Retinal blood vessel segmentation from retinal image using B-COSFIRE and adaptive thresholding

Abstract

<span>Segmentation of blood vessels (BVs) from retinal image is one of the important steps in developing a computer-assisted retinal diagnosis system and has been widely researched especially for implementing automatic BV segmentation methods. This paper proposes an improvement to an existing retinal BV (RBV) segmentation method by combining the trainable B-COSFIRE filter with adaptive thresholding methods. The proposed method can automatically configure its selectivity given a prototype pattern to be detected. Its segmentation performance is comparable to many published methods with the advantage of robustness against noise on retinal background. Instead of using grid search to find the optimal threshold value for a whole dataset, adaptive thresholding (AT) is used to determine the threshold for each retinal image. Two AT methods investigated in this study were ISODATA and Otsu’s method. The proposed method was validated using 40 images from two benchmark datasets for retinal BV segmentation validation, namely DRIVE and STARE. The validation results indicated that the segmentation performance of the proposed unsupervised method is comparable to the original B-COSFIRE method and other published methods, without requiring the availability of ground truth data for new dataset. The Sensitivity and Specificity values achieved for DRIVE and STARE are 0.7818, 0.9688, 0.7957 and 0.9648, respectively.</span>

Efficient BFCN for Automatic Retinal Vessel Segmentation

“…Roychowdhury et al [ 11 ] proposed a region growing method for segmenting blood vessels, but specialized knowledge was required in the setting of blood vessel seed points and the formulation of termination rules. By combining a trainable B-COSFIRE filter with an adaptive threshold method, Ali et al [ 12 ] proposed the improvement over the current method of retinal blood vessel segmentation. The proposed method can automatically configure selectivity in a prototype mode check.…”

Recent Techniques and Trends for Retinal Blood Vessel Extraction and Tortuosity Evaluation: A Comprehensive Review

“…Two methods, ISODATA and Otsu thresholding were used as part of adaptive thresholding to find the optimal threshold. The combination of the B-COSFIRE filter with the ISODATA method achieved better results than the combination with Otsu thresholding [62].…”

“…The threshold for blood vessel segmentation can be divided into methods based on statistical elements, knowledge or fuzzy logic. In the individual approaches (see Table IX), images were preprocessed in combination with wavelet transform or filters, and subsequently adaptive thresholding was applied [62][63][64][65][66].…”

Retina blood vessel extraction based on kirsch’s template method

“…The total number of false positive (FP), false negative (FN), true positive (TP), and true negative (TN) pixels are used as the parameter for the formula to quantify the extraction performance. The comparison of the images will be between the ground truth image and the segmented image [21].…”

“…This method is also used by Yanli Hou [18] which propose the improved multiscale line detector to yield the blood vessel response. In addition, there also others method using the adaptive thresholding technique [19,20], Bar-selective Combination of Shifted Filter Response (B-COSFIRE) [21,22], Kirsch method [7][8][9][10][11] and others. The research is able to reduce the time for the opthalmologist to analyse and diagnose the result of the fundus image of patient.…”