Difference image and fuzzy c-means for detection of retinal vessels
06 Mar 2016-pp 169-172
TL;DR: A study that combines difference image (DI) with fuzzy c-means (FCM) for the detection of vessels in retinal images is presented and achieves promising results.
Abstract: Digital retinal photography and the application of computer vision in ophthalmology are increasingly becoming helpful in the diagnosis and management of retinopathies and cardiovascular diseases. Although several automatic methods of detecting vessels in retinal images have been proposed, there has however been a need for improved automatic vessel detection methods that is capable of handling the problem of large vessel network connectivity and poor detection of thin retinal vessels. A study that combines difference image (DI) with fuzzy c-means (FCM) for the detection of vessels in retinal images is presented in this paper. The DI is used to handle noise caused by illumination variation in the pre-processing of retinal images and the vessels are detected using FCM. A post-processing phase that combines different morphological operations for the removal of the noisy pixels was applied. The method proposed in this paper achieves a high average sensitivity rate of 0.7302 and average accuracy rate of 0.9444 on DRIVE database. In comparison with several previously proposed methods in the literature, the method proposed in this paper achieves promising results.
Citations
More filters
TL;DR: This issue marks a transition and a changing of the guard for Computational and Mathematical Methods in Medicine as Hindawi takes the helm and converts CMMM to the community-based, open access model that they have so successfully championed.
Abstract: This issue marks a transition and a changing of the guard for Computational and Mathematical Methods in Medicine (CMMM). It is with some nostalgia that we look back on our long and illustrious association with Taylor and Francis; however, at the same time we look to the future with optimism and hope as Hindawi takes the helm and converts CMMM to the community-based, open access model that they have so successfully championed. The Hindawi Publishing Corporation is one of the fastest growing academic publishers worldwide with over 200 academic journals in their portfolio and a commitment to the highest levels of peer review and excellence.
Reflecting on the genesis and evolution of CMMM, it is clear that Brian Sleeman, the founding Editor-in-Chief, showed great foresight in creating a journal that brought together the disparate disciplines of mathematics and medicine and that continues to play a major role in the development of mathematical medicine. He worked passionately to develop and promote the journal through some difficult times, with the insight and courage to bring together both biomedical/clinical scientists and mathematical scientists onto a single editorial board (a practice that has become more commonplace in subsequent journals in the field). The success that the journal has enjoyed thus far is a clear testament to his hard work, dedication, and vision.
The journal has continued to provide a unique forum for the dissemination of interdisciplinary research resulting from collaborations between clinicians/experimentalists and theoreticians. CMMM has also continued to evolve rapidly, reflecting the increased focus on systems and interdisciplinary collaborative efforts across the breadth of biomedical, clinical, and translational research areas. The past year also saw the result of much hard work, with the inclusion of the journal in PubMed/Medline and the Science Citation Index Expanded. This was a great development for the journal since it not only has had an enormous impact on the general awareness and profile of the journal but has also resulted in increased submissions and downloads from the journal website over the past year. It has been exciting and rewarding to see the journal develop and evolve in this manner, and we look forward to increased success following this higher profile.
The future looks extremely bright for the field of mathematical medicine as it emerges from its period of infancy and takes its place as a legitimate and central field of research and enquiry. Our sincere hope and wish is that CMMM continues from strength to strength and fulfills its role and promise as envisioned originally by its founding editor.
Pamela Jones
Sivabal Sivaloganathan
138 citations
01 Mar 2020-Acta informatica medica : AIM : journal of the Society for Medical Informatics of Bosnia & Herzegovina : časopis Društva za medicinsku informatiku BiH
TL;DR: This study aims to analyze the performance of the algorithms of k-means and FCM for retinal blood vessel segmentation using the performance parameters of the area under the curve (AUC).
Abstract: Introduction The segmentation method has a number of approaches, one of which is clustering. The clustering method is widely used for segmenting retinal blood vessels, especially the k-mean algorithm and fuzzy c-means (FCM). Unfortunately, so far there have been no studies comparing the two methods for blood vessel segmentation. Many studies do not explain the reason for choosing the method. Aim This study aims to analyze the performance of the algorithms of k-means and FCM for retinal blood vessel segmentation. Methods This research method is divided into three stages, namely preprocessing, segmentation, and performance analysis. Preprocessing uses the green channel method, Contrast-limited adaptive histogram equalization (CLAHE) and median filter. Segmentation is divided into three processes, namely clustering, thresholding and determining the region of interest (ROI). In the thresholding process, the determination of the threshold value uses two methods, namely the mean and the median. The third stage performs performance analysis using the performance parameters of the area under the curve (AUC) and statistical tests. Results The statistical test results comparing FCM with k-means based on AUC values resulted in p-values <0.05 with a confidence level of 95%. Conclusion Retinal vascular segmentation with the FCM method is significantly better than k-means.
