Robust pore size analysis of filamentous networks from three-dimensional confocal microscopy

We describe a robust method for determining morphological properties of filamentous biopolymer networks, such as collagen or other connective tissue matrices, from confocal microscopy image stacks. Morphological properties including pore size distributions and percolation thresholds are important for transport processes, e.g., particle diffusion or cell migration through the extracellular matrix. The method is applied to fluorescently labeled fiber networks prepared from rat-tail tendon and calf-skin collagen, at concentrations of 1.2, 1.6, and 2.4 mg/ml. The collagen fibers form an entangled and branched network. The medial axes, or skeletons, representing the collagen fibers are extracted from the image stack by threshold intensity segmentation and distance-ordered homotopic thinning. The size of the fluid pores as defined by the radii of largest spheres that fit into the cavities between the collagen fibers is derived from Euclidean distance maps and maximal covering radius transforms of the fluid phase. The size of the largest sphere that can traverse the fluid phase between the collagen fibers across the entire probe, called the percolation threshold, was computed for both horizontal and vertical directions. We demonstrate that by representing the fibers as the medial axis the derived morphological network properties are both robust against changes of the value of the segmentation threshold intensity and robust to problems associated with the point-spread function of the imaging system. We also provide empirical support for a recent claim that the percolation threshold of a fiber network is close to the fiber diameter for which the Euler index of the networks becomes zero.     

调控骨骼肌纤维类型转化的信号通路

骨骼肌由异质性的肌纤维组成,不同类型的肌纤维具有不同的形态、代谢、生理和生化特性.根据不同肌纤维中表达的特异肌球蛋白重链亚型可将成体哺乳动物骨骼肌纤维分为4类,即Ⅰ,Ⅱa,Ⅱx和Ⅱb型.骨骼肌保持高度可塑性,当机体受到某些生理或病理刺激时,骨骼肌为了适应需要,通过激活胞内相关信号通路改变肌纤维特异基因的表达从而诱发肌纤维类型的转化.本文综述了细胞内参与调控肌纤维类型转化的多条重要信号通路,如Ca2+信号通路,Ras/MAPK信号通路及多种转录调节因子,辅激活因子和抑制子等,为改善肉类品质,提高运动训练效果及治疗肌肉相关疾病奠定了理论基础.     

Contrast-Based Fully Automatic Segmentation of White Matter Hyperintensities: Method and Validation

White matter hyperintensities (WMH) on T2 or FLAIR sequences have been commonly observed on MR images of elderly people. They have been associated with various disorders and have been shown to be a strong risk factor for stroke and dementia. WMH studies usually required visual evaluation of WMH load or time-consuming manual delineation. This paper introduced WHASA (White matter Hyperintensities Automated Segmentation Algorithm), a new method for automatically segmenting WMH from FLAIR and T1 images in multicentre studies. Contrary to previous approaches that were based on intensities, this method relied on contrast: non linear diffusion filtering alternated with watershed segmentation to obtain piecewise constant images with increased contrast between WMH and surroundings tissues. WMH were then selected based on subject dependant automatically computed threshold and anatomical information. WHASA was evaluated on 67 patients from two studies, acquired on six different MRI scanners and displaying a wide range of lesion load. Accuracy of the segmentation was assessed through volume and spatial agreement measures with respect to manual segmentation; an intraclass correlation coefficient (ICC) of 0.96 and a mean similarity index (SI) of 0.72 were obtained. WHASA was compared to four other approaches: Freesurfer and a thresholding approach as unsupervised methods; k-nearest neighbours (kNN) and support vector machines (SVM) as supervised ones. For these latter, influence of the training set was also investigated. WHASA clearly outperformed both unsupervised methods, while performing at least as good as supervised approaches (ICC range: 0.87–0.91 for kNN; 0.89–0.94 for SVM. Mean SI: 0.63–0.71 for kNN, 0.67–0.72 for SVM), and did not need any training set.     

