Search

Abstract Blunt chest traumas are a clinical challenge, both for diagnosis and treatment. The use of Cardiovascular Magnetic Resonance can play a major role in this setting. We present two cases: a 12-year-old boy and 45-year-old man. Late gadolinium enhancement imaging enabled visualization of myocardial damage resulting from the trauma.

Background: Light chain (AL) and transthyretin (ATTR) amyloid fibrils are deposited in the extracellular space of the myocardium, resulting in heart failure and premature mortality. Extracellular expansion can be quantified by computed tomography, offering a rapid, cheaper, and more practical alternative to cardiac magnetic resonance, especially among patients with cardiac devices or on renal dialysis., Objectives: This study sought to investigate the association of extracellular volume fraction by computed tomography (ECV CT ), myocardial remodeling, and mortality in patients with systemic amyloidosis., Methods: Patients with confirmed systemic amyloidosis and varying degrees of cardiac involvement underwent electrocardiography-gated cardiac computed tomography. Whole heart and septal ECV CT was analyzed. All patients also underwent clinical assessment, electrocardiography, echocardiography, serum amyloid protein component, and/or technetium-99m ( 99m Tc) 3,3-diphosphono-1,2-propanodicarboxylic acid scintigraphy. ECV CT was compared across different extents of cardiac infiltration (ATTR Perugini grade/AL Mayo stage) and evaluated for its association with myocardial remodeling and all-cause mortality., Results: A total of 72 patients were studied (AL: n = 35, ATTR: n = 37; median age: 67 [IQR: 59-76] years, 70.8% male). Mean septal ECV CT was 42.7% ± 13.1% and 55.8% ± 10.9% in AL and ATTR amyloidosis, respectively, and correlated with indexed left ventricular mass (r = 0.426; P < 0.001), left ventricular ejection fraction (r = 0.460; P < 0.001), N-terminal pro-B-type natriuretic peptide (r = 0.563; P < 0.001), and high-sensitivity troponin T (r = 0.546; P < 0.001). ECV CT increased with cardiac amyloid involvement in both AL and ATTR amyloid. Over a mean follow-up of 5.3 ± 2.4 years, 40 deaths occurred (AL: n = 14 [35.0%]; ATTR: n = 26 [65.0%]). Septal ECV CT was independently associated with all-cause mortality in ATTR (not AL) amyloid after adjustment for age and septal wall thickness (HR: 1.046; 95% CI: 1.003-1.090; P = 0.037)., Conclusions: Cardiac amyloid burden quantified by ECV CT is associated with adverse cardiac remodeling as well as all-cause mortality among ATTR amyloid patients. ECV CT may address the need for better identification and risk stratification of amyloid patients, using a widely accessible imaging modality., Competing Interests: Funding Support and Author Disclosures Drs Moon and Treibel are directly and indirectly supported by the University College London Hospitals National Institute for Health Research Biomedical Research Centre and Biomedical Research Unit at Barts Hospital, respectively. This work was undertaken at University College London Hospital, which received a proportion of funding from the UK Department of Health National Institute for Health Research Biomedical Research Centre’s funding scheme. Dr Patel is funded by the British Heart Foundation Clinical Research Training Fellowship. Dr Gama is supported by a nonrestricted educational grant by Pfizer. Drs Treibel and Fontana are funded by British Heart Foundation intermediate fellowships (FS/19/35/34374 and FS/18/21/33447). Dr Thornton is supported by a British Heart Foundation Clinical Research Training Fellowship (FS/CRTF/21/24128). All other authors have reported that they have no relationships relevant to the contents of this paper to disclose., (Copyright © 2022 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.)

International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)-a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training., (© 2022. The Author(s).)

