Semiautomatic detection of myocardial contours in order to investigate normal values of the left ventricular trabeculated mass using MRI: Quantification of Trabeculated LV Mass

3D Fractal Dimension Analysis: Prognostic Value of Right Ventricular Trabecular Complexity in Participants with Arrhythmogenic Cardiomyopathy

BACKGROUND

Arrhythmogenic cardiomyopathy (ACM) is characterized by progressive myocardial fibro-fatty infiltration accompanied by trabecular disarray. Traditionally, two-dimensional (2D) instead of 3D fractal dimension (FD) analysis has been used to evaluate trabecular disarray. However, the prognostic value of trabecular disorder assessed by 3D FD measurement remains unclear.

PURPOSE

To investigate the prognostic value of right ventricular trabecular complexity in ACM patients using 3D FD analysis based on cardiac MR cine images.

STUDY TYPE

Retrospective.

POPULATION

85 ACM patients (mean age: 45 ± 17 years, 52 male).

FIELD STRENGTH/SEQUENCE

3.0T/cine imaging, T2-short tau inversion recovery (T2-STIR), and late gadolinium enhancement (LGE).

ASSESSMENT

Using cine images, RV (right ventricular) volumetric and functional parameters were obtained. RV trabecular complexity was measured with 3D fractal analysis by box-counting method to calculate 3D-FD. Cox and logistic regression models were established to evaluate the prognostic value of 3D-FD for major adverse cardiac events (MACE).

STATISTICAL TESTS

Cox regression and logistic regression to explore the prognostic value of 3D-FD. C-index, time-dependent receiver operating characteristic (ROC) curves and area under the ROC curve (AUC) to evaluate the incremental value of 3D-FD. Intraclass correlation coefficient for interobserver variability. P < 0.05 indicated statistical significance.

RESULTS

26 MACE were recorded during the 60 month follow-up (interquartile range: 48-67 months). RV 3D-FD significantly differed between ACM patients with MACE (2.67, interquartile range: 2.51 ~ 2.81) and without (2.52, interquartile range: 2.40 ~ 2.67) and was a significant independent risk factor for MACE (hazard ratio, 1.02; 95% confidence interval: 1.01, 1.04). In addition, prognostic model fitness was significantly improved after adding 3D-FD to RV global longitudinal strain, LV involvement, and 5-year risk score separately.

DATA CONCLUSION

The myocardial trabecular complexity assessed through 3D FD analysis was found associated with MACE and provided incremental prognostic value beyond conventional ACM risk factors.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 1.

A machine learning framework for the evaluation of myocardial rotation in patients with noncompaction cardiomyopathy

Aims

Noncompaction cardiomyopathy (NCC) is considered a genetic cardiomyopathy with unknown pathophysiological mechanisms. We propose to evaluate echocardiographic predictors for rigid body rotation (RBR) in NCC using a machine learning (ML) based model.

Methods and results

Forty-nine outpatients with NCC diagnosis by echocardiography and magnetic resonance imaging (21 men, 42.8±14.8 years) were included. A comprehensive echocardiogram was performed. The layer-specific strain was analyzed from the apical two-, three, four-chamber views, short axis, and focused right ventricle views using 2D echocardiography (2DE) software. RBR was present in 44.9% of patients, and this group presented increased LV mass indexed (118±43.4 vs. 94.1±27.1g/m², P = 0.034), LV end-diastolic and end-systolic volumes (P< 0.001), E/e’ (12.2±8.68 vs. 7.69±3.13, P = 0.034), and decreased LV ejection fraction (40.7±8.71 vs. 58.9±8.76%, P < 0.001) when compared to patients without RBR. Also, patients with RBR presented a significant decrease of global longitudinal, radial, and circumferential strain. When ML model based on a random forest algorithm and a neural network model was applied, it found that twist, NC/C, torsion, LV ejection fraction, and diastolic dysfunction are the strongest predictors to RBR with accuracy, sensitivity, specificity, area under the curve of 0.93, 0.99, 0.80, and 0.88, respectively.