Terrestrial laser scanner based 3D reconstruction of trees and retrieval of leaf area index in a forest environment

Three-dimensional reconstruction of trees and the estimation of biophysical parameters is significant for the management of forest resources, ecological studies carbon cycle and biodiversity. Terrestrial LiDAR data provides detailed, objective and three-dimensional measurement of forest structure and exact metrics of the tree canopies. Several methods for tree detection including canopy height models and raster interpolation models are based on commercial software and huge data processing. The objective of the given study is the three-dimensional reconstruction of trees by implementing segmentation algorithms and thereby estimating the Leaf Area Index of individual tree segments by terrestrial laser scanned data in the Mudumalai forests of Western Ghats, India. The hierarchical minimum cut segmentation method is used for the three-dimensional reconstruction of the individual trees by tracking cylinders along individual branches and trees in a hierarchical order. Super voxel clustering method is also implemented in the study for tree reconstruction and estimating the tree parameters. Leaf area index is calculated by applying a multivariate regression technique for the heights and the diameter obtained from both the segmentation methods. Results obtained indicated a strong correlation with the in-situ measurements which are obtained from the instruments. The approach addresses the applicability of segmentation algorithms which can be run fully automatically. The approach successfully reconstructed a high precision and realistic model of trees in the Western Ghats region which failed in the case of traditional tree modeling methods which requires multiple instruments operating simultaneously for extracting each parameter. The method proved that using TLS; multiple forest parameters can be estimated simultaneously.     

Mechanical load-dependent regulation of satellite cell and fiber size in rat soleus muscle

The effects of mechanical unloading and reloading on the properties of rat soleus muscle fibers were investigated in male Wistar Hannover rats. Satellite cells in the fibers of control rats were distributed evenly throughout the fiber length. After 16 days of hindlimb unloading, the number of satellite cells in the central, but not the proximal or distal, region of the fiber was decreased. The number of satellite cells in the central region gradually increased during the 16-day period of reloading. The mean sarcomere length in the central region of the fibers was passively shortened during unloading due to the plantarflexed position at the ankle joint: sarcomere length was maintained at <2.1 µm, which is a critical length for tension development. Myonuclear number and domain size, fiber cross-sectional area, and the total number of mitotically active and quiescent satellite cells of whole muscle fibers were lower than control fibers after 16 days of unloading. These values then returned to control values after 16 days of reloading. These results suggest that satellite cells play an important role in the regulation of muscle fiber properties. The data also indicate that the satellite cell-related regulation of muscle fiber properties is dependent on the level of mechanical loading, which, in turn, is influenced by the mean sarcomere length. However, it is still unclear why the region-specific responses, which were obvious in satellite cells, were not induced in myonuclear number and fiber cross-sectional area. sarcomere     

Differential sensitivity to androgens within a sexually dimorphic muscle of male frogs (Xenopus laevis)

Male frogs use their forelimb flexor muscles to clasp females during the mating behavior known as amplexus. We investigated the effects of testosterone on a principal forelimb flexor, the flexor carpi radialis muscle (FCR), using morphological and histochemical techniques. Male Xenopus laevis were surgically manipulated to produce high or low levels of circulating testosterone for an 8-week period. After this treatment, measurement of fibers in muscle cross-sections revealed that average fiber size was positively correlated with testosterone level. This effect was not the same for all muscle fibers, however. Fibers in the shoulder region were more sensitive to testosterone than fibers in other regions of the muscle. Histochemical staining of cross-sections showed that the patterns of staining for myosin ATPase or succinic dehydrogenase (SDH) were not influenced by testosterone levels, but total SDH activity was increased by testosterone treatment. When sensitivity to testosterone was correlated with ATPase activity, fibers with high ATPase activity were found to be more sensitive to testosterone than fibers with low activity, regardless of position within the muscle. Most fibers with high ATPase activity were located in the shoulder region of the muscle. These fibers are innervated by different motor axons than are fibers in the elbow region of the muscle, and contractions of shoulder (but not elbow) region fibers, elicited by stimulation of motor axons, are slowed by testosterone treatment (Regnier and Herrera, 1993, J. Physiol. 461:565–581). © 1993 John Wiley & Sons, Inc.     

