Dataset Information

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

ABSTRACT: 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.

SUBMITTER: Hadler T

PROVIDER: S-EPMC9033783 | biostudies-literature | 2022 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Hadler Thomas T Wetzl Jens J Lange Steffen S Geppert Christian C Fenski Max M Abazi Endri E Gröschel Jan J Ammann Clemens C Wenson Felix F Töpper Agnieszka A Däuber Sascha S Schulz-Menger Jeanette J

Scientific reports 20220422 1

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 wi ...[more]

PMID: 35459270

Similar Datasets

Project description:BackgroundThe beating heart is the generator of blood flow through the cardiovascular system. Within the heart's own chambers, normal complex blood flow patterns can be disturbed by diseases. Methods for the quantification of intra-cardiac blood flow, with its 4D (3D+time) nature, are lacking. We sought to develop and validate a novel semi-automatic analysis approach that integrates flow and morphological data.MethodIn six healthy subjects and three patients with dilated cardiomyopathy, three-directional, three-dimensional cine phase-contrast cardiovascular magnetic resonance (CMR) velocity data and balanced steady-state free-precession long- and short-axis images were acquired. The LV endocardium was segmented from the short-axis images at the times of isovolumetric contraction (IVC) and isovolumetric relaxation (IVR). At the time of IVC, pathlines were emitted from the IVC LV blood volume and traced forwards and backwards in time until IVR, thus including the entire cardiac cycle. The IVR volume was used to determine if and where the pathlines left the LV. This information was used to automatically separate the pathlines into four different components of flow: Direct Flow, Retained Inflow, Delayed Ejection Flow and Residual Volume. Blood volumes were calculated for every component by multiplying the number of pathlines with the blood volume represented by each pathline. The accuracy and inter- and intra-observer reproducibility of the approach were evaluated by analyzing volumes of LV inflow and outflow, the four flow components, and the end-diastolic volume.ResultsThe volume and distribution of the LV flow components were determined in all subjects. The calculated LV outflow volumes [ml] (67 +/- 13) appeared to fall in between those obtained by through-plane phase-contrast CMR (77 +/- 16) and Doppler ultrasound (58 +/- 10), respectively. Calculated volumes of LV inflow (68 +/- 11) and outflow (67 +/- 13) were well matched (NS). Low inter- and intra-observer variability for the assessment of the volumes of the flow components was obtained.ConclusionsThis semi-automatic analysis approach for the quantification of 4D blood flow resulted in accurate LV inflow and outflow volumes and a high reproducibility for the assessment of LV flow components.

Project description:BackgroundAutomatic analyses of echocardiograms may support inexperienced users in quantifying left ventricular (LV) function. We have developed an algorithm for fully automatic measurements of mitral annular plane systolic excursion (MAPSE) and mitral annular systolic (S') and early diastolic (e') peak velocities. We aimed to study the influence of user experience of automatic measurements of these indices in echocardiographic recordings acquired by medical students and clinicians.MethodsWe included 75 consecutive patients referred for echocardiography at a university hospital. The patients underwent echocardiography by clinicians (cardiologists, cardiology residents and sonographers), who obtained manual reference measurements of MAPSE by M-mode and of S' and e' by colour tissue Doppler imaging (cTDI). Immediately after, each patient was examined by 1 of 39 medical students who were instructed in image acquisition on the day of participation. Each student acquired cTDI recordings from 1 to 4 patients. All cTDI recordings by students and clinicians were analysed for MAPSE, S' and e' using a fully automatic algorithm. The automatic measurements were compared to the manual reference measurements.ResultsCorrect tracking of the mitral annulus was feasible in 50 (67%) and 63 (84%) of the students' and clinicians' recordings, respectively (p = 0.007). Image quality was highest in the clinicians' recordings. Mean difference ± standard deviation of the automatic measurements of the students' recordings compared to the manual reference was - 0.0 ± 2.0 mm for MAPSE, 0.3 ± 1.1 cm/s for S' and 0.6 ± 1.4 cm/s for e'. The corresponding intraclass correlation coefficients for MAPSE, S' and e' were 0.85 (good), 0.89 (good) and 0.92 (excellent), respectively. Automatic measurements from the students' and clinicians' recordings were in similar agreement with the reference when mitral annular tracking was correct.ConclusionsIn case of correct tracking of the mitral annulus, the agreement with reference for the automatic measurements was overall good. Low image quality reduced feasibility. Adequate image acquisition is essential for automatic analyses of LV function indices, and thus, appropriate education of the operators is mandatory. Automatic measurements may help inexperienced users of ultrasound, but do not remove the need for dedicated education and training.

