Multi-atlas cardiac PET segmentation

Abstract

We propose a multi-atlas based segmentation method for cardiac PET and SPECT images to deal with the high variability of tracer uptake characteristics in myocardium. In addition, we verify its performance by comparing it to the manual segmentation and single-atlas based approach, using dynamic myocardial PET. Methods: Twelve left coronary artery ligated SD rats underwent ([ 18 F]fluoropentyl) triphenylphosphonium salt PET/CT scans. Atlas-based segmentation is based on the spatial normalized template with pre-defined region-ofinterest (ROI) for each anatomical or functional structure. To generate multiple left ventricular (LV) atlases, each LV image was segmented manually and divided into angular segments. The segmentation methods performances were compared in regional count information using leave-one-out cross-validation. Additionally, the polar-maps of kinetic parameters were estimated. Results: In all images, the highest r 2 template yielded the lowest root-mean-square error (RMSE) between the source image and the best-matching templates ranged between 0.91-0.97 and 0.06-0.11, respectively. The single-atlas and multi-atlas based ROIs yielded remarkably different perfusion distributions: only the multi-atlas based segmentation showed equivalent high correlation results (r 2 = 0.92) with the manual segmentation compared with the single-atlas based (r 2 = 0.88). The high perfusion value underestimation was remarkable in single-atlas based segmentation. Conclusions: The main advantage of the proposed multi-atlas based cardiac segmentation method is that it does not require any prior information on the tracer distribution to be incorporated into the image segmentation algorithms. Therefore, the same procedure suggested here is applicable to any other cardiac PET or SPECT imaging agents without modification.

Evaluation of the active contour and topographic watershed segmentation “assessment of the systolic ejection fraction in the left ventricular for medical assistance in 5D short axis cine MRI”

“…In the formulation of sets of levels, a Heaviside function is used to specify the interior and exterior of C [ 32 ]. The following approximation of the Heaviside function Ң ɸ (x) specifies the interior of C:ɸ(x)

Figure 2 Illustration of the CA evolution process towards the contours of the object of interest [ 21 ].

…”

The role of atlases and multi-atlases in brain tissue segmentation based on multispectral magnetic resonance image data

“…Atlases have many recent applications in medical image segmentation, involving organs like: lung [1], pancreas [2], prostate [3], bones [4], cartilage [5], brain tissues and lesions [6], [7], [8], [9], cardiac structures (e.g. myocardium) [10], [11], and multiple abdominal organs [12]. Atlases are involved in the processing of image data collected through various imaging modalities, including magnetic resonance imaging (MRI) [3], [6], [7], computed tomography (CT) [1], [4], CT angiography [10], positron emission tomography (PET) [11], X-ray [13] and mammography [14].…”

“…myocardium) [10], [11], and multiple abdominal organs [12]. Atlases are involved in the processing of image data collected through various imaging modalities, including magnetic resonance imaging (MRI) [3], [6], [7], computed tomography (CT) [1], [4], CT angiography [10], positron emission tomography (PET) [11], X-ray [13] and mammography [14]. For further information on atlas-based image segmentation techniques, there are available systematic review papers (e.g.…”

Brain Tumor Segmentation from MRI Data Using Ensemble Learning and Multi-Atlas

“…Atlases have recently been involved in several medical imaging problems, including the segmentation of brain tissues and lesions [1], [2], [3], prostate [4], lung [5], cardiac structures (e.g. myocardium) [6], [7], pancreas [8], [9], bones [10], cartilage [11], and multiple abdominal organ [12]. Atlases are used in segmentation problems based on image data originating from virtually all imaging modalities, including magnetic resonance images (MRI) [1], [2], [4], computed tomography (CT) [5], [9], [10], CT angiography [6], positron emission tomography (PET) [7], X-ray [13] and mammography [14].…”

“…myocardium) [6], [7], pancreas [8], [9], bones [10], cartilage [11], and multiple abdominal organ [12]. Atlases are used in segmentation problems based on image data originating from virtually all imaging modalities, including magnetic resonance images (MRI) [1], [2], [4], computed tomography (CT) [5], [9], [10], CT angiography [6], positron emission tomography (PET) [7], X-ray [13] and mammography [14]. A systematic review of earlier image segmentation solutions based on atlases and multi-atlases is given by Cabezas et al [15].…”