Segmentation improvement through denoising of PET images with 3D-context modelling in wavelet domain

Positron emission tomography (PET) images have been incorporated into the radiotherapy process as a powerful tool to assist in the contouring of lesions, leading to the emergence of a broad spectrum of automatic segmentation schemes for PET images (PET-AS). However, not all proposed PET-AS algorithms take into consideration the previous steps of image preparation. PET image noise has been shown to be one of the most relevant affecting factors in segmentation tasks. This study demonstrates a nonlinear filtering method based on spatially adaptive wavelet shrinkage using three-dimensional context modelling that considers the correlation of each voxel with its neighbours. Using this noise reduction method, excellent edge conservation properties are obtained. To evaluate the influence in the segmentation schemes of this filter, it was compared with a set of Gaussian filters (the most conventional) and with two previously optimised edge-preserving filters. Five segmentation schemes were used (most commonly implemented in commercial software): fixed thresholding, adaptive thresholding, watershed, adaptive region growing and affinity propagation clustering. Segmentation results were evaluated using the Dice similarity coefficient and classification error. A simple metric was also included to improve the characterisation of the filters used for induced blurring evaluation, based on the measurement of the average edge width. The proposed noise reduction procedure improves the results of segmentation throughout the performed settings and was shown to be more stable in low-contrast and high-noise conditions. Thus, the capacity of the segmentation method is reinforced by the denoising plan used.     

Automated Glioblastoma Segmentation Based on a Multiparametric Structured Unsupervised Classification

Automatic brain tumour segmentation has become a key component for the future of brain tumour treatment. Currently, most of brain tumour segmentation approaches arise from the supervised learning standpoint, which requires a labelled training dataset from which to infer the models of the classes. The performance of these models is directly determined by the size and quality of the training corpus, whose retrieval becomes a tedious and time-consuming task. On the other hand, unsupervised approaches avoid these limitations but often do not reach comparable results than the supervised methods. In this sense, we propose an automated unsupervised method for brain tumour segmentation based on anatomical Magnetic Resonance (MR) images. Four unsupervised classification algorithms, grouped by their structured or non-structured condition, were evaluated within our pipeline. Considering the non-structured algorithms, we evaluated K-means, Fuzzy K-means and Gaussian Mixture Model (GMM), whereas as structured classification algorithms we evaluated Gaussian Hidden Markov Random Field (GHMRF). An automated postprocess based on a statistical approach supported by tissue probability maps is proposed to automatically identify the tumour classes after the segmentations. We evaluated our brain tumour segmentation method with the public BRAin Tumor Segmentation (BRATS) 2013 Test and Leaderboard datasets. Our approach based on the GMM model improves the results obtained by most of the supervised methods evaluated with the Leaderboard set and reaches the second position in the ranking. Our variant based on the GHMRF achieves the first position in the Test ranking of the unsupervised approaches and the seventh position in the general Test ranking, which confirms the method as a viable alternative for brain tumour segmentation.     

Strains at the myotendinous junction predicted by a micromechanical model

The goal of this work was to create a finite element micromechanical model of the myotendinous junction (MTJ) to examine how the structure and mechanics of the MTJ affect the local micro-scale strains experienced by muscle fibers. We validated the model through comparisons with histological longitudinal sections of muscles fixed in slack and stretched positions. The model predicted deformations of the A-bands within the fiber near the MTJ that were similar to those measured from the histological sections. We then used the model to predict the dependence of local fiber strains on activation and the mechanical properties of the endomysium. The model predicted that peak micro-scale strains increase with activation and as the compliance of the endomysium decreases. Analysis of the models revealed that, in passive stretch, local fiber strains are governed by the difference of the mechanical properties between the fibers and the endomysium. In active stretch, strain distributions are governed by the difference in cross-sectional area along the length of the tapered region of the fiber near the MTJ. The endomysium provides passive resistance that balances the active forces and prevents the tapered region of the fiber from undergoing excessive strain. These model predictions lead to the following hypotheses: (i) the increased likelihood of injury during active lengthening of muscle fibers may be due to the increase in peak strain with activation and (ii) endomysium may play a role in protecting fibers from injury by reducing the strains within the fiber at the MTJ.     

Muscle fiber size and function in elderly humans: a longitudinal study.

Cross-sectional studies are likely to underestimate age-related changes in skeletal muscle strength and mass. The purpose of this longitudinal study was to assess whole muscle and single muscle fiber alterations in the same cohort of 12 older (mean age: start of study 71.1+/-5.4 yr and end of study 80+/-5.3 yr) volunteers (5 men) evaluated 8.9 yr apart. No significant changes were noted at follow-up in body weight, body mass index, and physical activity. Muscle strength, evaluated using isokinetic dynamometry, and whole muscle specific force of the knee extensors were significantly lower at follow-up. This was accompanied by a significant reduction (5.7%) in cross-sectional area of the total anterior muscle compartment of the thigh as evaluated by computed tomography. Muscle histochemistry showed no significant changes in fiber type distribution or fiber area. Experiments with chemically skinned single muscle fibers (n=411) demonstrated no change in type I fiber size but an increase in IIA fiber diameter. A trend toward an increase in maximal force in both fiber types was observed. Maximum unloaded shortening velocity did not change. In conclusion, single muscle fiber contractile function may be preserved in older humans in the presence of significant alterations at the whole muscle level. This suggests that surviving fibers compensate to partially correct muscle size deficits in an attempt to maintain optimal force-generating capacity.     

