2,070 Hits in 10.9 sec

A Review of Machine Learning Methods for Retinal Blood Vessel Segmentation and Artery/Vein Classification

Muthu Rama Krishnan Mookiah, Stephen Hogg, Tom J MacGillivray, Vijayaraghavan Prathiba, Rajendra Pradeepa, Viswanathan Mohan, Ranjit Mohan Anjana, Alexander S. Doney, Colin N.A. Palmer, Emanuele Trucco
2020 Medical Image Analysis  
The results allow us to offer our views on the outlook for vessel segmentation and classification for fundus camera images.  ...  The eye affords a unique opportunity to inspect a rich part of the human microvasculature non-invasively via retinal imaging.  ...  In terms of the challenges listed above, multi-scale line detection and double thresholding were used to enhance thin vessels, vessels at crossover points and close parallel ones Nguyen et al. (2013) ;  ... 
doi:10.1016/ pmid:33385700 fatcat:tborpqx7erglne723rnocq24qe

Automated detection of proliferative diabetic retinopathy using a modified line operator and dual classification

R.A. Welikala, J. Dehmeshki, A. Hoppe, V. Tah, S. Mann, T.H. Williamson, S.A. Barman
2014 Computer Methods and Programs in Biomedicine  
Two vessel segmentation approaches are applied, using the standard line operator and a novel modified line operator. The latter is designed to reduce false responses to non-vessel edges.  ...  Sensitivity and specificity results using a dataset of 60 images are 0.862 and 0.944 respectively on a per patch basis and 1.00 and 0.90 respectively on a per image basis.  ...  This includes a novel modified line operator, based on double sided thresholding, designed to segment vessels whilst reducing false responses to non-vessel edges. © 2014, Elsevier.  ... 
doi:10.1016/j.cmpb.2014.02.010 pmid:24636803 fatcat:ydwtinlkhzbx5lgslpdtsbaxnm

Blood vessel segmentation methodologies in retinal images – A survey

M.M. Fraz, P. Remagnino, A. Hoppe, B. Uyyanonvara, A.R. Rudnicka, C.G. Owen, S.A. Barman
2012 Computer Methods and Programs in Biomedicine  
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  ...  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 binary maps of the vessels are obtained at four scales by using morphological reconstruction with a double threshold operator.  ... 
doi:10.1016/j.cmpb.2012.03.009 pmid:22525589 fatcat:t6cjgne6rbckjlj7w7r4ptx6ui

A Review of Computer Aided Detection of Anatomical Structures and Lesions of DR from Color Retina Images

Sreejini K S, V. K Govindan
2015 International Journal of Image Graphics and Signal Processing  
It is difficult to detect vessels at regions where close vessels are merged, at regions of missing of small vessels, at optic disc regions, and at regions of pathology.  ...  The research in detection of anatomical structures is further divided into subcategories, namely, vessel segmentation and vessel centerline extraction, optic disc segmentation and localization, and fovea  ...  This uses two dictionary; one for small scale to medium scale vessel center-lines and non-vessel center-lines, and the other for large scale vessel center-lines and non-vessel center-lines.  ... 
doi:10.5815/ijigsp.2015.11.08 fatcat:5sqvtk5gebc27cpwijh3e45wby

An exclusive‐disjunction‐based detection of neovascularisation using multi‐scale CNN

Geetha Pavani P, Birendra Biswal, M V S Sairam, Pradyut Kumar Biswal
2021 IET Image Processing  
In the first stage, the retinal images are classified into non-NV and NV using multi-scale convolutional neural network, while in the second stage, 13 relevant features are extracted from the vascular  ...  At the same time, the pixel locations of optic disc (OD) are detected using intensity distribution and variations on the retinal images.  ...  A Gaussian-shaped curve is used for the detection of piecewise linear segments of blood vessels in the retinal images by considering a grey-level cross section of blood vessels.  ... 
doi:10.1049/ipr2.12122 fatcat:xaqw35xrdfaa5eztaq4ycvyt7a

Classification of Eye Diseases Using Optic Cup Segmentation and Optic Disc Ratio

B.Balaji Naik, R. Mariappan
2016 IOSR Journal of Computer Engineering  
The retinal images are widely used in the diagnosis and treatment of various eye diseases such as diabetic retinopathy, cataract and glaucoma.  ...  Segmentation imaging of the eye retina provides an important role in the calculation the shape and size of the optic disc and the anterior segment and the abnormal growth of any geometry in the eye region  ...  Then thresholding is applied and distinction between the first and reconstructed image is found. The ensuing image is superimposed on the first retinal image.  ... 
doi:10.9790/0661-1805031522 fatcat:o2426xay7nbzlmmpj5lxt3sdue

Segmentation of Exudates from Retinal Image

M. Reema Lovelyn, Rama Prasath
2017 Indian Journal of Science and Technology  
Non-uniform and low contrast images cannot be used for detection. They are reduced using the preprocessing techniques.  ...  The edges were detected using the edge detection techniques after this finally the exudates are detected. Findings: This paper deals with the retinal images to detect exudates.  ...  Venkata Subramanian Dean (School of Computer Sciences), for their encouragement and support to complete this project. We are thankful to Dr.  ... 
doi:10.17485/ijst/2017/v10i42/120343 fatcat:kvpt4uf5yfhsdo3tz55t6v7c4a

