Cardiac Image Segmentation from Cine Cardiac MRI Using Graph Cuts and Shape Priors

In this paper, we propose a novel method for segmentation of the left ventricle, right ventricle, and myocardium from cine cardiac magnetic resonance images of the STACOM database. Our method incorporates prior shape information in a graph cut framework to achieve segmentation. Poor edge information and large within-patient shape variation of the different parts necessitates the inclusion of prior shape information. But large interpatient shape variability makes it difficult to have a generalized shape model. Therefore, for every dataset the shape prior is chosen as a single image clearly showing the different parts. Prior shape information is obtained from a combination of distance functions and orientation angle histograms of each pixel relative to the prior shape. To account for shape changes, pixels near the boundary are allowed to change their labels by appropriate formulation of the penalty and smoothness costs. Our method consists of two stages. In the first stage, segmentation is performed using only intensity information which is the starting point for the second stage combining intensity and shape information to get the final segmentation. Experimental results on different subsets of 30 real patient datasets show higher segmentation accuracy in using shape information and our method's superior performance over other competing methods.     

Automatic Cardiac Segmentation Using Semantic Information from Random Forests

We propose a fully automated method for segmenting the cardiac right ventricle (RV) from magnetic resonance (MR) images. Given a MR test image, it is first oversegmented into superpixels and each superpixel is analyzed to detect the presence of RV regions using random forest (RF) classifiers. The superpixels containing RV regions constitute the region of interest (ROI) which is used to segment the actual RV. Probability maps are generated for each ROI pixel using a second set of RF classifiers which give the probabilities of each pixel belonging to RV or background. The negative log-likelihood of these maps are used as penalty costs in a graph cut segmentation framework. Low-level features like intensity statistics, texture anisotropy and curvature asymmetry, and high level context features are used at different stages. Smoothness constraints are imposed based on semantic information (importance of each feature to the classification task) derived from the second set of learned RF classifiers. Experimental results show that compared to conventional method our algorithm achieves superior performance due to the inclusion of semantic knowledge and context information.     

Joint Segmentation and Groupwise Registration of Cardiac Perfusion Images Using Temporal Information

We propose a joint segmentation and groupwise registration method for dynamic cardiac perfusion images that uses temporal information. The nature of perfusion images makes groupwise registration especially attractive as the temporal information from the entire image sequence can be used. Registration aims to maximize the smoothness of the intensity signal while segmentation minimizes a pixel’s dissimilarity with other pixels having the same segmentation label. The cost function is optimized in an iterative fashion using B-splines. Tests on real patient datasets show that compared with two other methods, our method shows lower registration error and higher segmentation accuracy. This is attributed to the use of temporal information for groupwise registration and mutual complementary registration and segmentation information in one framework while other methods solve the two problems separately.     

Endocardial Border Detection in Cardiac Magnetic Resonance Images Using Level Set Method

Segmentation of the left ventricle in MRI images is a task with important diagnostic power. Currently, the evaluation of cardiac function involves the global measurement of volumes and ejection fraction. This evaluation requires the segmentation of the left ventricle contour. In this paper, we propose a new method for automatic detection of the endocardial border in cardiac magnetic resonance images, by using a level set segmentation-based approach. To initialize this level set segmentation algorithm, we propose to threshold the original image and to use the binary image obtained as initial mask for the level set segmentation method. For the localization of the left ventricular cavity, used to pose the initial binary mask, we propose an automatic approach to detect this spatial position by the evaluation of a metric indicating object’s roundness. The segmentation process starts by the initialization of the level set algorithm and ended up through a level set segmentation. The validation process is achieved by comparing the segmentation results, obtained by the automated proposed segmentation process, to manual contours traced by tow experts. The database used was containing one automated and two manual segmentations for each sequence of images. This comparison showed good results with an overall average similarity area of 97.89%.     

Cardiac MRI Segmentation Using Mutual Context Information from Left and Right Ventricle

In this paper, we propose a graphcut method to segment the cardiac right ventricle (RV) and left ventricle (LV) by using context information from each other. Contextual information is very helpful in medical image segmentation because the relative arrangement of different organs is the same. In addition to the conventional log-likelihood penalty, we also include a “context penalty” that captures the geometric relationship between the RV and LV. Contextual information for the RV is obtained by learning its geometrical relationship with respect to the LV. Similarly, RV provides geometrical context information for LV segmentation. The smoothness cost is formulated as a function of the learned context which helps in accurate labeling of pixels. Experimental results on real patient datasets from the STACOM database show the efficacy of our method in accurately segmenting the LV and RV. We also conduct experiments on simulated datasets to investigate our method’s robustness to noise and inaccurate segmentations.     

Assessment of Ventricular Contractility During Cardiac Magnetic Resonance Imaging Examinations Using Normalized Maximal Ventricular Power

Normalized maximal ventricular power (nPWR^max) is an index of cardiac function which measures the innate blood pumping ability, or contractility, of the left ventricle (LV), and its noninvasive assessment could prove useful in a variety of patients. nPWR^max is defined as the maximum instantaneous product of LV pressure and the rate of change of LV volume, divided by the end diastolic volume squared. We have quantified nPWR^maxnoninvasively in humans by pairing magnetic resonance imaging (MRI) LV volume measurements with aortic pressure estimated using radial artery tonometry and a frequency domain transfer function. In healthy volunteers undergoing cardiac MRI we have tested the sensitivity of nPWR^max to LV contractility with dobutamine and to cardiac loading with methoxamine, a vasoconstrictor. We have found that aortic pressures can be reliably estimated using a transfer function, which we generated and validated in a group of patients undergoing cardiac catheterization. Furthermore, we found that nPWR^max was unchanged by methoxamine, yet sensitive to contractility, with a 325% increase at dobutamine levels half that given during routine clinical cardiac stress tests for ischemia. In conclusion, we have shown that ventricular contractility can be assessed independent of cardiac loading in patients during routine noninvasive cardiac imaging examinations. © 2001 Biomedical Engineering Society. PAC01: 8761Pk, 8719Hh, 8719Uv     