Aims: Left atrial (LA) remodelling is a common feature of many cardiovascular pathologies and is a sensitive marker of adverse cardiovascular outcomes. The aim of this study was to establish normal ranges for LA parameters derived from coronary computed tomographic angiography (CCTA) imaging using a standardised image processing pipeline to establish normal ranges in a previously described cohort., Methods: CCTA imaging from 193 subjects recruited to the Budapest GLOBAL twin study was analysed. Indexed LA cavity volume (LACV i ), LA surface area (LASA i ), wall thickness and LA tissue volume (LATV i ) were calculated. Wall thickness maps were combined into an atlas. Indexed LA parameters were compared with clinical variables to identify early markers of pathological remodelling., Results: LACV i is similar between sexes (31 ml/m 2 v 30 ml/m 2 ) and increased in hypertension (33 ml/m 2 v 29 ml/m 2 , p = 0.009). LASA i is greater in females than males (47.8 ml/m 2 v 45.8 ml/m 2 male, p = 0.031). Median LAWT was 1.45 mm. LAWT was lowest at the inferior portion of the posterior LA wall (1.14 mm) and greatest in the septum (median = 2.0 mm) (p < 0.001). Conditions known to predispose to the development of AF were not associated with differences in tissue thickness., Conclusions: The reported LACV i , LASA i , LATV i and tissue thickness derived from CCTA may serve as reference values for this age group and clinical characteristics for future studies. Increased LASA i in females in the absence of differences in LACV i or LATV i may indicate differential LA shape changes between the sexes. AF predisposing conditions, other than sex, were not associated with detectable changes in LAWT. Clinical trial registration: http://www.ClinicalTrials.gov/NCT01738828., Competing Interests: The authors report no relationships that could be construed as a conflict of interest., (© 2020 Published by Elsevier B.V.)

Objectives: To assess the use of CT with unfolded cylindrical projection (UCP) for rib fracture detection and characterization., Methods: The images from 60 polytraumatized patients who underwent whole body CT were evaluated for the presence and characterization of rib fractures (displaced or not, single or multiple). Two readers independently evaluated conventional CT images and UCP images in two readout sessions at least one month apart. All readouts were timed. A gold standard was established by two radiologists with 12 and 22 years of clinical experience based on the combined analysis of conventional and UCP reformats., Results: Using UCP, the mean evaluation time was 27%-54% shorter (P = 0.01 and <0.0001) while maintaining a comparable diagnostic performance (sensitivity and specificity of 68.4-79.1% and 99.5-99.6% for conventional reformats and 70.6-91.0% and 96.8-97.7% for UCP) and a good reproducibility (Kappa of 0.71). The multiple fracture detection ratio of UCP was similar to that of conventional reformats (>80%). There were more false positives and false negatives using UCP and displaced fractures were harder to characterize., Conclusion: UCP yielded a diagnostic performance similar to that of conventional reformats for the detection of rib fractures with a good reproducibility and a noticeable reduction in evaluation time., (Copyright © 2018. Published by Elsevier B.V.)

Atrial fibrillation (AF) is a supraventricular tachyarrhythmia characterized by complete absence of coordinated atrial contraction and is associated with an increased morbidity and mortality. Personalized computational modeling provides a novel framework for integrating and interpreting the role of atrial electrophysiology (EP) including the underlying anatomy and microstructure in the development and sustenance of AF. Coronary computed tomography angiography data were segmented using a statistics-based approach and the smoothed voxel representations were discretized into high-resolution tetrahedral finite element (FE) meshes. To estimate the complex left atrial myofiber architecture, individual fiber fields were generated according to morphological data on the endo- and epicardial surfaces based on local solutions of Laplace's equation and transmurally interpolated to tetrahedral elements. The influence of variable transmural microstructures was quantified through EP simulations on 3 patients using 5 different fiber interpolation functions. Personalized geometrical models included the heterogeneous thickness distribution of the left atrial myocardium and subsequent discretization led to high-fidelity tetrahedral FE meshes. The novel algorithm for automated incorporation of the left atrial fiber architecture provided a realistic estimate of the atrial microstructure and was able to qualitatively capture all important fiber bundles. Consistent maximum local activation times were predicted in EP simulations using individual transmural fiber interpolation functions for each patient suggesting a negligible effect of the transmural myofiber architecture on EP. The established modeling pipeline provides a robust framework for the rapid development of personalized model cohorts accounting for detailed anatomy and microstructure and facilitates simulations of atrial EP., (Copyright © 2018 Elsevier B.V. All rights reserved.)