Automatic image segmentation of nuclear stained breast tissue sections using color active contour model and an improved watershed method

Automatic image segmentation of immunohistologically stained breast tissue sections helps pathologists to discover the cancer disease earlier. The detection of the real number of cancer nuclei in the image is a very tedious and time consuming task. Segmentation of cancer nuclei, especially touching nuclei, presents many difficulties to separate them by traditional segmentation algorithms. This paper presents a new automatic scheme to perform both classification of breast stained nuclei and segmentation of touching nuclei in order to get the total number of cancer nuclei in each class. Firstly, a modified geometric active contour model is used for multiple contour detection of positive and negative nuclear staining in the microscopic image. Secondly, a touching nuclei method based on watershed algorithm and concave vertex graph is proposed to perform accurate quantification of the different stains. Finally, benign nuclei are identified by their morphological features and they are removed automatically from the segmented image for positive cancer nuclei assessment. The proposed classification and segmentation schemes are tested on two datasets of breast cancer cell images containing different level of malignancy. The experimental results show the superiority of the proposed methods when compared with other existing classification and segmentation methods. On the complete image database, the segmentation accuracy in term of cancer nuclei number is over than 97%, reaching an improvement of 3–4% over earlier methods.     

Growth and metamorphosis of the rectus abdominis muscle in Rana pipiens

Cross sections through the middle segment of the anuran rectus abdominis muscle were analyzed morphometrically at nine stages of development, from early larval life through full maturity. The numbers, sizes, and relative distributions of twitch and slow muscle fibers, newly differentiated fibers, degenerating fibers, and satellite cells were determined at each stage. The data indicate that the muscle increases slowly in size and fiber content during early larval life. New fibers appear to form primarily along the medial margin of the muscle. During mid-larval stages, when thyroid hormone levels are rising, new fibers form throughout the medial portion of the muscle. At a slightly later stage, fibers in the lateral region of the muscle begin to degenerate. Structurally normal presynaptic elements are present on both degenerating fibers and the empty basal laminae of fibers that had been removed by phagocytes. Both fiber formation and fiber loss slow during midmetamorphic climax, at the time when thyroid hormone levels reach a peak in anurans and begin to decline. Degenerating fibers appear within the body of the muscle at the end of metamorphosis. By the end of the second postmetamorphic month, neither degenerating nor newly differentiated fibers are present. The muscle continues to grow through adult life primarily by fiber hypertrophy.     

A Simulation of Human Heart Function

A simulation of the function of the human heart and heart muscle has been developed in the form of a digital computer code. For a given set of values for the input variables, realistic values of the cardiac output variables are predicted. A detailed discussion of the simulation and some results obtained from its application are presented. This simulation represents a unique combination of what was known in muscle mechanics, muscle thermodynamics, and of the structure, size, and shape of the heart, into an engineering model to improve the understanding of human heart muscle function. The left ventricle (LV) is treated as a thick-walled sphere whose wall is composed entirely of muscle fibers. Force-length velocity relationships are used to determine the tension in each fiber. The pressure in the LV is computed from fiber tension and fiber structure in the LV. A lumped-parameter simulation of the arterial tree provides a load impedance for the LV. Results are presented for simulation of normal human LV performance.     

