Automated Segmentation of Abdominal Aortic Aneurysms in Multi-spectral MR Images

Abstract

Abstract. An automated method for segmenting the outer boundary of abdominal aortic aneurysms in MR images is presented. The method is based on the well known Active Shape Models (ASM), which fit a global landmark-based shape model on the basis of local boundary appearance models. The original threedimensional ASM scheme is modified to deal with multi-spectral image information and inconsistent boundary appearance in a principled way, with only a limited amount of training data. In addition, a framework for user interaction is proposed. If required, the obtained segmentation can be corrected in an interactive manner by indicating points on the desired boundary. The methods are evaluated in leave-one-out experiments on 21 datasets. A segmentation scheme combining gray level information from two or three MR sequences produces significantly better results than a single-scan model. Average volume errors with respect to the manual segmentation are 4.0%, in 19 out of 21 datasets. In the cases in which the obtained error is large, results can easily be improved using the interactive scheme.

Outlier Detection and Handling for Robust 3-D Active Shape Models Search

“…In most applications, each ratio of the interlandmark distances can be assumed to follow a Gaussian distribution, in which case it can be shown [22] that the statistical tolerance interval, i.e., the solution of (7), can be calculated from the mean and standard deviation in the following form (8) where is the two-sided tolerance factor, which can be approximated by [23] (9)…”

“…Specific constraints found in the model are usually imposed to limit the shapes to valid instances. Model construction [2]- [4], as well as image segmentation [5], [6] using ASM, has been generalized to 3-D and higher dimensional cases, and the method is used extensively in clinical applications [7], [8].…”

Segmentation of thin structures in volumetric medical images

“…Recent segmentation techniques for thin structures include [18], where 'medial atoms' are used to segment branching tubular structures, a user-defined B-spline template snakes that initialize a segmentation process [41], and active shape model for segmenting abdominal aortic aneurysms, where a set of landmark points that denote the same anatomical points are matched [15]. Often, similar to [21], [22], several resolution levels enable more efficient coarse to fine fitting.…”

Segmentation of Intracranial Vessels and Aneurysms in Phase Contrast Magnetic Resonance Angiography Using Multirange Filters and Local Variances

“…For instance, detection of AAA was modeled as an abrupt change of radius of a vessel segment [12]. In [13], Bruijne et al described the segmentation of AAA using intensive user interaction along with shape modeling when training data is limited. Lin employed shape information to sustain the disturbance induced by AAA while performing vascular analysis [14].…”