Purpose: To report the development of easy-to-use magnetic resonance imaging (MRI) fractal tools deployed on platforms accessible to all. The trabeculae of the left ventricle vary in health and disease but their measurement is difficult. Fractal analysis of cardiac MR images can measure trabecular complexity as a fractal dimension (FD)., Materials and Methods: This Health Insurance Portability and Accountability Act (HIPAA)-compliant study was approved by the local Institutional Review Board. Participants provided written informed consent. The original MatLab implementation (region-based level set segmentation and box-counting algorithm) was recoded for two platforms (OsiriX and a clinical MR reporting platform [cvi 42 , Circle Cardiovascular Imaging, Calgary, Canada]). For validation, 100 subjects were scanned at 1.5T and 20 imaged twice for interstudy reproducibility. Cines were analyzed by the three tools and FD variability determined. Manual trabecular delineation by an expert reader (R1) provided ground truth contours for validation of segmentation accuracy by point-to-curve (P2C) distance estimates. Manual delineation was repeated by R1 and a second reader (R2) on 15 cases for intra/interobserver variability., Results: FD by OsiriX and the clinical MR reporting platform showed high correlation with MatLab values (correlation coefficients: 0.96 [95% CI: 0.95-0.97] and 0.96 [0.95-0.96]) and high interstudy and intraplatform reproducibility. Semiautomated contours in OsiriX and the clinical MR reporting platform were highly correlated with ground truth contours evidenced by low P2C errors: 0.882 ± 0.76 mm and 0.709 ± 0.617 mm. Validity of ground truth contours was inferred from low P2C errors between readers (R1-R1: 0.798 ± 0.718 mm; R1-R2: 0.804 ± 0.649 mm)., Conclusion: This set of accessible fractal tools that measure trabeculation in the heart have been validated and released to the cardiac MR community (http://j.mp/29xOw3B) to encourage novel clinical applications of fractals in the cardiac imaging domain., Level of Evidence: 3 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2017;46:1082-1088., (© 2017 International Society for Magnetic Resonance in Medicine.)

Purpose: Left atrial arrhythmia substrate assessment can involve multiple imaging and electrical modalities, but visual analysis of data on 3D surfaces is time-consuming and suffers from limited reproducibility. Unfold maps (e.g., the left ventricular bull's eye plot) allow 2D visualization, facilitate multimodal data representation, and provide a common reference space for inter-subject comparison. The aim of this work is to develop a method for automatic representation of multimodal information on a left atrial standardized unfold map (LA-SUM)., Methods: The LA-SUM technique was developed and validated using 18 electroanatomic mapping (EAM) LA geometries before being applied to ten cardiac magnetic resonance/EAM paired geometries. The LA-SUM was defined as an unfold template of an average LA mesh, and registration of clinical data to this mesh facilitated creation of new LA-SUMs by surface parameterization., Results: The LA-SUM represents 24 LA regions on a flattened surface. Intra-observer variability of LA-SUMs for both EAM and CMR datasets was minimal; root-mean square difference of 0.008 ± 0.010 and 0.007 ± 0.005 ms (local activation time maps), 0.068 ± 0.063 gs (force-time integral maps), and 0.031 ± 0.026 (CMR LGE signal intensity maps). Following validation, LA-SUMs were used for automatic quantification of post-ablation scar formation using CMR imaging, demonstrating a weak but significant relationship between ablation force-time integral and scar coverage (R 2  = 0.18, P < 0.0001)., Conclusions: The proposed LA-SUM displays an integrated unfold map for multimodal information. The method is applicable to any LA surface, including those derived from imaging and EAM systems. The LA-SUM would facilitate standardization of future research studies involving segmental analysis of the LA.

Introduction and Objectives: Patients with hypertrophic cardiomyopathy (HCM) have irregular ventricular shapes with small and sometimes obliterated cavities at end-systole that affect the quantification of left ventricular mass (LVM) by conventional methods, such as M-mode or two-dimensional echocardiography. The goal of this study was to validate the use of real time three-dimensional echocardiography (RT3DE) to quantify LVM using cardiac magnetic resonance imaging (CMR) as a reference, in a large population of patients with different types of HCM., Methods: Forty-eight consecutive patients with HCM had a complete transthoracic examination and CMR performed within 7 days. LVM was calculated by M-mode and RT3DE and compared to CMR that served as gold standard., Results: Left ventricular mass calculated by RT3DE was 195 ± 41 g and 187 ± 49 g by CMR. The correlation between the two methods was moderate, with a Lin index of 0.63 and good linear correlation (r = 0.63, P < 0.0001). The correlation was high when RT3DE was of high or adequate image quality. The correlation between LVM by M-mode and CMR was poor., Conclusion: Three-dimensional echocardiography is an accurate method for the quantification of LVM in patients with different subtypes of HCM that is in better agreement with CMR reference values than M-mode measurements., (© 2015, Wiley Periodicals, Inc.)

