Automated segmentation of the left-ventricle from MRI with a fully convolutional network to investigate CTRCD in breast cancer patients

Purpose: The goal of this study was to develop a fully convolutional network (FCN) tool to automatedly segment the left-ventricular (LV) myocardium in displacement encoding with stimulated echoes MRI. The segmentation results are used for LV chamber quantification and strain analyses in breast cancer patients susceptible to cancer therapy-related cardiac dysfunction (CTRCD). Approach: A DeepLabV3+ FCN with a ResNet-101 backbone was custom-designed to conduct chamber quantification on 45 female breast cancer datasets (23 training, 11 validation, and 11 test sets). LV structural parameters and LV ejection fraction (LVEF) were measured, and myocardial strains estimated with the radial point interpolation method. Myocardial classification validation was against quantization-based ground-truth with computations of accuracy, Dice score, average perpendicular distance (APD), Hausdorff-distance, and others. Additional validations were conducted with equivalence tests and Cronbach's alpha (C - α ) intraclass correlation coefficients between the FCN and a vendor tool on chamber quantification and myocardial strain computations. Results: Myocardial classification results against ground-truth were Dice = 0.89 , APD = 2.4    mm , and accuracy = 97 % for the validation set and Dice = 0.90 , APD = 2.5    mm , and accuracy = 97 % for the test set. The confidence intervals (CI) and two one-sided t-test results of equivalence tests between the FCN and vendor-tool were CI = - 1.36 % to 2.42%, p-value < 0.001 for LVEF (58 ± 5 % versus 57 ± 6 % ), and CI = - 0.71 % to 0.63%, p-value < 0.001 for longitudinal strain (- 15 ± 2 % versus - 15 ± 3 % ). Conclusions: The validation results were found equivalent to the vendor tool-based parameter estimates, which show that accurate LV chamber quantification followed by strain analysis for CTRCD investigation can be achieved with our proposed FCN methodology.

Cardiac Magnetic Resonance Normal Reference Values of Biventricular Size and Function in Male Athlete's Heart

OBJECTIVES

The aim of this meta-analysis was to derive normal reference values of biventricular size and function estimated by cardiac magnetic resonance (CMR) in competitive athletes.

BACKGROUND

Exercise-induced enlargement of cardiac chambers is commonly observed in competitive athletes. However, ventricular dilatation is also a common phenotypic expression of life-threatening cardiomyopathies. The use of CMR for the exclusion of pathology is growing. However, normal reference values have not been established for athletes.

METHODS

The authors conducted a systematic review of English-language studies in the MEDLINE, Scopus, and Cochrane databases investigating biventricular size and function by CMR in athletes. Athletes were divided into endurance, combined, and mixed groups according to the sport practiced. The potential impact of training volume was also evaluated.

RESULTS

Twenty-seven studies and 983 competitive athletes were included for CMR quantification of biventricular size and function. In this review, normal reference values are presented for biventricular size and function to be applied to male competitive athletes according to the disciplines practiced. A significant impact of training volume was demonstrated for the right ventricle: athletes practicing the largest number of training hours per week were those exhibiting the greatest degree of right ventricular remodeling. Notably, biventricular function was not significantly affected by training volume.

CONCLUSIONS

The present meta-analysis defines the normal limits of biventricular size and function estimated by CMR in competitive athletes. The authors suggest using these normal reference values as an alternative to standard upper limits derived from the general population when interpreting CMR images in athletes.

Standardization of adult transthoracic echocardiography reporting in agreement with recent chamber quantification, diastolic function, and heart valve disease recommendations: an expert consensus document of the European Association of Cardiovascular Imaging

Aims

This European Association Cardiovascular Imaging (EACVI) Expert Consensus document aims at defining the main quantitative information on cardiac structure and function that needs to be included in standard echocardiographic report following recent ASE/EACVI chamber quantification, diastolic function, and heart valve disease recommendations. The document focuses on general reporting and specific pathological conditions such as heart failure, coronary artery and valvular heart disease, cardiomyopathies, and systemic diseases.

Methods and results

Demographic data (age, body surface area, blood pressure, and heart rhythm and rate), type (vendor and model) of ultrasound system used and image quality need to be reported. In addition, measurements should be normalized for body size. Reference normal values, derived by ASE/EACVI recommendations, shall always be reported to differentiate normal from pathological conditions. This Expert Consensus document suggests avoiding the surveillance of specific variable using different ultrasound techniques (e.g. in echo labs with high expertise in left ventricular ejection fraction by 3D and not by 2D echocardiography). The report should be also tailored in relation with different cardiac pathologies, quality of images, and needs of the caregivers.

Conclusion

The conclusion should be concise reflecting the status of left ventricular structure and function, the presence of left atrial and/or aortic dilation, right ventricular dysfunction, and pulmonary hypertension, leading to an objective communication with the patient health caregiver. Variation over time should be considered carefully, taking always into account the consistency of the parameters used for comparison.