The extraction of the coronary artery central lumen lines from CTA datasets is a necessary prerequisite for the computerized assessment of heart related disease. In this work, we present an automatic approach for this task that consists of generic methods for detection of tubular objects, extraction of their centerlines, grouping of the single centerlines into complete tree structures, and some application specific adaptions for the identification of the coronary arteries. The tube detection approach is based on the Gradient Vector Flow and an analysis of the resulting vector field. Contrary to conventional tube detection filters this approach avoids multi-scale analysis with related scale space problems and is able to identify tubular objects surrounded by different tissues such as blood vessels in proximity of calcifications. After identification of the tubular structures their centerlines are extracted and grouped into complete tree structures. Based on gray value information and centerline length tubular structures not belonging to the coronary arteries are removed. The approach has been evaluated on 16 clinical datasets showing a high overlap of 94% with known reference centerlines and an average distance of 0.58mm.

Edge Based Tube Detection for Coronary Artery Centerline Extraction

We present a new method for the simultaneous, nearly automatic segmentation of liver contours, vessels,
and tumors from abdominal CTA scans. The method repeatedly applies multi-resolution, multi-class
smoothed Bayesian classification followed by morphological adjustment and active contours refinement.
It uses multi-class and voxel neighborhood information to compute an accurate intensity distribution
function for each class. Only one user-defined voxel seed for the liver and additional seeds according
to the number of tumors inside the liver are required for initialization. The algorithm do not require
manual adjustment of internal parameters. In this work, a retrospective study on a validated clinical
dataset totaling 20 tumors from 9 patients CTAs� was performed. An aggregated competition score of
61 was obtained on the test set of this database. In addition we measured the robustness of our algorithm
to different seeds initializations. These results suggest that our method is clinically applicable, accurate,
efficient, and robust to seed selection compared to manually generated ground truth segmentation and to
other semi-automatic segmentation methods.

An iterative Bayesian approach for liver analysis: tumors validation study

We propose an algorithm for tracking blood vessel segments in Computed Tomographic (CT) images.
Our procedure first finds core points that tend to concentrate along the centerlines of vessels. Intuitively,
the core points are centers of intensity plateaus in two-dimensional slices through the input image. The
starting and the end point of the desired vessel (S and E) are also considered core points. The weighted
core graph is built by connecting nearby core points with edges. Edge weights are designed so that edges
of large weights are unlikely to follow a vessel segment. We compute the shortest path connecting S and
E in the core graph. The output is the result of applying shortcutting operations to this path.

Vessel tracking by connecting the dots

In this paper a specific method is presented to facilitate the semi-automatic segmentation of liver metastases in CT images. Accurate and reliable segmentation of tumors is e.g. essential for the follow-up of cancer treatment. The core of the algorithm is a level set function. The initialization is provided by a spiral-scanning technique based on dynamic programming. The level set evolves according to a speed image that is the result of a statistical pixel classification algorithm with supervised learning. This method is tested on CT images of the abdomen and compared with manual delineations of liver tumors.

Segmentation of Liver Metastases Using a Level Set Method with Spiral-Scanning Technique and Supervised Fuzzy Pixel Classification

The Definiens Cognition Network Technology is applied to detect automatically tumors in a human liver. On the basis of a test data set containing ten tumors we show first quantitative results which are compared to manual segmentations provided by medical experts.

Cognition Network Technology for a Fully Automated 3D Segmentation of Liver Tumors

This document describes a user-steered method to interactively track centerlines of tubular objects in 3D space. The method is developed as a plug-in of ImageJ using Java language. To evaluate the tracking ability and tracking accuracy, this method has been applied to coronary artery tracking in coronary CT angiography data. Its potential as a user-steered 3D centerline tracking tool has been discussed as well as its limitations and possible improvements.

3D Interactive Centerline Extraction

This article presents an algorithm for the segmentation of liver metastases in CT scans. It is a hybrid method that combines adaptive thresholding based on a gray value analysis of the ROI with model-based morphological processing. We show the results of the MICCAI liver tumor segmentation competition 2008 which were successful for all ten tumors.

Segmentation of Liver Metastases in CT Scans by Adaptive Thresholding and Morphological Processing

Automatic tracking of coronary arteries in Computed Tomography Angiography (CTA) is a challenging task. To accomplish it we propose a method consisting of two main steps: (1) A 3D model of the heart is matched for detecting the approximate position of the heart. Based on this information candidates for origins of coronary arteries are calculated. (2) Fitting of cylindrical sampling patterns is performed for extracting the vessel tree of coronary arteries. Branching and termination are handled by depth-first search and noise level estimation respectively. Results show that -- compared to human intra-observer variations -- the presented method performs worse for accuracy measures (on average 39.4 scores), but slightly better for overlap measures (on average 51.5 scores).

Shape and Appearance Models for Automatic Coronary Artery Tracking

We present a method for tracking a coronary artery centerline given a single user supplied distal endpoint. Briefly, we first isolate the aorta and compute its surface. Next, we apply a novel two-stage Hough-like election scheme to the image volume to detect points which exhibit axial symmetry (vessel centerpoints). From the axial symmetry image a graph is constructed. This graph is searched for the optimal path from the user supplied point to any point on the surface of the aorta. Our technique falls under Challenge 2 of the Coronary Artery Tracking Challenge.

Coronary Artery Centerline Tracking Using Axial Symmetries

Liver tumour segmentation from computed tomography (CT) scans is a challenging task. A semi-automatic method based on 2D region growing with knowledge-based constraints is proposed to segment lesions from constituent 2D slices obtained from 3D CT images. Minimal user involvement is required to define an approximate region of interest around the suspected legion area. The seed point and feature vectors are then calculated and voxels are labeled using a region-growing approach. Knowledge-based constraints are incorporated into the method to ensure the size and shape of the segmented region is within acceptable parameters. The individual segmented lesions can then be stacked together to generate a 3D volume. The proposed method was tested on a training set of 10 tumours and a testing set of 10 tumours. To evaluate the results quantitatively, various measures were used to generate scores. Based on the results obtained from the 10 testing tumours, the method was resulted in an average score of 64.