Many of the structures and parameters that are detected, measured and reported in cardiovascular magnetic resonance (CMR) have at least some properties that are fractal, meaning complex and self-similar at different scales. To date however, there has been little use of fractal geometry in CMR; by comparison, many more applications of fractal analysis have been published in MR imaging of the brain.This review explains the fundamental principles of fractal geometry, places the fractal dimension into a meaningful context within the realms of Euclidean and topological space, and defines its role in digital image processing. It summarises the basic mathematics, highlights strengths and potential limitations of its application to biomedical imaging, shows key current examples and suggests a simple route for its successful clinical implementation by the CMR community.By simplifying some of the more abstract concepts of deterministic fractals, this review invites CMR scientists (clinicians, technologists, physicists) to experiment with fractal analysis as a means of developing the next generation of intelligent quantitative cardiac imaging tools.

Knowledge of left atrial (LA) anatomy is important for atrial fibrillation ablation guidance, fibrosis quantification and biophysical modelling. Segmentation of the LA from Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) images is a complex problem. This manuscript presents a benchmark to evaluate algorithms that address LA segmentation. The datasets, ground truth and evaluation code have been made publicly available through the http://www.cardiacatlas.org website. This manuscript also reports the results of the Left Atrial Segmentation Challenge (LASC) carried out at the STACOM'13 workshop, in conjunction with MICCAI'13. Thirty CT and 30 MRI datasets were provided to participants for segmentation. Each participant segmented the LA including a short part of the LA appendage trunk and proximal sections of the pulmonary veins (PVs). We present results for nine algorithms for CT and eight algorithms for MRI. Results showed that methodologies combining statistical models with region growing approaches were the most appropriate to handle the proposed task. The ground truth and automatic segmentations were standardised to reduce the influence of inconsistently defined regions (e.g., mitral plane, PVs end points, LA appendage). This standardisation framework, which is a contribution of this work, can be used to label and further analyse anatomical regions of the LA. By performing the standardisation directly on the left atrial surface, we can process multiple input data, including meshes exported from different electroanatomical mapping systems.

Background: Diffuse myocardial fibrosis may provide a substrate for the initiation and maintenance of ventricular arrhythmia. T1 mapping overcomes the limitations of the conventional delayed contrast-enhanced cardiac magnetic resonance (CE-CMR) imaging technique by allowing quantification of diffuse fibrosis., Objective: The purpose of this study was to assess whether myocardial tissue characterization using T1 mapping would predict ventricular arrhythmia in ischemic and non-ischemic cardiomyopathies., Methods: This was a prospective longitudinal study of consecutive patients receiving implantable cardioverter-defibrillators in a tertiary cardiac center. Participants underwent CMR myocardial tissue characterization using T1 mapping and conventional CE-CMR scar assessment before device implantation. The primary end point was an appropriate implantable cardioverter-defibrillator therapy or documented sustained ventricular arrhythmia., Results: One hundred thirty patients (71 ischemic and 59 non-ischemic) were included with a mean follow-up period of 430 ± 185 days (median 425 days; interquartile range 293 days). At follow-up, 23 patients (18%) experienced the primary end point. In multivariable-adjusted analyses, the following factors showed a significant association with the primary end point: secondary prevention (hazard ratio [HR] 1.70; 95% confidence interval [95% CI] 1.01-1.91), noncontrast T1(&#95;native) for every 10-ms increment in value (HR 1.10; CI 1.04-1.16; 90-ms difference between the end point-positive and end point-negative groups), and Grayzone(&#95;2sd-3sd) for every 1% left ventricular increment in value (HR 1.36; CI 1.15-1.61; 4% difference between the end point-positive and end point-negative groups). Other CE-CMR indices including Scar(&#95;2sd), Scar(&#95;FWHM), and Grayzone(&#95;2sd-FWHM) were also significantly, even though less strongly, associated with the primary end point as compared with Grayzone(&#95;2sd-3sd)., Conclusion: Quantitative myocardial tissue assessment using T1 mapping is an independent predictor of ventricular arrhythmia in both ischemic and non-ischemic cardiomyopathies., (Copyright © 2015 Heart Rhythm Society. Published by Elsevier Inc. All rights reserved.)

