Sex-specific structural and functional cardiac remodeling during healthy aging assessed by cardiovascular magnetic resonance.

BACKGROUND: Aging as a major non-modifiable cardiac risk factor challenges future cardiovascular medicine and economic demands, which requires further assessments addressing physiological age-associated cardiac changes. OBJECTIVES: Using cardiovascular magnetic resonance (CMR), this study aims to characterize sex-specific ventricular adaptations during healthy aging. METHODS: The population included healthy volunteers who underwent CMR at 1.5 or 3 Tesla scanners applying cine-imaging with a short-axis coverage of the left (LV) and right (RV) ventricle. The cohort was divided by sex (female and male) and age (subgroups in years): 1 (19-29), 2 (30-39), 3 (40-49), and 4 (≥50). Cardiac adaptations were quantitatively assessed by CMR indices. RESULTS: After the exclusion of missing or poor-quality CMR datasets or diagnosed disease, 140 of 203 volunteers were part of the final analysis. Women generally had smaller ventricular dimensions and LV mass, but higher biventricular systolic function. There was a significant age-associated decrease in ventricular dimensions as well as a significant increase in LV mass-to-volume ratio (LV-MVR, concentricity) in both sexes (LV-MVR in g/ml: age group 1 vs. 4: females 0.50 vs. 0.57, p=0.016, males 0.56 vs. 0.67, p=0.024). LV stroke volume index decreased significantly with age in both sexes, but stronger for men than for women (in ml/m2: age group 1 vs. 4: females 51.76 vs. 41.94, p<0.001, males 55.31 vs. 40.78, p<0.001). Ventricular proportions (RV-to-LV-volume ratio) were constant between the age groups in both sexes. CONCLUSIONS: In both sexes, healthy aging was associated with an increase in concentricity and a decline in ventricular dimensions. Furthermore, relevant age-related sex differences in systolic LV performance were observed.

Post-hoc standardisation of parametric T1 maps in cardiovascular magnetic resonance imaging: a proof-of-concept.

BACKGROUND: In cardiovascular magnetic resonance imaging parametric T1 mapping lacks universally valid reference values. This limits its extensive use in the clinical routine. The aim of this work was the introduction of our self-developed Magnetic Resonance Imaging Software for Standardization (MARISSA) as a post-hoc standardisation approach. METHODS: Our standardisation approach minimises the bias of confounding parameters (CPs) on the base of regression models. 214 healthy subjects with 814 parametric T1 maps were used for training those models on the CPs: age, gender, scanner and sequence. The training dataset included both sex, eleven different scanners and eight different sequences. The regression model type and four other adjustable standardisation parameters were optimised among 240 tested settings to achieve the lowest coefficient of variation, as measure for the inter-subject variability, in the mean T1 value across the healthy test datasets (HTE, N = 40, 156 T1 maps). The HTE were then compared to 135 patients with left ventricular hypertrophy including hypertrophic cardiomyopathy (HCM, N = 112, 121 T1 maps) and amyloidosis (AMY, N = 24, 24 T1 maps) after applying the best performing standardisation pipeline (BPSP) to evaluate the diagnostic accuracy. FINDINGS: The BPSP reduced the COV of the HTE from 12.47% to 5.81%. Sensitivity and specificity reached 95.83% / 91.67% between HTE and AMY, 71.90% / 72.44% between HTE and HCM, and 87.50% / 98.35% between HCM and AMY. INTERPRETATION: Regarding the BPSP, MARISSA enabled the comparability of T1 maps independently of CPs while keeping the discrimination of healthy and patient groups as found in literature. FUNDING: This study was supported by the BMBF / DZHK.

Comparison of manual and artificial intelligence based quantification of myocardial strain by feature tracking-a cardiovascular MR study in health and disease.

OBJECTIVES: The analysis of myocardial deformation using feature tracking in cardiovascular MR allows for the assessment of global and segmental strain values. The aim of this study was to compare strain values derived from artificial intelligence (AI)-based contours with manually derived strain values in healthy volunteers and patients with cardiac pathologies. MATERIALS AND METHODS: A cohort of 136 subjects (60 healthy volunteers and 76 patients; of those including 46 cases with left ventricular hypertrophy (LVH) of varying etiology and 30 cases with chronic myocardial infarction) was analyzed. Comparisons were based on quantitative strain analysis and on a geometric level by the Dice similarity coefficient (DSC) of the segmentations. Strain quantification was performed in 3 long-axis slices and short-axis (SAX) stack with epi- and endocardial contours in end-diastole. AI contours were checked for plausibility and potential errors in the tracking algorithm. RESULTS: AI-derived strain values overestimated radial strain (+ 1.8 ± 1.7% (mean difference ± standard deviation); p = 0.03) and underestimated circumferential (- 0.8 ± 0.8%; p = 0.02) and longitudinal strain (- 0.1 ± 0.8%; p = 0.54). Pairwise group comparisons revealed no significant differences for global strain. The DSC showed good agreement for healthy volunteers (85.3 ± 10.3% for SAX) and patients (80.8 ± 9.6% for SAX). In 27 cases (27/76; 35.5%), a tracking error was found, predominantly (24/27; 88.9%) in the LVH group and 22 of those (22/27; 81.5%) at the insertion of the papillary muscle in lateral segments. CONCLUSIONS: Strain analysis based on AI-segmented images shows good results in healthy volunteers and in most of the patient groups. Hypertrophied ventricles remain a challenge for contouring and feature tracking. CLINICAL RELEVANCE STATEMENT: AI-based segmentations can help to streamline and standardize strain analysis by feature tracking. KEY POINTS: • Assessment of strain in cardiovascular magnetic resonance by feature tracking can generate global and segmental strain values. • Commercially available artificial intelligence algorithms provide segmentation for strain analysis comparable to manual segmentation. • Hypertrophied ventricles are challenging in regards of strain analysis by feature tracking.

