This paper describes an ensemble segmentation trained by the AdaBoost algorithm, which finds a sequence of weak hypotheses, each of which is appropriate for the distribution on training example, and combines the weak hypotheses by a weighted majority vote. In our study, a weak hypothesis corresponds to a weak segmentation process. This paper shows a procedure for generating an ensemble segmentation algorithm using AdaBoost, and applies it to a liver lesion extraction problem from a contrast enhanced abdominal CT volume. A leave-one-patient-out validation test using 16 CT volumes demonstrated the effectiveness of the generated ensemble segmentation algorithm. In addition, we evaluated the performance by applying the algorithm to unknown test data provided by the �3D Liver Tumor Segmentation Challenge 2008�.

Ensemble segmentation using AdaBoost with application to liver lesion extraction from a CT volume

In this paper, we present an automatic method for extracting center axis representations (centerlines) 
of coronary arteries in contrast enhanced (CE)-CT angiography scans. 
The algorithm first detects the aorta which is used as an initial mask for ostia
detection~cite{grady2006:fast}. Second, the ostia locations are detected via a vessel centerline extraction method~cite{Gulsun:Tek:008} which
tracks the center axis of the coronaries starting from the aorta surface. The full centerline tree of the coronary arteries are
computed via the multi-scale medialness-based vessel tree extraction algorithm which starts a tracking process from
the ostia locations until all the braches are reached. The centerline extraction algorithm is a 
graph-based optimization algorithm using multi-scale medialness filters.

Automatic Coronary Tree Modeling

A method for automatic liver tumor segmentation from computer tomography (CT) images is presented in this paper. Segmentation is an important operation before surgery planning, and automatic methods offer an alternative to laborious manual segmentation. In addition, segmentations of automatic methods are reproducible, so they can be reliably evaluated and they do not depend on the performer of the segmentation. In this work, the segmentation is performed in two stages. First a rough segmentation of tumors is obtained by simple thresholding and morphological operations. 
The second stage refines the rough segmentation result using fuzzy clustering and a geometric deformable model (GDM) that is fitted on the clustering result. 
The method was evaluated with data provided by Liver Tumor Segmentation Challenge 08, to which the method also participated. The data included 10 
images from which 20 tumors were segmented. The method showed promising results.

Liver Tumor Segmentation Using Implicit Surface Evolution

This paper presents a local feature vector based method for automated Multiple Sclerosis (MS) lesion segmentation of multi spectral MRI data. Twenty datasets from MS patients with FLAIR, T1,T2, MD and FA data with expert annotations are available as training set from the MICCAI 2008 challenge on MS, and 24 test datasets. Our local feature vector method contains neighbourhood voxel intensities, histogram and MS probability atlas information. Principal Component Analysis(PCA) \cite{PCA} with log-likelihood ratio is used to classify each voxel. MRI suffers from intensity inhomogenities. We try to correct this ''bias field'' with 3 methods: a genetic algorithm, edge preserving filtering and atlas based correction. A large observer variability exist between expert classifications, but the similarity scores between model and expert classifications are often lower. Our model gives the best classification results with raw data, because bias correction gives artifacts at the edges and flatten large MS lesions.

Multiple Sclerosis Detection in Multispectral Magnetic Resonance Images with Principal Components Analysis.

This paper presents a new fully automatic method for segmentation of
brain images that possess multiple sclerosis (MS) lesions.
Multichannel magnetic resonance images are used to delineate multiple
sclerosis lesions while segmenting the brain into its major
structures. The method is an atlas based segmentation
technique employing a topological atlas as well as a statistical
atlas. An advantage of this approach is that all segmented structures
are topologically constrained, thereby allowing subsequent processing
with cortical unfolding or diffeomorphic shape analysis techniques.
Validation on data from two studies demonstrates that the method has
an accuracy comparable with other MS lesion segmentation methods,
while simultaneously segmenting the whole brain.

Multiple Sclerosis Lesion Segmentation Using Statistical and Topological Atlases

A fully automatic workflow for Multiple Sclerosis (MS) lesion segmentation is described. Fully automatic means that no user interaction is performed in any of the steps and that all parameters are fixed for all the images processed in beforehand. Our workflow is composed of three steps: an intensity inhomogeneity (IIH) correction, skull-stripping and MS lesions segmentation. A validation comparing our results with two experts is done on MS MRI datasets of 24 MS patients from two different sites.

A robust Expectation-Maximization algorithm for Multiple Sclerosis lesion segmentation

Liver tumors segmentation is an important prerequisite for planning of surgical interventions.
For clinical applicability, the segmentation approach must be able to cope with
the high variation in shape and gray-value appearance of the liver. We present a fully
automatic 3D segmentation method for the liver tumors from contrast-enhanced CT data.
The method consists of two main stages.
First an initial histogram and statistical distribution functions are created, and from
them a new image is created where, in each voxel, a weighted function is attached in accordance
with the probability of the voxel grey level. Next, we use the active contour method
on the new image, where the active contour evolution is based upon the minimization of
variances between the liver tumor and its closest neighborhood.

Liver Tumor segmentation in CT images using probabilistic

Automatically segmenting subcortical structures in brain images has the potential to greatly accelerate drug trials and population studies of disease. Here we propose an automatic subcortical segmentation algorithm using the auto context model. Unlike many segmentation algorithms that separately compute a shape prior and an image appearance model, we develop a framework based on machine learning to learn a unified appearance and context model. In order to test the method, specificity and sensitivity measurements were obtained on a standardized dataset provided by the competition organizers. Our overall score of 77 seems to be competitive with others who's overall score was in the range of 50 - 90.

Automatic Segmentation of MS Lesions Using a Contextual Model for the MICCAI Grand Challenge

This paper proposes a new method for fully automated multiple sclerosis (MS) lesion segmentation in cranial magnetic resonance (MR) imaging. The algorithm uses the T1-weighted and the fluid attenuation inversion recovery scans. It is based the K-Nearest Neighbor (KNN) classification technique. The data has been acquired at the Children�s Hospital Boston (CHB) and the University of North Carolina (UNC). Manual segmentations, composed by a human expert of the CHB, were used for training of the KNN-classification. The method uses voxel location and signal intensity information for determination of the probability being a lesion per voxel, thus generating probabilistic segmentation images. By applying a threshold on the probabilistic images binary segmentations are derived. Automatic segmentations were performed on a set of testing images, and compared with manual segmentations from a CHB and a UNC expert rater. Furthermore, a combined segmentation was composed from segmentations from different algorithms, and used for evaluation. The proposed method shows good resemblance with the segmentations of the CHB rater. High specificity and lower specificity has been observed in comparison with the combined segmentations. Over- and undersegmentation can be easily corrected in this procedure by varying the threshold on the probabilistic segmentation image. The proposed method offers an automated and fully reproducible approach that accurate and applicable on standard clinical MR images.

Automated MS-Lesion Segmentation by K-Nearest Neighbor Classification

This document examines the application of a new parametric method on the segmentation of MS 
lesions in brain sMRI, as applied to the data provided for the MS Lesion Segmentation Challenge at 
MICCAI 2008. The method uses the vector image joint histogram, built over a training set, as an explicit 
model of the feature vectors indicating lesion. The histogram is used to predict lesions in the test data by 
labeling feature vectors consistent with lesion feature vectors in the training set. The results are evaluated 
using STAPLE to compare against two separate human raters.