Left ventricular segmentation based on a parallel watershed transformation towards an accurate heart function evaluation

Abstract

Magnetic Resonance Imaging (MRI) has emerged as the golden reference for cardiac examination. This modality allows the assessment of human cardiovascular morphology, functioning, and perfusion. Although a couple of challenging issues, such as the cardiac MR image's features and the large variability of images among several patients, still influences the cardiac cavities' segmentation and needs to be carried out. In this paper, we have profoundly reviewed and fully compared semi-automated segmentation methods performed on cardiac Cine-MR short-axis images for the evaluation of the left ventricular functions. However, the number of parameters handled by the synthesized works is limited if not null. For the sake of ensuring the highest coverage of the LV parameters computing, we have introduced a parallel watershedbased approach to segment the left ventricular allowing hence the computation of six parameters (End-Diastolic Volume, End-Systolic Volume, Ejection Fraction, Cardiac output, Stroke Volume and Left Ventricular Mass). An algorithm is associated with main considered measurements. The experimental results that were obtained through studying twenty patients' MRI data base, demonstrate the accuracy of our approach for estimating real values of the maximal set of parameters thanks to a faithful segmentation of the myocardium.

Ventricular segmentation and modeling using topological watershed transformation and harmonic state model

“…Finally, an analysis stage which leads to the determination of the healthy or pathological character of the cardiac function under study. The work of several research groups gave rise to various publications concerning the analysis of marked MRI images [7], [19]- [21]. To contribute to a better understanding of these works, we will start with the concept of active contour [22] which was developed as a deformable curve in an attempt to get as close as possible to the contours of an image which helps locate and/or follow their movement over time.…”

“…The work of several research groups gave rise to various publications concerning the analysis of marked MRI images. 8,[19][20][21] To contribute to a better understanding of these works, we will start with the concept of active contour 22 which was developed as a deformable curve in an attempt to get as close as possible to the contours of an image which helps locate and/or follow their movement over time. These active contours are used in many applications such as locating vessels in angiograms and tracking heart movement.…”

“…In this part we will deal with region-based segmentation, also called similarity-based segmentation which consists of converting an input image into a gray image to perform segmentation using morphological operations. The Watershed Algorithm [27][28][29] is indeed an important morphological technique. Based on this algorithm, the image is visualized on the topographic surface and the gray levels of a pixel are interpreted by its altitude.…”

“…Figure 1 illustrates these cavities according to the short and long axis sections. The analysis and the quantitative assessment of the cardiac functions such as ejection fraction (EF) and myocardial mass (MM), as well as cardiac mass (CM), are frequently asked in clinical workflow [5]- [7]. In fact, MRI in cine mode is the most used acquisition in clinical routine because it allows continuous observation of cardiac kinetics.…”

“…The analysis and the quantitative assessment of the cardiac functions such as ejection fraction (EF) and myocardial mass (MM), as well as cardiac mass (CM), are frequently asked in clinical workflow. [6][7][8] In fact, MRI in cine mode is the most used acquisition in clinical routine because it allows continuous observation of cardiac kinetics. The magnetic resonnace imaging (MRI) sequences performed provide both a 2D and 3D visualization.…”