Application of Morphological Bit Planes in Retinal Blood Vessel Extraction

Digital Imaging Research Centre, Faculty of Science Engineering and Computing, Kingston University London, Penrhyn Road, Kingston upon Thames, KT12EE, UK, .
Journal of Digital Imaging (Impact Factor: 1.19). 07/2012; 26(2). DOI: 10.1007/s10278-012-9513-3
Source: PubMed


The appearance of the retinal blood vessels is an important diagnostic indicator of various clinical disorders of the eye and the body. Retinal blood vessels have been shown to provide evidence in terms of change in diameter, branching angles, or tortuosity, as a result of ophthalmic disease. This paper reports the development for an automated method for segmentation of blood vessels in retinal images. A unique combination of methods for retinal blood vessel skeleton detection and multidirectional morphological bit plane slicing is presented to extract the blood vessels from the color retinal images. The skeleton of main vessels is extracted by the application of directional differential operators and then evaluation of combination of derivative signs and average derivative values. Mathematical morphology has been materialized as a proficient technique for quantifying the retinal vasculature in ocular fundus images. A multidirectional top-hat operator with rotating structuring elements is used to emphasize the vessels in a particular direction, and information is extracted using bit plane slicing. An iterative region growing method is applied to integrate the main skeleton and the images resulting from bit plane slicing of vessel direction-dependent morphological filters. The approach is tested on two publicly available databases DRIVE and STARE. Average accuracy achieved by the proposed method is 0.9423 for both the databases with significant values of sensitivity and specificity also; the algorithm outperforms the second human observer in terms of precision of segmented vessel tree.

22 Reads
  • [Show abstract] [Hide abstract]
    ABSTRACT: This study plays a vital role in the significance of the analysis of an image in medical image processing field, is gaining thought of many researchers in modern times. The recognition of faults present in the destroyed portion of an image is imperative for based field. In this paper, we focus at developing an approach for better classification of medical images. Our methodology is based on the concept of a novel fuzzy approach with bit plane (FCMBP) algorithm. The bit plane filtering method is used to slice the given image for classification to find out the destroyed region of the given image. The sliced image should be normalized with the old techniques and compared with the fuzzy technique for better classification and cluster of the spoiled portion. Thereby the control points have been extracted that are needed for further reconstruction of images. The performance of fuzzy approach with bit plane technique is evaluated using simulation and it is proved that our approach yields better results when compared to accessible methods.
    Emerging Trends in Computing, Communication and Nanotechnology (ICE-CCN), 2013 International Conference on; 01/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: Automatic segmentation of the retinal vasculature is considered as a first step in computer assisted medical applications related to diagnosis and treatment planning. This paper describes a pixel classification based method of segmenting retinal blood vessels using linear discriminant analysis. The vessel-ness measure of a pixel is defined by the feature vector comprised of a modified multiscale line operator and Gabor filter responses. The sequential forward feature selection scheme is used to identify the optimal scales for the line operator and Gabor filter. The linear discriminant classifier utilizes only two features for pixel classification. The feature vector encodes information to reliably handle normal vessels in addition to vessels with strong light reflexes along their centerline, which is more apparent on retinal arteriolars than venules. The method is evaluated on the three publicly available DRIVE, STARE and MESSIDOR datasets. The method is computationally fast and its performance approximates the 2nd human observer as well as other existing methodologies available in the literature, thus making it a suitable tool for automated retinal image analysis.
    IEEE International Conference on Computer Medical Applications (ICCMA), 2013; 01/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: Changes and variation in retinal vessel width are related to vascular risk factors and prospectively related to cardiovascular disease in later life. Hence, assessment of vessel width may be a useful physio-marker and potential predictor of cardiovascular status. However, measurement of vessel calibre from retinal images is a challenging process to automate. This paper proposes an automated system to measure vessel calibre in retinal images, which is demonstrated in images of multi-ethnic school children. The diameter measurement is based on the detection of the centreline pixels from a vessel probability map image, determining the vessel orientation at these pixels, extracting the vessel segments and later using a two-dimensional model, which is optimized to fit various types of intensity profiles of vessel segments. The width is then estimated from parameters of the optimized model. The method is also quantitatively analyzed using monochromatic representations of different colour spaces. The algorithm is evaluated on a recently introduced public database CHASE_DB1, which is a subset of retinal images of multi-ethnic children from the Child Heart and Health Study in England (CHASE) dataset. Moreover, the precise estimation of retinal vascular widths is critical for epidemiologists to identify the risk factors. This work also introduces an interactive software tool for epidemiologists, with which retinal vessel calibre can be precisely marked.
    Computerized medical imaging and graphics: the official journal of the Computerized Medical Imaging Society 03/2013; 37(1):48-60. DOI:10.1016/j.compmedimag.2013.01.004 · 1.22 Impact Factor
Show more

Similar Publications