A Sensitive,Reproducible and Objective Immunofluorescence Analysis Method of Dystrophin in Individual Fibers in Samples from Patients with Duchenne Muscular Dystrophy

Duchenne muscular dystrophy (DMD) is characterized by the absence or reduced levels of dystrophin expression on the inner surface of the sarcolemmal membrane of muscle fibers. Clinical development of therapeutic approaches aiming to increase dystrophin levels requires sensitive and reproducible measurement of differences in dystrophin expression in muscle biopsies of treated patients with DMD. This, however, poses a technical challenge due to intra- and inter-donor variance in the occurrence of revertant fibers and low trace dystrophin expression throughout the biopsies. We have developed an immunofluorescence and semi-automated image analysis method that measures the sarcolemmal dystrophin intensity per individual fiber for the entire fiber population in a muscle biopsy. Cross-sections of muscle co-stained for dystrophin and spectrin have been imaged by confocal microscopy, and image analysis was performed using Definiens software. Dystrophin intensity has been measured in the sarcolemmal mask of spectrin for each individual muscle fiber and multiple membrane intensity parameters (mean, maximum, quantiles per fiber) were calculated. A histogram can depict the distribution of dystrophin intensities for the fiber population in the biopsy. This method was tested by measuring dystrophin in DMD, Becker muscular dystrophy, and healthy muscle samples. Analysis of duplicate or quadruplicate sections of DMD biopsies on the same or multiple days, by different operators, or using different antibodies, was shown to be objective and reproducible (inter-assay precision, CV 2–17% and intra-assay precision, CV 2–10%). Moreover, the method was sufficiently sensitive to detect consistently small differences in dystrophin between two biopsies from a patient with DMD before and after treatment with an investigational compound.     

Size and metabolic properties of fibers in rat fast-twitch muscles after hindlimb suspension

Hindlimb suspension (HS) results in whole muscle atrophic and metabolic changes that vary in magnitude in different hindlimb muscles. The present study was designed to investigate these effects in single fibers. Fiber type and size and the activities of two metabolic marker enzymes were determined in a deep (close to the bone) and a superficial (away from the bone) region of the medial gastrocnemius (MG) and the tibialis anterior (TA) of control (CON) and 28-day HS adult female rats. Fibers were classified as dark or light adenosinetriphosphatase (ATPase) based on their qualitative staining reaction for myosin ATPase following alkaline preincubation. Fiber area and succinate dehydrogenase (SDH) and alpha-glycerophosphate dehydrogenase (GPD) activities were determined in tissue sections by use of an image analysis system. After 28 days of HS, the mean body weights of the CON and HS were similar. MG atrophied 28%, whereas TA weight was maintained in the HS. Both dark and light ATPase fibers in the deep region of the MG had smaller cross-sectional areas following HS, with the atrophic response being approximately twice as great in the light ATPase fibers. No significant changes in fiber type composition in either muscle or in fiber sizes in the superficial region of the MG or in either region of the TA were observed. Mean SDH activities of both fiber types were significantly lower in the MG and TA following HS. In contrast, mean GPD activities were either increased or maintained in light and dark ATPase fibers of both muscles in HS. Changes in SDH and GPD activity could not be directly linked to changes in fiber cross-sectional area. In summary, these data suggest an independence of the mechanisms determining muscle fiber size and metabolic adaptations associated with HS.     

Isoform diversity of giant proteins in relation to passive and active contractile properties of rabbit skeletal muscles

The active and passive contractile performance of skeletal muscle fibers largely depends on the myosin heavy chain (MHC) isoform and the stiffness of the titin spring, respectively. Open questions concern the relationship between titin-based stiffness and active contractile parameters, and titin's importance for total passive muscle stiffness. Here, a large set of adult rabbit muscles (n = 37) was studied for titin size diversity, passive mechanical properties, and possible correlations with the fiber/MHC composition. Titin isoform analyses showed sizes between approximately 3300 and 3700 kD; 31 muscles contained a single isoform, six muscles coexpressed two isoforms, including the psoas, where individual fibers expressed similar isoform ratios of 30:70 (3.4:3.3 MD). Gel electrophoresis and Western blotting of two other giant muscle proteins, nebulin and obscurin, demonstrated muscle type-dependent size differences of < or =70 kD. Single fiber and single myofibril mechanics performed on a subset of muscles showed inverse relationships between titin size and titin-borne tension. Force measurements on muscle strips suggested that titin-based stiffness is not correlated with total passive stiffness, which is largely determined also by extramyofibrillar structures, particularly collagen. Some muscles have low titin-based stiffness but high total passive stiffness, whereas the opposite is true for other muscles. Plots of titin size versus percentage of fiber type or MHC isoform (I-IIB-IIA-IID) determined by myofibrillar ATPase staining and gel electrophoresis revealed modest correlations with the type I fiber and MHC-I proportions. No relationships were found with the proportions of the different type II fiber/MHC-II subtypes. Titin-based stiffness decreased with the slow fiber/MHC percentage, whereas neither extramyofibrillar nor total passive stiffness depended on the fiber/MHC composition. In conclusion, a low correlation exists between the active and passive mechanical properties of skeletal muscle fibers. Slow muscles usually express long titin(s), predominantly fast muscles can express either short or long titin(s), giving rise to low titin-based stiffness in slow muscles and highly variable stiffness in fast muscles. Titin contributes substantially to total passive stiffness, but this contribution varies greatly among muscles.     