Multi-site comparison of parametric T1 and T2 mapping: healthy travelling volunteers in the Berlin research network for cardiovascular magnetic resonance (BER-CMR).

BACKGROUND: Parametric mapping sequences in cardiovascular magnetic resonance (CMR) allow for non-invasive myocardial tissue characterization. However quantitative myocardial mapping is still limited by the need for local reference values. Confounders, such as field strength, vendors and sequences, make intersite comparisons challenging. This exploratory study aims to assess whether multi-site studies that control confounding factors provide first insights whether parametric mapping values are within pre-defined tolerance ranges across scanners and sites. METHODS: A cohort of 20 healthy travelling volunteers was prospectively scanned at three sites with a 3 T scanner from the same vendor using the same scanning protocol and acquisition scheme. A Modified Look-Locker inversion recovery sequence (MOLLI) for T1 and a fast low-angle shot sequence (FLASH) for T2 were used. At one site a scan-rescan was performed to assess the intra-scanner reproducibility. All acquired T1- and T2-mappings were analyzed in a core laboratory using the same post-processing approach and software. RESULTS: After exclusion of one volunteer due to an accidentally diagnosed cardiac disease, T1- and T2-maps of 19 volunteers showed no significant differences between the 3 T sites (mean ± SD [95% confidence interval] for global T1 in ms: site I: 1207 ± 32 [1192-1222]; site II: 1207 ± 40 [1184-1225]; site III: 1219 ± 26 [1207-1232]; p = 0.067; for global T2 in ms: site I: 40 ± 2 [39-41]; site II: 40 ± 1 [39-41]; site III 39 ± 2 [39-41]; p = 0.543). CONCLUSION: Parametric mapping results displayed initial hints at a sufficient similarity between sites when confounders, such as field strength, vendor diversity, acquisition schemes and post-processing analysis are harmonized. This finding needs to be confirmed in a powered clinical trial. Trial registration ISRCTN14627679 (retrospectively registered).

Lazy Luna: Extendible software for multilevel reader comparison in cardiovascular magnetic resonance imaging.

BACKGROUND AND OBJECTIVES: Cardiovascular Magnetic Resonance (CMR) imaging is a growing field with increasing diagnostic utility in clinical routine. Quantitative diagnostic parameters are typically calculated based on contours or points provided by readers, e.g. natural intelligences (NI) such as clinicians or researchers, and artificial intelligences (AI). As clinical applications multiply, evaluating the precision and reproducibility of quantitative parameters becomes increasingly important. Although segmentation challenges for AIs and guidelines for clinicians provide quality assessments and regulation, the methods ought to be combined and streamlined for clinical applications. The goal of the developed software, Lazy Luna (LL), is to offer a flexible evaluation tool that is readily extendible to new sequences and scientific endeavours. METHODS: An interface was designed for LL, which allows for comparing annotated CMR images. Geometric objects ensure precise calculations of metric values and clinical results regardless of whether annotations originate from AIs or NIs. A graphical user interface (GUI) is provided to make the software available to non-programmers. The GUI allows for an interactive inspection of image datasets as well as implementing tracing procedures, which follow statistical reader differences in clinical results to their origins in individual image contours. The backend software builds on a set of meta-classes, which can be extended to new imaging sequences and clinical parameters. Following an agile development procedure with clinical feedback allows for a quick implementation of new classes, figures and tables for evaluation. RESULTS: Two application cases present LL's extendibility to clinical evaluation and AI development contexts. The first concerns T1 parametric mapping images segmented by two expert readers. Quantitative result differences are traced to reveal typical segmentation dissimilarities from which these differences originate. The meta-classes are extended to this new application scenario. The second applies to the open source Late Gadolinium Enhancement (LGE) quantification challenge for AI developers "Emidec", which illustrates LL's usability as open source software. CONCLUSION: The presented software Lazy Luna allows for an automated multilevel comparison of readers as well as identifying qualitative reasons for statistical reader differences. The open source software LL can be extended to new application cases in the future.

