Blood vessel segmentation methodologies in retinal images - A survey

By Muhammad Moazam Fraz, Paolo Remagnino, Andreas Hoppe, Bunyarit Uyyanonvara, Alicja R. Rudnicka, Christopher G. Owen, Sarah Ann Barman. Comput. Methods Programs Biomed., 2012

1,023 citations recorded by the source corpus.

Retinal vessel segmentation algorithms are a fundamental component of automatic retinal disease screening systems. This work examines the blood vessel segmentation methodologies in two dimensional retinal images acquired from a fundus camera and a survey of techniques is presented. The aim of this paper is to review, analyze and categorize the retinal vessel extraction algorithms, techniques and methodologies, giving a brief description, highlighting the key points and the performance measures. We intend to give the reader a framework for the existing research; to introduce the range of retinal vessel segmentation algorithms; to discuss the current trends and future directions and summarize the open problems. The performance of algorithms is compared and analyzed on two publicly available databases (DRIVE and STARE) of retinal images using a number of measures which include accuracy, true positive rate, false positive rate, sensitivity, specificity and area under receiver operating characteristic (ROC) curve.

Subfields: Computer Vision and Pattern Recognition, Ophthalmology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/8a56de217a22761b8ccec0fbf2bc29aca48b1e0f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Ophthalmology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Understanding Deep Learning Techniques for Image Segmentation (2019, background): “Some of the most common types of tasks are segmentation of organic elements such as vessels [47], tissues [73], and nerves [107].”
A Discriminatively Trained Fully Connected Conditional Random Field Model for Blood Vessel Segmentation in Fundus Images (2017, background): “Although numerous attempts have been made in the ﬁeld of automated retinal vessel segmentation, this task is still an active area of research due to the potential impact of having more accurate results [2].”
Hierarchical retinal blood vessel segmentation based on feature and ensemble learning (2015, methodology): “Moreover, the generation of retinal maps and detection of branch points have been utilized for temporal or multimodal image registration, retinal image mosaic synthesis, optic disc identification, fovea localization and biometric identification [2].”
Deep Retinal Image Understanding (2016, methodology): “Classic methods for addressing the task of blood vessel segmentation involve hand crafted ﬁlters like line detectors [17,14] and vessel enhancement techniques [20,26,5].”
Computer Methods and Programs in Biomedicine (neutral): “…is supported by the constant introduction in clinical practice of new medical technologies aimed tion of such algorithms is still poor as publicly available image datasets with associated Gold Standard (GS) segmentation are currently limited to speciﬁc anatomical regions, such as retina [12] .”
Evolutionary Compression of Deep Neural Networks for Biomedical Image Segmentation (2020, background): “This trend is mainly attributed to the paradigm that transferred from traditional image processing and machine learning to deep learning [31], [32].”
A location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images (2017, background): “In [12], many vessels detection methods are reviewed.”
Segmenting Retinal Blood Vessels With Deep Neural Networks (2016, methodology): “Blood vessel segmentation in fundus imaging was subject to numerous studies in the past – the extensive review published in 2012 cites 73 works that used machine learning, matched filtering, morphological processing, vessel tracking, multi-scale and model-based approaches [8].”
A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology (2019, background): “Similarly, vascular tree segmentation [36] is a case where post-processing for topology correction could be replaced with topological priors inside the”
A Cross-Modality Learning Approach for Vessel Segmentation in Retinal Images (2016, methodology): “The existence of vessel crossing, branching and centerline reflex makes it difficult [1], [8], [9] to segment the vessels accurately using artificially designed features.”
An effective retinal blood vessel segmentation method using multi-scale line detection (2013, background): “A complete review of existing methods for retinal blood vessel segmentation can be referenced at [9].”
Image-Based Phenotyping of the Mature Arabidopsis Shoot System (2014, background): “Computer vision approaches are successfully developed in other fields dealing with similar structures like blood vessels or biological neural networks [13,22].”
Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database (2013, background): “There is a considerable body of work on automatic retinal vessel segmentation [15].”
Blood Vessel Segmentation of Fundus Images by Major Vessel Extraction and Subimage Classification (2015, background): “The problem of automated segmentation of retinal blood vessels has received significant attention over the past decade [12].”
An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation (2012, background): “A recent detailed review of these methods can be found in [4].”
Recurrent residual U-Net for medical image segmentation (2019, methodology): “49,52 Therefore, there is no overlap between the training and testing samples.”