Purpose: Magnetic resonance imaging (MRI), specifically late-enhanced MRI, is the standard clinical imaging protocol to assess cardiac viability. Segmentation of myocardial walls is a prerequisite for this assessment. Automatic and robust multisequence segmentation is required to support processing massive quantities of data., Methods: A generic rule-based framework to automatically segment the left ventricle myocardium is presented here. We use intensity information, and include shape and interslice smoothness constraints, providing robustness to subject- and study-specific changes. Our automatic initialization considers the geometrical and appearance properties of the left ventricle, as well as interslice information. The segmentation algorithm uses a decoupled, modified graph cut approach with control points, providing a good balance between flexibility and robustness., Results: The method was evaluated on late-enhanced MRI images from a 20-patient in-house database, and on cine-MRI images from a 15-patient open access database, both using as reference manually delineated contours. Segmentation agreement, measured using the Dice coefficient, was 0.81±0.05 and 0.92±0.04 for late-enhanced MRI and cine-MRI, respectively. The method was also compared favorably to a three-dimensional Active Shape Model approach., Conclusion: The experimental validation with two magnetic resonance sequences demonstrates increased accuracy and versatility., (© 2013 Wiley Periodicals, Inc.)

Training active shape models requires collecting manual ground-truth meshes in a large image database. While shape information can be reused across multiple imaging modalities, intensity information needs to be imaging modality and protocol specific. In this context, this study has two main purposes: (1) to test the potential of using intensity models learned from MRI simulated datasets and (2) to test the potential of including a measure of reliability during the matching process to increase robustness. We used a population of 400 virtual subjects (XCAT phantom), and two clinical populations of 40 and 45 subjects. Virtual subjects were used to generate simulated datasets (MRISIM simulator). Intensity models were trained both on simulated and real datasets. The trained models were used to segment the left ventricle (LV) and right ventricle (RV) from real datasets. Segmentations were also obtained with and without reliability information. Performance was evaluated with point-to-surface and volume errors. Simulated intensity models obtained average accuracy comparable to inter-observer variability for LV segmentation. The inclusion of reliability information reduced volume errors in hypertrophic patients (EF errors from 17 ± 57% to 10 ± 18%; LV MASS errors from -27 ± 22 g to -14 ± 25 g), and in heart failure patients (EF errors from -8 ± 42% to -5 ± 14%). The RV model of the simulated images needs further improvement to better resemble image intensities around the myocardial edges. Both for real and simulated models, reliability information increased segmentation robustness without penalizing accuracy.

In this paper, we present a novel technique based on nonrigid image registration for myocardial motion estimation using both untagged and 3-D tagged MR images. The novel aspect of our technique is its simultaneous usage of complementary information from both untagged and 3-D tagged MR images. To estimate the motion within the myocardium, we register a sequence of tagged and untagged MR images during the cardiac cycle to a set of reference tagged and untagged MR images at end-diastole. The similarity measure is spatially weighted to maximize the utility of information from both images. In addition, the proposed approach integrates a valve plane tracker and adaptive incompressibility into the framework. We have evaluated the proposed approach on 12 subjects. Our results show a clear improvement in terms of accuracy compared to approaches that use either 3-D tagged or untagged MR image information alone. The relative error compared to manually tracked landmarks is less than 15% throughout the cardiac cycle. Finally, we demonstrate the automatic analysis of cardiac function from the myocardial deformation fields.

Introduction and Objectives: In hypertrophic cardiomyopathy (HCM), it has been suggested that regional fiber disarray produces segments that exhibit no or severely reduced deformation, and that these segments are distributed nonuniformly within the left ventricle (LV). This contrasts with observations in other types of hypertrophy, such as in athlete's heart or hypertensive left ventricular hypertrophy (HLVH), in which abnormal cardiac deformation may exist but the reduction is not so severe that some segments exhibit no deformation. Our aim was to use the strain distribution to study deformation in HCM., Methods: We used tagged magnetic resonance imaging to reconstruct LV systolic deformation in 12 controls, 10 athletes, 12 patients with HCM, and 10 patients with HLVH. Deformation was quantified using a fast nonrigid registration algorithm and peak radial and circumferential systolic strain values were determined in 16 LV segments., Results: Patients with HCM had significantly lower average strain values than individuals in other groups. However, while the deformation observed in healthy subjects and HLVH patients clustered around the mean, in HCM patients, segments with normal contraction coexisted with segments exhibiting no or significantly reduced deformation, which resulted in a greater heterogeneity of strain values. Moreover, some nondeforming segments were observed even when fibrosis and hypertrophy were absent., Conclusions: The strain distribution characterized specific patterns of myocardial deformation in patients with LVH due to different etiologies. Patients with HCM had significantly lower mean strain values and a greater heterogeneity in strain values than controls, athletes and HLVH patients. In addition, they had nondeforming regions.