An Enhanced Segmentation Technique for Blood Vessel in Retinal Images

Kimmy Mehta, Navpreet Kaur
2016 International Journal of Computer Applications  
After removing the noise, segmentation of blood vessels is carried out using thresholding method. Segmented image needs to be post-processed before considering it for examining any disease.  ...  In this paper, an effective blood vessel segmentation method from coloured retinal fundus images is presented. Segmentation is done by extracting the green channel from RGB retinal image.  ...  Finally, Ricci and Pefetti [53] used a support vector machine (SVM) for pixel categorization as vessel or non-vessel.  ... 
doi:10.5120/ijca2016911548 fatcat:lc7drvetrbexzclj4t5p6p2ro4

Comparative Analysis of Vessel Segmentation Techniques in Retinal Images

Azhar Imran, Jianqiang Li, Yan Pei, Ji-Jiang Yang, Qing Wang
2019 IEEE Access  
INDEX TERMS Vessel segmentation, retinal diseases, image segmentation, retinal fundus images, medical imaging. 114866 VOLUME 7, 2019 A.  ...  .: Comparative Analysis of Vessel Segmentation Techniques in Retinal Images FIGURE 3.  ...  The vessel skeleton map was constructed using double threshold curvature image and morphological reconstruction which was used to obtain retinal vessel segmentation.  ... 
doi:10.1109/access.2019.2935912 fatcat:64ycsdgecza4tkq3m5c7qs2r7m

Leveraging Multiscale Hessian-Based Enhancement With a Novel Exudate Inpainting Technique for Retinal Vessel Segmentation

Roberto Annunziata, Andrea Garzelli, Lucia Ballerini, Alessandro Mecocci, Emanuele Trucco
2016 IEEE journal of biomedical and health informatics  
Retinal vascular enhancement is achieved with a multiple-scale Hessian approach.  ...  Accurate vessel detection in retinal images is an important and difficult task. Detection is made more challenging in pathological images with the presence of exudates and other abnormalities.  ...  [29] for making their retinal image datasets publicly available.  ... 
doi:10.1109/jbhi.2015.2440091 pmid:26054078 fatcat:vqg7i5hdkneurhgbhq72yedaju

BAT algorithm inspired retinal blood vessel segmentation

Vallikutti Sathananthavathi, Ganesan Indumathi
2018 IET Image Processing  
The proposed methodology for the retinal vessel segmentation is based on BAT algorithm and random forest classifier.  ...  Performance of the proposed method is analysed by the publicly available databases such as digital retinal images for vessel extraction and structured analysis of the retina.  ...  The matched filter-based approach detects the retinal blood vessel by applying the matched filter kernel and thresholding on the input retinal image.  ... 
doi:10.1049/iet-ipr.2017.1266 fatcat:4mchunvd5rfjbffsmzvqdr3kai

Accurate Image Analysis of the Retina Using Hessian Matrix and Binarisation of Thresholded Entropy with Application of Texture Mapping

Xiaoxia Yin, Brian W-H Ng, Jing He, Yanchun Zhang, Derek Abbott, Alfred S. Lewin
2014 PLoS ONE  
The result is combined with a binarized image, obtained using a threshold that maximizes entropy, to extract the retinal vessels from the background.  ...  The resultant image exhibits the central light reflex of retinal arteries and veins, which prevents the segmentation of whole vessels.  ...  ., China for supporting the project. Author Contributions  ... 
doi:10.1371/journal.pone.0095943 pmid:24781033 pmcid:PMC4004557 fatcat:27g5big7dvcbldnyr2omweoyjy

Automated Detection of Leakage in Fluorescein Angiography Images with Application to Malarial Retinopathy

Yitian Zhao, Ian J. C. MacCormick, David G. Parry, Sophie Leach, Nicholas A. V. Beare, Simon P. Harding, Yalin Zheng
2015 Scientific Reports  
We have developed a framework that can automatically detect three types of leakage (large focal, punctate focal, and vessel segment leakage) and validated it on images from patients with malarial retinopathy  ...  The detection and assessment of leakage in retinal fluorescein angiogram images is important for the management of a wide range of retinal diseases.  ...  The support of these groups was essential for the success of this work.  ... 
doi:10.1038/srep10425 pmid:26030010 pmcid:PMC4450752 fatcat:tnnpfu2ubjdcrottzqj2dy237y

Automatic detection of microaneurysms using microstructure and wavelet methods

2015 Sadhana (Bangalore)  
Based on ground truth validation, good segmentation results are achieved when compared to existing algorithms such as local relative entropy-based thresholding, inverse adaptive surface thresholding, inverse  ...  Retinal microaneurysm is one of the earliest signs in diabetic retinopathy diagnosis.  ...  First, vessel centre-line candidates are extracted using multi-scale matched filtering, scale production, double thresholding and centre-line detection.  ... 
doi:10.1007/s12046-015-0353-y fatcat:qc4iq3n7nbhm3cjrxhxftwnhai

Classification of eye diseases using optic cup segmentation and optic disc ratio and its implementation using VHDL

B. Balaji Naik
2018 International Journal of Engineering & Computer Science  
The retinal images are widely used in the diagnosis and treatment of various eye diseases such as diabetic retinopathy, cataract, and glaucoma.  ...  Segmentation imaging of the eye retina provides an important role in the calculation the shape and size of the optic disc and the anterior segment and the abnormal growth of any geometry in the eye region  ...  Then thresholding is applied and the distinction between the first and reconstructed image is found. The ensuing image is superimposed on the first retinal image.  ... 
doi:10.31295/ijecs.v1n1.19 fatcat:rsxlcd4ojnbynbgc7647hsjqya
« Previous Showing results 1 — 15 out of 2,070 results