Interactive segmentation of abdominal aortic aneurysms in CTA images

Abstract

A model-based approach to interactive segmentation of abdominal aortic aneurysms from CTA data is presented. After manual delineation of the aneurysm sac in the first slice, the method automatically detects the contour in subsequent slices, using the result from the previous slice as a reference. If an obtained contour is not sufficiently accurate, the user can intervene and provide an additional manual reference contour. The method is inspired by the active shape model (ASM) segmentation scheme (), in which a statistical shape model, derived from corresponding landmark points in manually labeled training images, is fitted to the image in an iterative manner. In our method, a shape model of the contours in two adjacent image slices is progressively fitted to the entire volume. The contour obtained in one slice thus constrains the possible shapes in the next slice. The optimal fit is determined on the basis of multi-resolution gray level models constructed from gray value patches sampled around each landmark. We propose to use the similarity of adjacent image slices for this gray level model, and compare these to single-slice features that are more generally used with ASM. The performance of various image features is evaluated in leave-one-out experiments on 23 data sets. Features that use the similarity of adjacent image slices outperform measures based on single-slice features in all cases. The average number of slices in our datasets is 51, while on average eight manual initializations are required, which decreases operator segmentation time by a factor of 6.

Abdominal arteries recognition in x-ray using a structural model

“…The constraint propagation then progressively tightens the domains. We can observe that first the distance and directional constraints between A 4 and RL 1 allow to strongly reduce the domain of RL 1 . Then further reductions of D(RL 1 ) allow to conversely obtain a reduction of D(A 4 ) using those constraints.…”

“…Initially many possible positions are extracted by the low-level filters. The candidates for A 4 are presented in blue, whereas the possible positions for RL 1 and RR 1 are presented in yellow. The constraint propagation then progressively tightens the domains.…”

“…For instance approaches were proposed to automatically or semi-automatically segment the abdominal aorta in CTA or MRA, e.g. in [1][2][3] . The diameter of the lumen or of the outer wall are then estimated along the aorta, providing relevant information to assess the risk of rupture.…”

Semi-Automatic Segmentation of Ct/Mri Images Based on Active Contour Method for 3D Reconstruction of Abdominal Aortic Aneurysms

“…Medical Center Utrecht, one can notice their approach to segmenting the abdominal aorta evolved from an attempt to use an algorithm for automatic segmentation based on the active shape model (ASM), for which the probability of a given contour being the edge of aorta was calculated with the k nearest neighbour method (kNN) [2]. The authors mention that if the contour was wrongly assessed, an intervention by the operator is necessary and a few secondary points need to be added.…”

Region based level set segmentation of the outer wall of the carotid bifurcation in CTA

“…For the wall segmentation a gray level modeling approach with a KNN classifier using intensity profiles sampled along the surface normal was used. The active shape model (ASM) based method by De Bruijne et al [6], [7] also addressed aortic aneurysm segmentation. This method requires a manual delineation of the aneurysm in the first slice after which the contour propagates to the adjacent slices based on grey value similarity.…”