Towards automatic full heart segmentation in computed-tomography images

Abstract

We present a robust, fast and fully automatic approach enabling the segmentation of the main anatomical structures of the heart in CT images. The proposed method is based on the adaptation of a 3D triangulated mesh to new unknown images exploiting simultaneously knowledge of organ shape and typical gray level appearance in images, both learned from a training database made of 28 data sets. The described approach was tested on more than 50 volume images at different cardiac phases. Visual inspection by experts reveals that the proposed method is overall robust and succeeds in segmenting the heart up to minor interactive local corrections. IntroductionAutomatic segmentation plays a central role when inspecting reconstructed 3D cardiac images (e.g. from CT or MR scanners) [1]. An accurate classification of the different cardiac regions is usually the first step of subsequent tasks like: Visualization, coronary artery inspection, measurement of the ejection fraction for the left and right ventricles, wall motion analysis, intervention planning (e.g. for electro-physiology treatment).Because a significant amount of information about global functional analysis is delivered by the left ventricle, much work has been dedicated in extracting this structure from medical images. However, volumetric images acquired by emerging imaging techniques like e.g. multislice CT offer much more information, motivating the need for methods that are able to segment the other anatomical structures of the cardiac region.In this paper, we present a model-based approach capable of extracting the main anatomical structures of the heart. Unlike other works on model-based segmentation, we also concentrated our efforts in procedures enabling the initialization of the model without any click required from the user.During the training phase, typical boundary appearances are learned from representative images. This allows a very robust boundary detection when segmenting new unknown images. Moreover, although we adapt a single mesh, special attention has been paid in allowing each anatomical part of the model to be free to globally deform in an independent fashion. 2.Shape-constrained deformable models frameworkDeformable models have been widely used for the segmentation of medical images [2]. However, they might have too much flexibility when adapting towards the organ of interest and be sensitive to image artifacts. Using a priori information about shape variability to constrain the deformation flexibility has been recognized to improve the robustness of the segmentation process [3]. In this paper, we will use the approach introduced in [4], which constrains the model to remain close to the trained shape while allowing local non-learned deformations to account for the individuality of each patient.The input of the shape-constrained deformable model approach is a mesh with vertices v j (j = 0...V ) connected in T triangles. The mesh is adapted to a new image minimizing an energy function, which is usually made of two contributions. The fir...

Automatic LV volume measurement in low dose multi-phase CT by shape tracking

“…the initial phase image has to be replaced by a fully automatic method. 22 The overall results show, that the new automatic tracking method is able to replace the semi-automatic short axis method with a good correlation of results in the assessment of left ventricular function from retrospective ECG-gated cardiac multi-slice computed tomography image series.…”

“…A sparse sampling by ray-casting has been proposed in 21 and was successfully used to quickly determine the human heart centre. 22 Also an affine pre-registration by a set of anatomical landmarks is suitable, 23, 24 but requires manual or automatic localization of these landmarks. We decided in order for the shape tracking method to have an optimal and approved initialization to semi-automatically adapt the model to the initial end-diastolic phase image.…”

Generation of a cardiac shape model from CT Data

“…The surfaces may be also automatically deformed to fit the respective image boundaries. The application of the surface model for fully automatic cardiac analysis is currently employed [4]. In addition to the end-diastolic shape model, a mean cardiac motion model was created on the basis of 11 multi-phase data sets.…”

Using anatomical knowledge expressed as fuzzy constraints to segment the heart in CT images

“…However, there is also a need to segment the heart as a whole in order to distinguish its limits and the separations with surrounding structures such as the liver or the aorta. The existing methods for segmenting the heart have been focused on MRI modality [5,[7][8][9][10][11] or ultrasound [6,12] but rarely on CT [13][14][15][16]. However, for the aforementioned applications, CT is one of the most common anatomical imaging modalities.…”

“…The work by Ecabert et al [15,16] describes a multi-compartment mesh of both atria, both ventricles, the myocardium around the left ventricle and the trunks of the great vessels and it is adapted to an image volume. The adaptation is performed in a coarse-to-fine manner by progressively relaxing constraints on the degrees of freedom of the allowed deformations.…”