Conclusion

In this study, a random forest algorithm was capable of selecting the best echocardiographic predictors to RBR pattern in NCC patients, which was consistent with worse systolic, diastolic, and myocardium deformation indices. Prospective studies are warranted to evaluate the role of this tool for NCC risk stratification.

Medical image segmentation automatic quality control: A multi-dimensional approach

In clinical applications, using erroneous segmentations of medical images can have dramatic consequences. Current approaches dedicated to medical image segmentation automatic quality control do not predict segmentation quality at slice-level (2D), resulting in sub-optimal evaluations. Our 2D-based deep learning method simultaneously performs quality control at 2D-level and 3D-level for cardiovascular MR image segmentations. We compared it with 3D approaches by training both on 36,540 (2D) / 3842 (3D) samples to predict Dice Similarity Coefficients (DSC) for 4 different structures from the left ventricle, i.e., trabeculations (LVT), myocardium (LVM), papillary muscles (LVPM) and blood (LVC). The 2D-based method outperformed the 3D method. At the 2D-level, the mean absolute errors (MAEs) of the DSC predictions for 3823 samples, were 0.02, 0.02, 0.05 and 0.02 for LVM, LVC, LVT and LVPM, respectively. At the 3D-level, for 402 samples, the corresponding MAEs were 0.02, 0.01, 0.02 and 0.04. The method was validated in a clinical practice evaluation against semi-qualitative scores provided by expert cardiologists for 1016 subjects of the UK BioBank. Finally, we provided evidence that a multi-level QC could be used to enhance clinical measurements derived from image segmentations.

Deep Learning-based Automated Segmentation of Left Ventricular Trabeculations and Myocardium on Cardiac MR Images: A Feasibility Study

Purpose

To develop and evaluate a complete deep learning pipeline that allows fully automated end-diastolic left ventricle (LV) cardiac MRI segmentation, including trabeculations and automatic quality control of the predicted segmentation.

Materials and Methods

This multicenter retrospective study includes training, validation, and testing datasets of 272, 27, and 150 cardiac MR images, respectively, collected between 2012 and 2018. The reference standard was the manual segmentation of four LV anatomic structures performed on end-diastolic short-axis cine cardiac MRI: LV trabeculations, LV myocardium, LV papillary muscles, and the LV blood cavity. The automatic pipeline was composed of five steps with a DenseNet architecture. Intraobserver agreement, interobserver agreement, and interaction time were recorded. The analysis includes the correlation between the manual and automated segmentation, a reproducibility comparison, and Bland-Altman plots.

Results

The automated method achieved mean Dice coefficients of 0.96 ± 0.01 (standard deviation) for LV blood cavity, 0.89 ± 0.03 for LV myocardium, and 0.62 ± 0.08 for LV trabeculation (mean absolute error, 3.63 g ± 3.4). Automatic quantification of LV end-diastolic volume, LV myocardium mass, LV trabeculation, and trabeculation mass-to-total myocardial mass (TMM) ratio showed a significant correlation with the manual measures (r = 0.99, 0.99, 0.90, and 0.83, respectively; all P < .01). On a subset of 48 patients, the mean Dice value for LV trabeculation was 0.63 ± 0.10 or higher compared with the human interobserver (0.44 ± 0.09; P < .01) and intraobserver measures (0.58 ± 0.09; P < .01). Automatic quantification of the trabeculation mass-to-TMM ratio had a higher correlation (0.92) compared with the intra- and interobserver measures (0.74 and 0.39, respectively; both P < .01).

Conclusion

Automated deep learning framework can achieve reproducible and quality-controlled segmentation of cardiac trabeculations, outperforming inter- and intraobserver analyses.Supplemental material is available for this article.© RSNA, 2020.