Project description:BackgroundQuantitative results of cardiovascular magnetic resonance (CMR) image analysis influence clinical decision making. Image analysis is performed based on dedicated software. The manufacturers provide different analysis tools whose algorithms are often unknown. The aim of this study was to evaluate the impact of software on quantification of left ventricular (LV) assessment, 2D flow measurement and T1- and T2-parametric mapping.MethodsThirty-one data sets of patients who underwent a CMR Scan on 1.5 T were analyzed using three different software (Circle CVI: cvi42, Siemens Healthineers: Argus, Medis: Qmass/Qflow) by one reader blinded to former results. Cine steady state free precession short axis images were analyzed regarding LV ejection fraction (EF), end-systolic and end-diastolic volume (ESV, EDV) and LV mass. Phase-contrast magnetic resonance images were evaluated for forward stroke volume (SV) and peak velocity (Vmax). Pixel-wise generated native T1- and T2-maps were used to assess T1- and T2-time. Forty-five data sets were evaluated twice (15 per software) for intraobserver analysis. Equivalence was considered if the confidence interval of a paired assessment of two sofware was within a tolerance interval defined by ±1.96 highest standard deviation obtained by intraobserver analysis.ResultsFor each parameter, thirty data sets could be analyzed with all three software. All three software (A/B, A/C, B/C) were considered equivalent for LV EF, EDV, ESV, mass, 2D flow SV and T2-time. Differences between software were detected in flow measurement for Vmax and in parametric mapping for T1-time. For Vmax, equivalence was given between software A and C and for T1-time equivalence was given between software B and C.ConclusionSoftware had no impact on quantitative results of LV assessment, T2-time and SV based on 2D flow. In contrast to that, Vmax and T1-time may be influenced by software. CMR reports should contain the name and version of the software applied for image analysis to avoid misinterpretation upon follow-up and research examinations.Trial registrationISRCTN12210850 . Registered 14 July 2017, retrospectively registered.

Project description:BackgroundArrhythmogenic right ventricular cardiomyopathy (ARVC) is diagnosed according to the Task Force Criteria (TFC) in which cardiovascular magnetic resonance (CMR) imaging plays an important role. Our study aims to apply an automatic deep learning-based segmentation for right and left ventricular CMR assessment and evaluate this approach for classification of the CMR TFC.MethodsWe included 227 subjects suspected of ARVC who underwent CMR. Subjects were classified into (1) ARVC patients fulfilling TFC; (2) at-risk family members; and (3) controls. To perform automatic segmentation, a Bayesian Dilated Residual Neural Network was trained and tested. Performance of automatic versus manual segmentation was assessed using Dice-coefficient and Hausdorff distance. Since automatic segmentation is most challenging in basal slices, manual correction of the automatic segmentation in the most basal slice was simulated (automatic-basal). CMR TFC calculated using manual and automatic-basal segmentation were compared using Cohen's Kappa (κ).ResultsAutomatic segmentation was trained on CMRs of 70 subjects (39.6 ± 18.1 years, 47% female) and tested on 157 subjects (36.9 ± 17.6 years, 59% female). Dice-coefficient and Hausdorff distance showed good agreement between manual and automatic segmentations (≥ 0.89 and ≤ 10.6 mm, respectively) which further improved after simulated correction of the most basal slice (≥ 0.92 and ≤ 9.2 mm, p < 0.001). Pearson correlation of volumetric and functional CMR measurements was good to excellent (automatic (r = 0.78-0.99, p < 0.001) and automatic-basal (r = 0.88-0.99, p < 0.001) measurements). CMR TFC classification using automatic-basal segmentations was comparable to manual segmentations (κ 0.98 ± 0.02) with comparable diagnostic performance.ConclusionsCombining automatic segmentation of CMRs with correction of the most basal slice results in accurate CMR TFC classification of subjects suspected of ARVC.

Project description:BackgroundRight ventricular hypertrophy (RVH) provides a key remodeling index alterable by pulmonary hypertension. Although echocardiography commonly integrates linear wall thickness and chamber dimensions to quantify left ventricular remodeling, the utility of an equivalent right ventricular (RV)-based approach is unknown.MethodsThis was a retrospective analysis of 200 patients undergoing transthoracic echocardiography and cardiac magnetic resonance (CMR) within 30 days (median = 3 days; interquartile range, 15 days), stratified by echocardiography-quantified pulmonary artery systolic pressure (<35, 35 to <55, 55 to <75, or ≥75 mm Hg). Echocardiographic assessment included RV linear dimensions in parasternal long-axis and apical four-chamber views and wall thicknesses in parasternal long-axis, four-chamber, and subcostal views. Subcostal wall thickness was integrated with chamber diameters to calculate RV mass, which was tested in relation to CMR-quantified RV mass and all-cause mortality.ResultsEchocardiography-based quantification of all linear dimensions was feasible in 95% of patients (190 of 200). RV wall thicknesses in all orientations increased in relation to pulmonary artery systolic pressure (P < .001) and was greater among patients with, versus those without, CMR-evidenced RVH (P < .001 for all). Correlations between echocardiography and CMR were greatest for RV basal diameter (r = 0.73), RV subcostal wall thickness (r = 0.71), and global RV mass (r = 0.82; P < .001 for all). Echocardiography-derived global RV mass cutoffs were established in a derivation cohort and tested in a validation cohort. Results demonstrated good sensitivity and specificity (75.5% and 74.0%, respectively) in relation to CMR-quantified RVH. During follow-up (median, 4.2 years), 18% of patients (n = 36) died. Echocardiography-evidenced RVH (hazard ratio, 1.98; 95% CI, 1.09-3.88; P = .048) conferred similar mortality risk compared with RVH on CMR (hazard ratio, 2.41; 95% CI, 1.22-4.78; P = .01).ConclusionsEchocardiography-quantified RV parameters provide a robust index of RV afterload. Global RV mass calculated using a novel echocardiographic formula based on readily available linear indices yields good diagnostic performance for CMR-evidenced RVH and confers increased mortality risk.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets