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 relia… Show more
“…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.…”
Spinal cord tumour is an abnormal growth of cells in and around the spinal cord. Detecting spinal cord tumours is a very crucial process. Identifying the tumour from MRI is difficult because of the shape size and flexible nature of the spinal cord. The cross-sectional area of the cord is also very less. The boundary of tumour can be identified in the MRI by various segmentation techniques. Segmentation is one of the necessary steps. Spinal cord segmentation techniques are not as developed as brain segmentation techniques. In this paper, we review a number of spinal cord segmentation techniques like Intensity-based, Surface-Based Image-based techniques, and Machine learning techniques. A detailed analysis of the various segmentation techniques is proposed.
“…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.…”
Spinal cord tumour is an abnormal growth of cells in and around the spinal cord. Detecting spinal cord tumours is a very crucial process. Identifying the tumour from MRI is difficult because of the shape size and flexible nature of the spinal cord. The cross-sectional area of the cord is also very less. The boundary of tumour can be identified in the MRI by various segmentation techniques. Segmentation is one of the necessary steps. Spinal cord segmentation techniques are not as developed as brain segmentation techniques. In this paper, we review a number of spinal cord segmentation techniques like Intensity-based, Surface-Based Image-based techniques, and Machine learning techniques. A detailed analysis of the various segmentation techniques is proposed.
“…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.…”
Section: The New Anisotropic Geodesic Metric With Nonlocal Informationmentioning
confidence: 99%
“…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.…”
In this work, we introduce an anisotropic minimal path model based on a new Riemannian tensor integrating the crossing-adaptive anisotropic radius-lifted tensor field and the front freezing indicator by appearance and path features. The non-local path feature only can be obtained during the geodesic distance computation process by the fast marching method. The predefined criterion derived from path feature is able to steer the front evolution by freezing the point causing high bending of the geodesic to solve the shortcut problem. We performed qualitative and quantitative experiments on synthetic and real images (including retinal vessels, rivers and roads) and compare with the minimal path models with classical anisotropic Riemannian metric and dynamic isotropic metric, which demonstrated the proposed method can detect desired targets from complex tubular tree structures.
“…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…”
Section: Computation Of the Crossing-adaptive Tensor Fieldmentioning
In this work, we propose a new minimal path model with a Riemannian metric updated scheme during the fast marching propagation for interactive vessel extraction. The invoked metric consists of a crossing-adaptive anisotropic radiuslifted tensor field and a front freezing indicator. The crossingadaptive tensor field reduces the anisotropy of the metric on the crossing points. The indicator steers the front evolution by freezing the points causing high curvature of a geodesic. Thus the short branches combination problem commonly existing in tubular structure delineation by minimal path models can be solved. We validate our model on the DRIVE and IOSTAR datasets, which demonstrates that it is able to extract the centreline position and vessel width from a complex vessel network efficiently and accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.