A novel solution of using deep learning for left ventricle detection: Enhanced feature extraction

BACKGROUND AND AIM

deep learning algorithms have not been successfully used for the left ventricle (LV) detection in echocardiographic images due to overfitting and vanishing gradient descent problem. This research aims to increase accuracy and improves the processing time of the left ventricle detection process by reducing the overfitting and vanishing gradient problem.

METHODOLOGY

the proposed system consists of an enhanced deep convolutional neural network with an extra convolutional layer, and dropout layer to solve the problem of overfitting and vanishing gradient. Data augmentation was used for increasing the accuracy of feature extraction for left ventricle detection.

RESULTS

four pathological groups of datasets were used for training and evaluation of the model: heart failure without infarction, heart failure with infarction, and hypertrophy, and healthy. The proposed model provided an accuracy of 94% in left ventricle detection for all the groups compared to the other current systems. The results showed that the processing time was reduced from 0.45 s to 0.34 s in an average.

CONCLUSION

the proposed system enhances accuracy and decreases processing time in the left ventricle detection. This paper solves the issues of overfitting of the data.

Left ventricular non-compaction as a potential source for cryptogenic ischemic stroke in the young: A case-control study

Background

Up to 50% of ischemic strokes in the young after thorough diagnostic work-up remain cryptogenic or associated with low-risk sources of cardioembolism such as patent foramen ovale (PFO). We studied with cardiac magnetic resonance (CMR) imaging, whether left ventricular (LV) non-compaction—a possible source for embolic stroke due to sluggish blood flow in deep intertrabecular recesses—is associated with cryptogenic strokes in the young.

Methods

Searching for Explanations for Cryptogenic Stroke in the Young: Revealing the Etiology, Triggers, and Outcome (SECRETO; NCT01934725) is an international prospective multicenter case-control study of young adults (aged 18–49 years) presenting with an imaging-positive first-ever ischemic stroke of undetermined etiology. In this pilot substudy, 30 cases and 30 age- and sex-matched stroke-free controls were examined with CMR. Transcranial Doppler (TCD) bubble test was performed to evaluate the presence and magnitude of right-to-left shunt (RLS).

Results

There were no significant differences in LV volumes, masses or systolic function between cases and controls; none of the participants had non-compaction cardiomyopathy. Semi-automated assessment of LV non-compaction was highly reproducible. Non-compacted LV mass (median 14.0 [interquartile range 12.6–16.0] g/m² vs. 12.7 [10.4–16.6] g/m², p = 0.045), the ratio of non-compacted to compacted LV mass (mean 25.6 ± 4.2% vs. 22.8 ± 6.0%, p = 0.015) and the percentage of non-compacted LV volume (mean 17.6 ± 2.9% vs. 15.7 ± 3.8%, p = 0.004) were higher in cases compared to controls. In a multivariate conditional logistic regression model including non-compacted LV volume, RLS and body mass index, the percentage of non-compacted LV volume (odds ratio [OR] 1.55, 95% confidence interval [CI] 1.10–2.18, p = 0.011) and the presence of RLS (OR 11.94, 95% CI 1.14–124.94, p = 0.038) were independently associated with cryptogenic ischemic stroke.

Conclusions

LV non-compaction is associated with a heightened risk of cryptogenic ischemic stroke in young adults, independent of concomitant RLS and in the absence of cardiomyopathy.

Clinical trial registration

SECRETO; NCT01934725. Registered 4^th September 2013. https://clinicaltrials.gov/ct2/show/NCT01934725

Recreational marathon running does not cause exercise-induced left ventricular hypertrabeculation

Background

Marathon running in novices represents a natural experiment of short-term cardiovascular remodeling in response to running training. We examine whether this stimulus can produce exercise-induced left ventricular (LV) trabeculation.

Methods

Sixty-eight novice marathon runners aged 29.5 ± 3.2 years had indices of LV trabeculation measured by echocardiography and cardiac magnetic resonance imaging 6 months before and 2 weeks after the 2016 London Marathon race, in a prospective longitudinal study.

