In this paper, we present a fast and interactive graph cut method for 3D segmentation of the endocardial wall of the left ventricle (LV) given 3D echocardiographic images. This is a challenging task due to the poor contrast and the low signal-to-noise ratio typical of echocardiographic images. The method is carried out in 3 steps. First, 3D sampling of the LV cavity is made in a spherical-cylindrical coordinate system. Then, a gradient-based energy term is assigned to each voxel, some of which being given an infinite energy to make sure the resulting volume passes through key anatomical points. Then, a graph-cut procedure provides delineation of the endocardial surface. Results obtained on 30 exams from the 2014 CETUS MICCAI challenge dataset reveal that our method takes between 5 and 10 seconds to segment a 3D volume with an overall mean surface distance lower than 2.3 mm and an ejection fraction error of less than 5% compared to a manual tracing by an expert.

Automatized Evaluation of the Left Ventricular Ejection Fraction from Echocardiographic Images Using Graph Cut

Segmentation of the left ventricle endocardium in 3D echocardiography is a critical step for the diagnosis of heart disease. Although recent work has shown effective endocardial edge detection, these techniques still preserve spurious anatomical edge responses that undermine overall ventricle segmentation. In this paper we propose a robust semiautomatic framework based on 2D structured learning that facilitates full 3D model-based endocardial segmentation. This method is evaluated on 30 publicly available datasets from different brands of ultrasound machines. Results show that the proposed method accurately finds the endocardium and effectively converges an explicit and continuous surface model to it.

Endocardial Segmentation using Structured Random Forests in 3D Echocardiography

In this paper, we present the use of a generic image segmentation method, namely a succession of Random Forest classifiers in an autocontext framework, for the MICCAI 2014 Challenge on Endocardial 3D Ultrasound Segmentation (CETUS). The proposed method segments each frame independently in 90 sec, without requiring temporal information such as end-diastolic or end-systolic time points nor any registration. For better segmentation accuracy, non-local means denoising can be applied to the images at the cost of an increased run-time. The mean Dice score on the testing dataset was 84.4% without denoising and 86.4% with denoising. The originality of our approach lies in the introduction of two classes, the myocardium and the mitral valve, in addition to the left ventricle and the background classes, in order to gain contextual information for the segmentation task.

Endocardial 3D Ultrasound Segmentation using Autocontext Random Forests

We propose a learning based approach to perform automatic segmentation of the left ventricle in 3D cardiac ultrasound images. The segmentation contour is estimated through the use of a variant of Hough forests whose object localization capabilities are coupled with a patch-wise, appearance driven, contour estimation strategy. The performance of the proposed method is evaluated on a dataset of 30 images acquired
from 15 patients using different equipment and settings.

Left Ventricle Segmentation in Cardiac Ultrasound Using Hough-Forests With Implicit Shape and Appearance Priors

As part of the CETUS challenge, we present a multi-atlas segmentation framework to delineate the left-ventricle endocardium in echocardiographic images. To increase the robustness of the registration step, we introduce a speckle reduction step and a new shape representation based on sparse coding and manifold approximation in dictionary
space. The shape representation, unlike intensity values, provides consistent shape information across different images. The validation results on the test set show that registration based on our shape representation significantly improves the performance of multi-atlas segmentation compared to intensity based registration. To our knowledge it is the first time that multi-atlas segmentation achieves state-of-the-art results for echocardiographic images.

Learning Shape Representations for Multi-Atlas Endocardium Segmentation in 3D Echo Images

A method for real-time automatic tracking of the left ventricle (LV) in 3D ultrasound is presented. A mesh model of the LV is deformed using mean value coordinates enabling large variations. Kalman filtering and edge detection is used to track the mesh in each frame. The method is evaluated using the framework of the Challenge on Endocardial Three-dimensional Ultrasound Segmentation (CETUS). The results show that the method is able to robustly track the LV in all sequences with a mean mesh difference of about 2.5 mm

Real-time Tracking of the Left Ventricle in 3D Ultrasound Using Kalman Filter and Mean Value Coordinates

Segmentation of 3D echocardiograms (3DEs) is still a challenging task due to the low signal-to-noise ratio, the limited field of view, and typical ultrasound artifacts. We propose to segment the left ventricular endocardial surface by using Active Appearance Models (AAMs). Separate end-diastolic (ED) and end-systolic (ES) AAMs were built from presegmented 3DEs of the CETUS training data and 25 previously acquired 3DEs, imaged using various 3DE equipment. The AAMs fully automatically segmented the 15 training sets in a leave-one-out cross validation, comparing two training populations and various initialization strategies. All segmentations took about 15 seconds per patient. The comparison on the CETUS training data shows that the AAM benefits from additional training data and more accurate initialization. The results on the CETUS training and testing data confirm good ED and ES segmentation accuracy on multi-center, multi-vendor, multi-pathology data, and corresponding EF estimation. Selection from different initialization strategies, based on the minimal residual error, and propagation of detected ED contours to initialize ES detection, contributed to more accurate segmentations in this heterogeneous population.

Segmentation of Multi-Center 3D Left Ventricular Echocardiograms by Active Appearance Models

In this paper, we propose a semi-automatic method for left ventricle segmentation. The proposed method utilizes a multi-scale quadrature filter method to enhance the 3D volume, followed by a model-based level set method to segment the endocardial surface of the left ventricle. The phase map from the quadrature filters is also used to weight the influence of contour points when updating the statistical model.

Model-based left ventricle segmentation in 3D ultrasound using phase image

Malignant gliomas are highly heterogeneous brain tumors with complex an-
isotropic growth patterns and occult invasion. Computational modeling of cell migration and proliferation has been subject of intensive research aiming at a deeper understanding of the tumor biology and the ability to predict growth and thus improve therapy. However, current modeling techniques follow a generative approach and make strong assumptions about underlying mechanisms. The tumor is so far treated as homogeneous entity with behavioral parameters extrapolated from previous longitudinal image information.
We present a novel way of approaching this problem by employing data driven, discrim-
inative modeling techniques that learn relevant features from observed growth patterns and are able to make meaningful predictions solely on basis of local and regional tissue characteristics at one given point in time.
We demonstrate superior performance of the proposed discriminative method (DICE score
83) compared to the state of the art generative approach (DICE score 72) on six patients and a total of nine different time intervals. Our approach can help estimating occult invasion as well as it can advance our understanding of the tumor biology and lead to valuable predictions of tumor growth patterns that could guide and improve radio therapy.

Brain Tumor Progression Modeling - A Data Driven Approach

In radiation treatment (RT) planning medical doctors need to consider a variety of information sources for anatomical and functional target volume delineation. The validation and inspection of the defined target volumes and the resulting RT plan is a complex task, especially in the presence of moving target areas as it is the case for tumors of the chest and the upper abdomen. A 4D-PET/CT visualization system may become a helpful tool for validating RT plans. We define major requirements such a visualization system should fulfill to provide medical doctors with the necessary visual information to validate tumor delineations, and review the dose distribution of a RT plan. We present an implementation of such a system, and present qualitative results of its applications for a lung cancer patient.