26 citations
Cites methods from "Difference image and fuzzy c-means ..."
...Criteria for these conditions using the equation (7)...
[...]
TL;DR: In this article, an automated retinal fundus image segmentation system composed of three segmentation subsystems follow same core segmentation algorithm is proposed, despite of broad difference in features and characteristics; retinal vessels, optic disc, and exudate lesions are extracted by each subsystem without the need for texture analysis or synthesis.
Abstract: Eye exam can be as efficacious as physical one in determining health concerns. Retina screening can be the very first clue for detecting a variety of hidden health issues including pre-diabetes and diabetes. Through the process of clinical diagnosis and prognosis; ophthalmologists rely heavily on the binary segmented version of retina fundus image; where the accuracy of segmented vessels, optic disc, and abnormal lesions extremely affects the diagnosis accuracy which in turn affect the subsequent clinical treatment steps. This paper proposes an automated retinal fundus image segmentation system composed of three segmentation subsystems follow same core segmentation algorithm. Despite of broad difference in features and characteristics; retinal vessels, optic disc, and exudate lesions are extracted by each subsystem without the need for texture analysis or synthesis. For sake of compact diagnosis and complete clinical insight, our proposed system can detect these anatomical structures in one session with high accuracy even in pathological retina images. The proposed system uses a robust hybrid segmentation algorithm combines adaptive fuzzy thresholding and mathematical morphology. The proposed system is validated using four benchmark datasets: DRIVE and STARE (vessels), DRISHTI-GS (optic disc), and DIARETDB1 (exudates lesions). Competitive segmentation performance is achieved, outperforming a variety of up-to-date systems and demonstrating the capacity to deal with other heterogeneous anatomical structures.
20 citations
TL;DR: A literature review on vessel tracking methods focusing on machine-learning-based methods is presented in this article, where a general survey of deep learning-based vessel tracking frameworks is provided.
18 citations
Posted Content•
TL;DR: A literature review on vessel-tracking methods, focusing on machine- learning-based methods, and a general survey of deep-learning-based frameworks is provided.
Abstract: Developing efficient vessel-tracking algorithms is crucial for imaging-based diagnosis and treatment of vascular diseases. Vessel tracking aims to solve recognition problems such as key (seed) point detection, centerline extraction, and vascular segmentation. Extensive image-processing techniques have been developed to overcome the problems of vessel tracking that are mainly attributed to the complex morphologies of vessels and image characteristics of angiography. This paper presents a literature review on vessel-tracking methods, focusing on machine-learning-based methods. First, the conventional machine-learning-based algorithms are reviewed, and then, a general survey of deep-learning-based frameworks is provided. On the basis of the reviewed methods, the evaluation issues are introduced. The paper is concluded with discussions about the remaining exigencies and future research.
16 citations
References
More filters
01 Jan 1973
TL;DR: Two fuzzy versions of the k-means optimal, least squared error partitioning problem are formulated for finite subsets X of a general inner product space; in both cases, the extremizing solutions are shown to be fixed points of a certain operator T on the class of fuzzy, k-partitions of X, and simple iteration of T provides an algorithm which has the descent property relative to the least squarederror criterion function.
Abstract: Two fuzzy versions of the k-means optimal, least squared error partitioning problem are formulated for finite subsets X of a general inner product space. In both cases, the extremizing solutions are shown to be fixed points of a certain operator T on the class of fuzzy, k-partitions of X, and simple iteration of T provides an algorithm which has the descent property relative to the least squared error criterion function. In the first case, the range of T consists largely of ordinary (i.e. non-fuzzy) partitions of X and the associated iteration scheme is essentially the well known ISODATA process of Ball and Hall. However, in the second case, the range of T consists mainly of fuzzy partitions and the associated algorithm is new; when X consists of k compact well separated (CWS) clusters, Xi , this algorithm generates a limiting partition with membership functions which closely approximate the characteristic functions of the clusters Xi . However, when X is not the union of k CWS clusters, the limi...
5,787 citations
"Difference image and fuzzy c-means ..." refers methods in this paper
...The segmentation method is divided into three phases....
[...]