Results

After 17 weeks unsupervised marathon training, indices of LV trabeculation were essentially unchanged. Despite satisfactory inter-observer agreement in most methods of trabeculation measurement, criteria defining abnormally hypertrabeculated cases were discordant with each other. LV hypertrabeculation was a frequent finding in young, healthy individuals with no subject demonstrating clear evidence of a cardiomyopathy.

Conclusion

Training for a first marathon does not induce LV trabeculation. It remains unclear whether prolonged, high-dose exercise can create de novo trabeculation or expose concealed trabeculation. Applying cut off values from published LV noncompaction cardiomyopathy criteria to young, healthy individuals risks over-diagnosis.

•

Athletes often show excessive ventricular trabeculation.

•

It is unknown whether left ventricular noncompaction cardiomyopathy can be acquired.

•

It is proposed that trabeculation may result from athletic remodeling to exercise.

•

Imaging is prone to overdiagnosis of left ventricular noncompaction cardiomyopathy.

•

Recreational marathon running does not increase left ventricular trabeculation.

Influence of observer-dependency on left ventricular hypertrabeculation mass measurement and its relationship with left ventricular volume and ejection fraction - comparison between manual and semiautomatic CMR image analysis methods

Background

Recent studies concerning left ventricular noncompaction (LVNC) suggest that the extent of left ventricular (LV) hypertrabeculation has no impact on prognosis. The variety of methods of LV noncompacted myocardial mass (NCM) assessment may influence the results. Hence, we compared two methods of NCM estimation: largely observer-independent Hautvast’s_(H) computed algorithm-based approach and commonly used Jacquier’s_(J) method, and their associations with LV end-diastolic volume (EDV) and ejection fraction (EF).

Methods

Cardiac magnetic resonance images of 77 persons (45±17yo) - 42 LVNC, 15 non-ischemic dilative cardiomyopathy, 20 control group were analyzed. LVNC patients were divided into the subgroup with normal (LVNC_N) and high EDV (LVNC_DCM). NCM and total left ventricular mass (LVM) were estimated by Hautvast’s [excluding intertrabecular blood (ITB) and including papillary muscles (PMs) into NCM] and Jacquier’s approach (including ITB and PMs, if unclearly distinguished, into NCM).

Results

The cut-off value of NCM for LVNC diagnosis was 22% (AUC 0.933) for NCM_H/LVM_H and 26% (AUC 0.883) for NCM_J/LVM_J. Inter- and intra-observer variability (estimated by coefficient of variation [CoV] and intraclass correlation coefficient [ICC]) of NCM_H/LVM_H appeared better than of NCM_J/LVM_J (CoV 4.3%, ICC 0.981 and CoV 4.9%, ICC 0.978; respectively for NCM_H/LVM_H, while for NCM_J/LVM_J: CoV 19.7%, ICC 0.15 and CoV 12.9%, ICC 0.504). In LVNC_N subgroup, the correlation between EDV and NCM_H was stronger than NCM_J (r = 0.677, p<0.001 vs. r = 0.480, p = 0.038; respectively). In LVNC the EDV correlated with NCM_H/LVM_H (r = 0.391, p<0.01), but not with NCM_J/LVM_J. In the overall group a relationship was present between EF and NCM_H/LVM_H (r = -0.449, p<0.001), but not NCM_J/LVM_J. Only NCM_H/LVM_H explained the variability of EDV (b 0.434, p<0.001).

Conclusions

Choosing a method of NCM assessment that is less observer-dependent might increase the reliability of results. The impact of method selection on the LV parameters and cut-off values for hypertrabeculation should be further investigated.

Semi-automatic detection of myocardial trabeculation using cardiovascular magnetic resonance: correlation with histology and reproducibility in a mouse model of non-compaction

BACKGROUND

The definition of left ventricular (LV) non-compaction is controversial, and discriminating between normal and excessive LV trabeculation remains challenging. Our goal was to quantify LV trabeculation on cardiovascular magnetic resonance (CMR) images in a genetic mouse model of non-compaction using a dedicated semi-automatic software package and to compare our results to the histology used as a gold standard.

