X-Ray cardiac angiographic vessel segmentation based on pixel classification using machine learning and region growing

Abstract

This work proposes a pixel-classification approach for vessel segmentation in x-ray angiograms. The proposal uses textural features such as anisotropic diffusion, features based on the Hessian matrix, mathematical morphology and statistics. These features are extracted from the neighborhood of each pixel. The approach also uses the ELEMENT methodology, which consists of creating a pixelclassification controlled by region-growing where the result of the classification affects further classifications of pixels. The Random Forests classifier is used to predict whether the pixel belongs to the vessel structure. The approach achieved the best accuracy in the literature (95.48%) outperforming unsupervised state-of-the-art approaches.

Brain Tumor Segmentation Based on Bendlet Transform and Improved Chan-Vese Model

“…Figure 8 is the original image. Figure 9 shows the visualization results obtained by the proposed algorithm, CV, K-FCM [ 9 ], Ostu [ 30 ] and region growing algorithm [ 8 ] for brain tumor segmentation. The experimental results of the threshold algorithm were obtained by manually adjusting the threshold parameters several times.…”

“…Unsupervised segmentation does not require ground-truth images as a criterion to train the model. Although there are several general segmentation methods, such as histogram thresholding [ 7 ], region growing [ 8 ], CV, and statistical clustering [ 9 ], etc., they have failed to achieve good results in the domain of brain tumor identification. Wavelet-based methods are widely used to solve difficult and hot problems, and their effectiveness has been proven in many applications, including data compression [ 10 ], signal processing [ 11 ], image enhancement [ 12 ], image compression [ 13 ], image segmentation [ 14 ], pattern recognition [ 15 ], etc.…”

Semi-automatic segmentation of coronary vessels based on improved livewire algorithm

“…The qualitative and quantitative analysis of coronary artery is important in clinical practice [1][2][3] . Although automatic segmentation is feasible [4][5][6] , certain anatomical structures in x-ray angiographic images, including high curvatures, loops, superpositions, and crossings of vessels etc., still make it more practical to extract coronary vessels manually. Moreover, manual segmentation of coronary artery remains the gold standard.…”