Measurement of sarcomere shortening in skinned fibers from frog muscle by white light diffraction.

A new optical-electronic method has been developed to detect striation spacing of single muscle fibers. The technique avoids Bragg-angle and interference-fringe effects associated with laser light diffraction by using polychromatic (white) light. The light is diffracted once by an acousto-optical device and then diffracted again by the muscle fiber. The double diffraction reverses the chromatic dispersion normally obtained with polychromatic light. In frog skinned muscle fibers, active and passive sarcomere shortening were smooth when observed by white light diffraction, whereas steps and pauses occurred in the striation spacing signals obtained with laser illumination. During active contractions skinned fibers shortened at high rates (3-5 microns/s per half sarcomere, 0-5 degrees C) at loads below 5% of isometric tension. Compression of the myofibrillar lateral filament spacing using osmotic agents reduced the shortening velocity at low loads. A hypothesis is presented that high shortening velocities are observed with skinned muscle fibers because the cross-bridges cannot support compressive loads when the filament lattice is swollen.     

Variation and limitations in fiber enzymatic and size responses in hypertrophied muscle.

The present study was designed to determine whether the degree and kind of adaptation of a muscle fiber to a functional overload (FO) are determined by properties that are intrinsic to that fiber. The study also addresses the question of the capability of fibers to maintain a normal level of coordination of proteins per fiber as fiber volume changes dramatically. The plantaris muscle of six adult female cats was overloaded for 12 wk by bilateral synergist removal. Plantaris muscle fiber mean size doubled after FO, although some very small fibers that stained dark for adenosinetriphosphatase (ATPase) were observed in some of the FO muscles. There appeared to be no change in total succinate dehydrogenase activity per fiber. A reduction in succinate dehydrogenase activity per unit volume was observed in a substantial number of fibers, reflecting a disproportionate increase in fiber volume relative to mitochondrial volume. In contrast, total alpha-glycerophosphate dehydrogenase activity and actomyosin ATPase activity increased as fiber size increased, whereas there was no change in alpha-glycerophosphate dehydrogenase and ATPase activities per unit volume. Control and FO muscle fibers generally expressed either a fast or slow myosin heavy chain type, but in some cases FO muscle fibers expressed both fast and slow myosin heavy chains. The persistence of variability in fiber sizes and enzyme activities in fibers of overloaded muscles suggests a wide range in the adaptive potential of individual fibers to FO. These data indicate that a severalfold increase in cell size may occur without significant qualitative changes in the coordination of protein regulation associated with metabolic pathways and ATP utilization.     

A hybrid graph-based approach for right ventricle segmentation in cardiac MRI by long axis information transition

Right ventricle segmentation is a challenging task in cardiac image analysis due to its complex anatomy and huge shape variations. In this paper, we proposed a semi-automatic approach by incorporating the right ventricle region and shape information into livewire framework and using one slice segmentation result for the segmentation of adjacent slices. The region term is created using our previously proposed region growing algorithm combined with the SUSAN edge detector while the shape prior is obtained by forming a signed distance function (SDF) from a set of binary masks of the right ventricle and applying PCA on them. Short axis slices are divided into two groups: primary and secondary slices. A primary slice is segmented by the proposed modified livewire and the livewire seeds are transited to a pre-processed version of upper and lower slices (secondary) to find new seed positions in these slices. The shortest path algorithm is applied on each pair of seeds for segmentation. This method is applied on 48 MR patients (from MICCAI’12 Right Ventricle Segmentation Challenge) and yielded an average Dice Metric of 0.937 ± 0.58 and the Hausdorff Distance of 5.16 ± 2.88 mm for endocardium segmentation. The correlation with the ground truth contours were measured as 0.99, 0.98, and 0.93 for EDV, ESV and EF respectively. The qualitative and quantitative results declare that the proposed method outperforms the state-of-the-art methods that uses the same dataset and the cardiac global functional parameters are calculated robustly by the proposed method.