METHODS

Adult mice with ventricular non-compaction were generated by conditional trabecular deletion of Nkx2-5. Thirteen mice (5 controls, 8 Nkx2-5 mutants) were included in the study. Cine CMR series were acquired in the mid LV short axis plane (resolution 0.086 × 0.086x1mm3) (11.75 T). In a sub set of 6 mice, 5 to 7 cine CMR were acquired in LV short axis to cover the whole LV with a lower resolution (0.172 × 0.172x1mm3). We used semi-automatic software to quantify the compacted mass (Mc), the trabeculated mass (Mt) and the percentage of trabeculation (Mt/Mc) on all cine acquisitions. After CMR all hearts were sliced along the short axis and stained with eosin, and histological LV contouring was performed manually, blinded from the CMR results, and Mt, Mc and Mt/Mc were quantified. Intra and interobserver reproducibility was evaluated by computing the intra class correlation coefficient (ICC).

RESULTS

Whole heart acquisition showed no statistical significant difference between trabeculation measured at the basal, midventricular and apical parts of the LV. On the mid-LV cine CMR slice, the median Mt was 0.92 mg (range 0.07-2.56 mg), Mc was 12.24 mg (9.58-17.51 mg), Mt/Mc was 6.74% (0.66-17.33%). There was a strong correlation between CMR and the histology for Mt, Mc and Mt/ Mc with respectively: r2 = 0.94 (p < 0.001), r2 = 0.91 (p < 0.001), r2 = 0.83 (p < 0.001). Intra- and interobserver reproducibility was 0.97 and 0.8 for Mt; 0.98 and 0.97 for Mc; 0.96 and 0.72 for Mt/Mc, respectively and significantly more trabeculation was observed in the Mc Mutant mice than the controls.

CONCLUSION

The proposed semi-automatic quantification software is accurate in comparison to the histology and reproducible in evaluating Mc, Mt and Mt/ Mc on cine CMR.

Distribution of left ventricular trabeculation across age and gender in 140 healthy Caucasian subjects on MR imaging

PURPOSE

The purpose of this study was to quantify the distribution of trabeculated (T) and compact (C) left ventricular (LV) myocardium masses in a healthy Caucasian population against age, gender and LV parameters, and to provide normal values for T, C and T/C.

MATERIALS AND METHODS

One hundred and forty healthy subjects were prospectively recruited and underwent cardiac MRI at 1.5T with a stack of short-axis cine sequences covering the entire LV. End-diastolic volume (EDV), C and T masses were quantified using a semi-automatic method. Ejection fraction (EF) and T/C ratio were computed.

RESULTS

We included 70 men and 70 women with a mean age of 44±14 (SD) years (range: 20-69 years). The mean EF was 63.7±6.3 (SD) % (range: 50.7-82.0%), the mean EDV was 75.9±16.2 (SD) mL/m² (range: 36.4-112.2mL/m²), the mean C mass was 53.9±11.2 (SD) g/m² (range: 26.5-93.4g/m²) and the mean T mass was 4.9±2.4 (SD) g/m² (range: 1.1-11.4g/m²). The T/C ratio was 9.2±4.5% (range: 2.0-29.4%). Multivariate ANOVA test showed that the compact mass was influenced by EDV (P<0.0001), EF (P=0.001) and gender (P<0.0001), and the trabeculated mass depended on EDV (P<0.0001), gender (P=0.002) and age (P<0.0001), while the T/C ratio was only influenced by age (P=0.0003). Spearman test showed a correlation between EDV and C (r=0.60; P<0.0001),T (r=0.46; P<0.0001) and T/C ratio (r=0.26; P=0.0023).T and T/C ratio correlated with EF (r=-0.18, P=0.0373; r=-0.18, P=0.0321, respectively).

CONCLUSION

While the compact and trabeculated myocardium masses appear to relate separately to the cardiac function, age and gender, their ratio T/C appears to only decrease with age. Furthermore, we propose here normal values for T, C and T/C in a cohort of healthy Caucasians subjects.