01 Jan 1973
TL;DR: In this paper, two fuzzy versions of the k-means optimal, least squared error partitioning problem are formulated for finite subsets X of a general inner product space, and the extremizing solutions are shown to be fixed points of a certain operator T on the class of fuzzy, k-partitions of X, and simple iteration of T provides an algorithm which has the descent property relative to the LSE criterion function.
Abstract: Two fuzzy versions of the k-means optimal, least squared error partitioning problem are formulated for finite subsets X of a general inner product space. In both cases, the extremizing solutions are shown to be fixed points of a certain operator T on the class of fuzzy, k-partitions of X, and simple iteration of T provides an algorithm which has the descent property relative to the least squared error criterion function. In the first case, the range of T consists largely of ordinary (i.e. non-fuzzy) partitions of X and the associated iteration scheme is essentially the well known ISODATA process of Ball and Hall. However, in the second case, the range of T consists mainly of fuzzy partitions and the associated algorithm is new; when X consists of k compact well separated (CWS) clusters, Xi , this algorithm generates a limiting partition with membership functions which closely approximate the characteristic functions of the clusters Xi . However, when X is not the union of k CWS clusters, the limi...
5,254 citations
TL;DR: A method is presented for automated segmentation of vessels in two-dimensional color images of the retina based on extraction of image ridges, which coincide approximately with vessel centerlines, which is compared with two recently published rule-based methods.
Abstract: A method is presented for automated segmentation of vessels in two-dimensional color images of the retina. This method can be used in computer analyses of retinal images, e.g., in automated screening for diabetic retinopathy. The system is based on extraction of image ridges, which coincide approximately with vessel centerlines. The ridges are used to compose primitives in the form of line elements. With the line elements an image is partitioned into patches by assigning each image pixel to the closest line element. Every line element constitutes a local coordinate frame for its corresponding patch. For every pixel, feature vectors are computed that make use of properties of the patches and the line elements. The feature vectors are classified using a kNN-classifier and sequential forward feature selection. The algorithm was tested on a database consisting of 40 manually labeled images. The method achieves an area under the receiver operating characteristic curve of 0.952. The method is compared with two recently published rule-based methods of Hoover et al. and Jiang et al. . The results show that our method is significantly better than the two rule-based methods (p<0.01). The accuracy of our method is 0.944 versus 0.947 for a second observer.
3,416 citations
TL;DR: The concept of matched filter detection of signals is used to detect piecewise linear segments of blood vessels in these images and the results are compared to those obtained with other methods.
Abstract: Blood vessels usually have poor local contrast, and the application of existing edge detection algorithms yield results which are not satisfactory. An operator for feature extraction based on the optical and spatial properties of objects to be recognized is introduced. The gray-level profile of the cross section of a blood vessel is approximated by a Gaussian-shaped curve. The concept of matched filter detection of signals is used to detect piecewise linear segments of blood vessels in these images. Twelve different templates that are used to search for vessel segments along all possible directions are constructed. Various issues related to the implementation of these matched filters are discussed. The results are compared to those obtained with other methods. >
1,692 citations
"Difference image and fuzzy c-means ..." refers methods in this paper
...1 shows the comparison of segmented vessel network obtained using the proposed method with the original coloured retinal fundus image and the ground truth of the detected vessels....
[...]
TL;DR: In this paper, a method for automated segmentation of the vasculature in retinal images is presented, which produces segmentations by classifying each image pixel as vessel or non-vessel, based on the pixel's feature vector.
Abstract: We present a method for automated segmentation of the vasculature in retinal images. The method produces segmentations by classifying each image pixel as vessel or nonvessel, based on the pixel's feature vector. Feature vectors are composed of the pixel's intensity and two-dimensional Gabor wavelet transform responses taken at multiple scales. The Gabor wavelet is capable of tuning to specific frequencies, thus allowing noise filtering and vessel enhancement in a single step. We use a Bayesian classifier with class-conditional probability density functions (likelihoods) described as Gaussian mixtures, yielding a fast classification, while being able to model complex decision surfaces. The probability distributions are estimated based on a training set of labeled pixels obtained from manual segmentations. The method's performance is evaluated on publicly available DRIVE (Staal et al.,2004) and STARE (Hoover et al.,2000) databases of manually labeled images. On the DRIVE database, it achieves an area under the receiver operating characteristic curve of 0.9614, being slightly superior than that presented by state-of-the-art approaches. We are making our implementation available as open source MATLAB scripts for researchers interested in implementation details, evaluation, or development of methods
1,435 citations