Multilevel comparison of deep learning models for function quantification in cardiovascular magnetic resonance: On the redundancy of architectural variations.

Background: Cardiac function quantification in cardiovascular magnetic resonance requires precise contouring of the heart chambers. This time-consuming task is increasingly being addressed by a plethora of ever more complex deep learning methods. However, only a small fraction of these have made their way from academia into clinical practice. In the quality assessment and control of medical artificial intelligence, the opaque reasoning and associated distinctive errors of neural networks meet an extraordinarily low tolerance for failure. Aim: The aim of this study is a multilevel analysis and comparison of the performance of three popular convolutional neural network (CNN) models for cardiac function quantification. Methods: U-Net, FCN, and MultiResUNet were trained for the segmentation of the left and right ventricles on short-axis cine images of 119 patients from clinical routine. The training pipeline and hyperparameters were kept constant to isolate the influence of network architecture. CNN performance was evaluated against expert segmentations for 29 test cases on contour level and in terms of quantitative clinical parameters. Multilevel analysis included breakdown of results by slice position, as well as visualization of segmentation deviations and linkage of volume differences to segmentation metrics via correlation plots for qualitative analysis. Results: All models showed strong correlation to the expert with respect to quantitative clinical parameters (rz ' = 0.978, 0.977, 0.978 for U-Net, FCN, MultiResUNet respectively). The MultiResUNet significantly underestimated ventricular volumes and left ventricular myocardial mass. Segmentation difficulties and failures clustered in basal and apical slices for all CNNs, with the largest volume differences in the basal slices (mean absolute error per slice: 4.2 ± 4.5 ml for basal, 0.9 ± 1.3 ml for midventricular, 0.9 ± 0.9 ml for apical slices). Results for the right ventricle had higher variance and more outliers compared to the left ventricle. Intraclass correlation for clinical parameters was excellent (≥0.91) among the CNNs. Conclusion: Modifications to CNN architecture were not critical to the quality of error for our dataset. Despite good overall agreement with the expert, errors accumulated in basal and apical slices for all models.

Introduction of a cascaded segmentation pipeline for parametric T1 mapping in cardiovascular magnetic resonance to improve segmentation performance.

The manual and often time-consuming segmentation of the myocardium in cardiovascular magnetic resonance is increasingly automated using convolutional neural networks (CNNs). This study proposes a cascaded segmentation (CASEG) approach to improve automatic image segmentation quality. First, an object detection algorithm predicts a bounding box (BB) for the left ventricular myocardium whose 1.5 times enlargement defines the region of interest (ROI). Then, the ROI image section is fed into a U-Net based segmentation. Two CASEG variants were evaluated: one using the ROI cropped image solely (cropU) and the other using a 2-channel-image additionally containing the original BB image section (crinU). Both were compared to a classical U-Net segmentation (refU). All networks share the same hyperparameters and were tested on basal and midventricular slices of native and contrast enhanced (CE) MOLLI T1 maps. Dice Similarity Coefficient improved significantly (p < 0.05) in cropU and crinU compared to refU (81.06%, 81.22%, 72.79% for native and 80.70%, 79.18%, 71.41% for CE data), while no significant improvement (p < 0.05) was achieved in the mean absolute error of the T1 time (11.94 ms, 12.45 ms, 14.22 ms for native and 5.32 ms, 6.07 ms, 5.89 ms for CE data). In conclusion, CASEG provides an improved geometric concordance but needs further improvement in the quantitative outcome.

Introduction of Lazy Luna an automatic software-driven multilevel comparison of ventricular function quantification in cardiovascular magnetic resonance imaging.

Cardiovascular magnetic resonance imaging is the gold standard for cardiac function assessment. Quantification of clinical results (CR) requires precise segmentation. Clinicians statistically compare CRs to ensure reproducibility. Convolutional Neural Network developers compare their results via metrics. Aim: Introducing software capable of automatic multilevel comparison. A multilevel analysis covering segmentations and CRs builds on a generic software backend. Metrics and CRs are calculated with geometric accuracy. Segmentations and CRs are connected to track errors and their effects. An interactive GUI makes the software accessible to different users. The software's multilevel comparison was tested on a use case based on cardiac function assessment. The software shows good reader agreement in CRs and segmentation metrics (Dice > 90%). Decomposing differences by cardiac position revealed excellent agreement in midventricular slices: > 90% but poorer segmentations in apical (> 71%) and basal slices (> 74%). Further decomposition by contour type locates the largest millilitre differences in the basal right cavity (> 3 ml). Visual inspection shows these differences being caused by different basal slice choices. The software illuminated reader differences on several levels. Producing spreadsheets and figures concerning metric values and CR differences was automated. A multilevel reader comparison is feasible and extendable to other cardiac structures in the future.