Left ventricular MRI wall motion assessment by monogenic signal amplitude image computation

BACKGROUND

Cardiac Magnetic Resonance Imaging (MRI) is the commonly used technique for the assessment of left ventricular (LV) function. Apart manually or semi-automatically contouring LV boundaries for quantification of By visual interpretation of cine images, assessment of regional wall motion is performed by visual interpretation of cine images, thus relying on an experience-dependent and subjective modality.

OBJECTIVE

The aim of this work is to describe a novel algorithm based on the computation of the monogenic amplitude image to be utilized in conjunction with conventional cine-MRI visualization to assess LV motion abnormalities and to validate it against gold standard expert visual interpretation.

METHODS

The proposed method uses a recent image processing tool called "monogenic signal" to decompose the MR images into features, which are relevant for motion estimation. Wall motion abnormalities are quantified locally by measuring the temporal variations of the monogenic signal amplitude. The new method was validated by two non-expert radiologists using a wall motion scoring without and with the computed image, and compared against the expert interpretation. The proposed approach was tested on a population of 40 patients, including 8 subjects with normal ventricular function and 32 pathological cases (20 with myocardial infarction, 9 with myocarditis, and 3 with dilated cardiomyopathy).

RESULTS

The results show that, for both radiologists, sensitivity, specificity and accuracy of cine-MRI alone were similar and around 59%, 77%, and 71%, respectively. Adding the proposed amplitude image while visualizing the cine MRI images significantly increased both sensitivity, specificity and accuracy up to 75%, 89%, and 84%, respectively.

CONCLUSION

Accuracy of wall motion interpretation adding amplitude image to conventional visualization was proven feasible and superior to standard image interpretation on the considered population, in inexperienced observers. Adding the amplitude images as a diagnostic tool in clinical routine is likely to improve the detection of myocardial segments presenting a cardiac dysfunction.

Fully automated segmentation of the left ventricle in cine cardiac MRI using neural network regression

BACKGROUND

Left ventricle (LV) structure and functions are the primary assessment performed in most clinical cardiac MRI protocols. Fully automated LV segmentation might improve the efficiency and reproducibility of clinical assessment.

PURPOSE

To develop and validate a fully automated neural network regression-based algorithm for segmentation of the LV in cardiac MRI, with full coverage from apex to base across all cardiac phases, utilizing both short axis (SA) and long axis (LA) scans.

STUDY TYPE

Cross-sectional survey; diagnostic accuracy.

SUBJECTS

In all, 200 subjects with coronary artery diseases and regional wall motion abnormalities from the public 2011 Left Ventricle Segmentation Challenge (LVSC) database; 1140 subjects with a mix of normal and abnormal cardiac functions from the public Kaggle Second Annual Data Science Bowl database.

FIELD STRENGTH/SEQUENCE

1.5T, steady-state free precession.

ASSESSMENT

Reference standard data generated by experienced cardiac radiologists. Quantitative measurement and comparison via Jaccard and Dice index, modified Hausdorff distance (MHD), and blood volume.

STATISTICAL TESTS

Paired t-tests compared to previous work.

RESULTS

Tested against the LVSC database, we obtained 0.77 ± 0.11 (Jaccard index) and 1.33 ± 0.71 mm (MHD), both metrics demonstrating statistically significant improvement (P < 0.001) compared to previous work. Tested against the Kaggle database, the signed difference in evaluated blood volume was +7.2 ± 13.0 mL and -19.8 ± 18.8 mL for the end-systolic (ES) and end-diastolic (ED) phases, respectively, with a statistically significant improvement (P < 0.001) for the ED phase.

DATA CONCLUSION

A fully automated LV segmentation algorithm was developed and validated against a diverse set of cardiac cine MRI data sourced from multiple imaging centers and scanner types. The strong performance overall is suggestive of practical clinical utility.

LEVEL OF EVIDENCE

3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018.