Novel Technique for Cardiac Electromechanical Mapping with Magnetic Resonance Imaging Tagging and an Epicardial Electrode Sock

Near-simultaneous measurements of electrical and mechanical activation over the entire ventricular surface are now possible using magnetic resonance imaging tagging and a multielectrode epicardial sock. This new electromechanical mapping technique is demonstrated in the ventricularly paced canine heart. A 128–electrode epicardial sock and pacing electrodes were placed on the hearts of four anesthetized dogs. In the magnetic resonance scanner, tagged cine images (8–15 ms/frame) and sock electrode recordings (1000 Hz) were acquired under right-ventricular pacing and temporally referenced to the pacing stimulus. Electrical recordings were obtained during intermittent breaks in image acquisition, so that both data sets represented the same physiologic state. Since the electrodes were not visible in the images, electrode recordings and cine images were spatially registered with Gd-DTPA markers attached to the sock. Circumferential strain was calculated at locations corresponding to electrodes. For each electrode location, electrical and mechanical activation times were calculated and relationships between the two activation patterns were demonstrated. This method holds promise for improving understanding of the relationships between the patterns of electrical activation and contraction in the heart. © 2003 Biomedical Engineering Society. PAC2003: 8761Pk, 8719Rr, 8719Hh     

Cardiac fibromas

Cardiac fibroma is a rare benign nonencapsulated neoplasm of the heart. It occurs mainly in infants and children. It may grow to a large size, which results in a variety of clinical cardiac presentations, including sudden death. Surgical excision prevents recurrence.     

Cardiac tumours

Primary cardiac tumours are relatively rare and outnumbered by the incidence of metastatic disease within the heart. There are a number of conditions that occur in childhood but the majority arise in adults, are benign and predominantly myxomas. Sarcomas are largely classified on a similar basis to their soft tissue counterparts and have a poor prognosis.Arising within the circulation, they may first manifest with obstructive symptoms within the heart or distant embolic phenomena. A number of conditions may only be identified in the setting of a post-mortem examination and may be implicated in sudden cardiac deaths.     

Cardiac calcification

We present a case of sudden cardiac death (SCD) due to accelerated atheroma in a young man. Histological specimens revealed chronic myocardial ischaemia with severe calcification. The causes of myocardial calcification are reviewed and we summarise the key learning points relating to cocaine use and heart disease. Trainees should appreciate that in cases of accelerated coronary atheroma there may be multiple risk factors involved and that family history of myocardial ischaemia is often a key contributor.     

Cardiac myxoma

Summary Neoplasms are rare cardiac findings of which myxomas comprise about 75%. We report of 15 patients, predominantly female (60%) with a mean age of 58.8 years. Male patients (40%) were 20 years younger on average.80% of these tumors developed in the left atrium fixed to the atrial septum. In 2 patients the right ventricle and in 1 patient the right atrium was involved. No left ventricular or bilateral tumors were found. Clinical findings showed a great variety of symptoms. Often misdiagnosis was established until echocardiography was performed. Major symptoms were dyspnea (80%), elevated erythrocyte sedimentation rate (73%), arrhythmias (53%), lung edema (47%), embolization (40%) and anemia (40%).Pathological examination and tumor genesis are still in discussion. Several theories are reported in literature: a true thrombus, thrombus organization with malignant potential, true neoplasms as well as a familiar myxoma complex may explain clinical and histological features. Our findings did not confirm only one theory but emphasize different possibilities.Abbreviations LA Left atrium - RA Right atrium - RV Right ventricle     

Cardiac rhabdomyoma

Primary tumors of the heart are exceedingly rare with a prevalence rate of around 0.01% in autopsy studies. A majority of primary cardiac tumors are benign. Rhabdomyomas are the most common of benign pediatric cardiac tumors. A newborn female infant presented with perioral cyanosis and respiratory distress. She deteriorated progressively. The infant expired, and at autopsy, dissection of the heart revealed a large tumor mass in the interventricular septum. Histologically, the mass showed the classic “spider cells,” and a diagnosis of cardiac rhabdomyoma of childhood was established.     

Cardiac tumors

Primary cardiac tumors are rare and their subdivision often difficult because of their unknown origin. In the most recent classification, cardiac tumors are divided into benign (about 75% and malignant neoplasms in relationship to their tissue differentiation (rhabdomyoma, haemangioma, etc.) or uncertain aetiology (myxoma, papillary fibroelastoma). Primary malignant tumors are maimly represented by sarcomas. The most frequent tumor is cardiac myxoma, which by itself represents about 50% of all primary cardiac neoplasms. Although non-invasive technologies as trans-esophageal ecocardiography allow the detection and exact localization of cardiac mass, clinical diagnosis is often tardive. This is due, besides the intrinsic rarity, to two main factors: first, the tumor is often asymptomatic (incidental autopic finding) or; alternatively, it may show aspecif symptoms mimicking heart failure or other pathologies. In this article, clinicopathological features of main primary cardiac tumors are presented. Investigation of the histogenesis of some of these neoplasms is still a primary field of research.