In this study we propose a pipeline for simulation of late gadolinium enhancement images. We used a modified version of the XCAT phantom to improve simulation realism. Modifications included the modeling of trabeculae and papillary muscles, and the increase of sublabels to resemble tissue intensity variability. Magnetic properties for each body tissue were sampled in three settings: from Gaussian distributions, combining Rayleigh-Gaussian distributions, and from Rayleigh distributions. Thirty-two simulated datasets were compared with 32 clinical datasets from infarcted patients. Histograms were obtained for five tissues: lung, pericardium, myocardium, blood and hyper-enhanced area. Real and simulated histograms were compared with the Chi-square dissimilarity metric (χ(2)) and Kullback-Leibler divergence (KL). The generated simulated images look similar to real images according to both metrics. Rayleigh and the Rayleigh-Gaussian models obtained comparable average results (respectively: χ(2)= 0.16 ± 0.12 and 0.18 ± 0.11; KL=0.15 ± 0.17 and 0.16 ± 0.18).

Left ventricular hypertrophy (LVH) is a complex cardiac condition mainly identified by the thickening of the myocardial wall. Although most of the contemporary cardiac imaging modalities provide high resolution 3D images, the wall thickness (WT) is still measured within the acquired planes. This way of measurement may introduce an error as cardiac wall is not necessarily orthogonal to the plane. In this study we analyze how different approaches to measure WT can affect an automatic identification of hypertrophy. The compared approaches are: WT measured along surface normal and the one provided by a medial surface. For both approaches we evaluated their ability to identify LVH phenotypes by testing with two classifiers: Transductive Confidence Machine-k Nearest Neighbor (TCM-kNN) and Linear Discriminant Analysis (LDA). Fifty three subjects were included in this study: 18 patients with hypertrophic cardiomyopathy (HCM), 13 patients with hypertensive heart disease (HDD) and 22 sedentary subjects (CG). Medial surface based approach allowed obtaining higher classification accuracy in HDD patients, while normal based approach allowed for higher classification accuracy in HCM patients.

We present a novel approach for automatic segmentation of the myocardium in short-axis MRI using deformable medial models with an explicit representation of thickness. Segmentation is constrained by a Markov prior on myocardial thickness. Best practices from Active Shape Modeling (global PCA shape prior, statistical appearance model, local search) are adapted to the medial model. Segmentation performance is evaluated by comparing to manual segmentation in a heterogeneous adult MRI dataset. Average boundary displacement error is under 1.4 mm for left and right ventricles, comparing favorably with published work.

Blunt chest traumas are a clinical challenge, both for diagnosis and treatment. The use of cardiovascular magnetic resonance can play a major role in this setting. We present two cases: a 12-year-old boy and 45-year-old man. Late gadolinium enhancement imaging enabled visualization of myocardial damage resulting from the trauma.

Active shape models bear a great promise for model-based medical image analysis. Their practical use, though, is undermined due to the need to train such models on large image databases. Automatic building of point distribution models (PDMs) has been successfully addressed and a number of autolandmarking techniques are currently available. However, the need for strategies to automatically build intensity models around each landmark has been largely overlooked in the literature. This work demonstrates the potential of creating intensity models automatically by simulating image generation. We show that it is possible to reuse a 3D PDM built from computed tomography (CT) to segment gated single photon emission computed tomography (gSPECT) studies. Training is performed on a realistic virtual population where image acquisition and formation have been modeled using the SIMIND Monte Carlo simulator and ASPIRE image reconstruction software, respectively. The dataset comprised 208 digital phantoms (4D-NCAT) and 20 clinical studies. The evaluation is accomplished by comparing point-to-surface and volume errors against a proper gold standard. Results show that gSPECT studies can be successfully segmented by models trained under this scheme with subvoxel accuracy. The accuracy in estimated LV function parameters, such as end diastolic volume, end systolic volume, and ejection fraction, ranged from 90.0% to 94.5% for the virtual population and from 87.0% to 89.5% for the clinical population.