Gradient Competition Anisotropy for Centerline Extraction and Segmentation of Spinal Cords

Abstract

Centerline extraction and segmentation of the spinal cord--an intensity varying and elliptical curvilinear structure under strong neighboring disturbance are extremely challenging. This study proposes the gradient competition anisotropy technique to perform spinal cord centerline extraction and segmentation. The contribution of the proposed method is threefold--1) The gradient competition descriptor compares the image gradient obtained at different detection scales to suppress neighboring disturbance. It reliably recognizes the curvilinearity and orientations of elliptical curvilinear objects. 2) The orientation coherence anisotropy analyzes the detection responses offered by the gradient competition descriptor. It enforces structure orientation consistency to sustain strong disturbance introduced by high contrast neighboring objects to perform centerline extraction. 3) The intensity coherence segmentation quantifies the intensity difference between the centerline and the voxels in the vicinity of the centerline. It effectively removes the object intensity variation along the structure to accurately delineate the target structure. They constitute the gradient competition anisotropy method which can robustly and accurately detect the centerline and boundary of the spinal cord. It is validated and compared using 25 clinical datasets. It is demonstrated that the proposed method well suits the applications of spinal cord centerline extraction and segmentation.

Spinal Cord MRI Segmentation Techniques and Algorithms: A Survey

“…Law et al [27] implemented a partially automatic technique which calculates the centre line of spinal cord by suppressing neighboring disturbances in the image while assuring coherence of gradient alignment. Based on the intensity differences the method performs the segmentation of spinal cord by dividing the vicinity of the centreline into 2 regions ie the spinalcord and the structures around it.…”

Anisotropic tubular minimal path model with fast marching front freezing scheme

“…However, for crossing points, denoted by y, there will be at least two vessels across one another. This means that the highly anisotropic tensors which can be done by invoking the orientation scores [2] or by structure tensors [37]. In this section, we construct our crossing-adaptive radius-lifted tensor field through the tool of structure tensor.…”

“…For the crossing point, the tensor field T smooth is impacted greater by the vessel with bigger radius. Note that the main difference between T smooth and the structure tensor field used in[37] lies at the existence of the function . As discussed above, it can reduce or avoid the effects derived from the non-vessel regions.…”

Vessel Extraction Using Crossing-Adaptive Minimal Path Model With Anisotropic Enhancement And Curvature Constraint

“…So the speed computed from the anisotropic metric is slower along the weak vessel than that along the strong one. To solve this problem, the anisotropy of the metric on a crossing point is reduced by utilizing the crossing-adaptive structure tensors as described [9]. The spatial anisotropy tensor filed M a and scalar function P s of M are shown as…”