

“…To reveal the relative performance of our proposed method, we compared it with several existing state‐of‐the‐art vessel detection methods on the most popular datasets: DRIVE and STARE. The results are shown in Table , and the chosen methods have been ordered by the category the methods belonging to the most recent seven supervised methods and nine unsupervised segmentation methods . Note, a different AUC calculation was used in: AUC = ( se + sp )/2.…”

“…Note, to the best knowledge of the authors, only Zhang et al have tested their segmentation method on IOSTAR dataset. In consequence, we only compared with the performance obtained by in the bottom of Table and by no means exhaustive. In contrast, our method has better performance in terms of all metrics.…”

Tracking and diameter estimation of retinal vessels using Gaussian process and Radon transform

“…31 After applying a preprocessing step, they use several deep learning architectures to segment vessels. Second-order locally adaptive derivatives have been used in several papers for extracting vessel structures; Zhang et al 32 proposed a simpler version of this method by avoiding a computation of full Laplacian in vessel enhancements (geometric diffusions), which is much easier to understand and reproduce.…”