A Survey of Graph Cuts/Graph Search Based Medical Image Segmentation

Abstract

Medical image segmentation is a fundamental and challenging problem for analyzing medical images. Among different existing medical image segmentation methods, graph-based approaches are relatively new and show good features in clinical applications. In the graph-based method, pixels or regions in the original image are interpreted into nodes in a graph. By considering Markov random field to model the contexture information of the image, the medical image segmentation problem can be transformed into a graph-based energy minimization problem. This problem can be solved by the use of minimum s-t cut/ maximum flow algorithm. This review is devoted to cut-based medical segmentation methods, including graph cuts and graph search for region and surface segmentation. Different varieties of cut-based methods, including graph-cuts-based methods, model integrated graph cuts methods, graph-search-based methods, and graph search/graph cuts based methods, are systematically reviewed. Graph cuts and graph search with deep learning technique are also discussed.

Quantification in Musculoskeletal Imaging Using Computational Analysis and Machine Learning: Segmentation and Radiomics

“…Graph-based methods may encode global image information, thus allowing the use of contextual information. 64 In practice, the segmentation problem is transformed into a "vertex-labeling" or "graph-partitioning" problem that requires assigning correct labels to each node of the graph according to its properties. 65 Although the nodes of the graph most commonly are the image pixels or voxels, other types of vertices can also be used to construct the graph, such as region-or user-specific markers.…”

Multi-object Graph-based Segmentation with Non-overlapping Surfaces

“…Mesh vertices are then moved to the position associated with the outermost node in their normal aligned columns which is in S. The s-t cut is often computed with the efficient algorithm by Boykov and Kolmogorov [3]. Furthermore, several extensions to this basic construction have since been developed [4].…”

Robust Automated detection of Nanocarriers’ Toxicity using Microscopic Image Analysis

“…Binarization process isolates background pixels from foreground pixels based on the threshold value of luminance. Clustering based, histogram based are the generally known thresholding methods [11][12][13]. More progressive methods include graph cut and level set based, but these lead to more computational complexity [12,14,15].…”

“…Clustering based, histogram based are the generally known thresholding methods [11][12][13]. More progressive methods include graph cut and level set based, but these lead to more computational complexity [12,14,15]. Here a basic thresholding method was applied where pixels in input image having luminance value greater than threshold value are replaced with value 1, while rest of the pixels is replaced with value 0.…”