Dataset Information

Automated quantification of myocardial tissue characteristics from native T₁ mapping using neural networks with uncertainty-based quality-control.

ABSTRACT:

Background

Tissue characterisation with cardiovascular magnetic resonance (CMR) parametric mapping has the potential to detect and quantify both focal and diffuse alterations in myocardial structure not assessable by late gadolinium enhancement. Native T₁ mapping in particular has shown promise as a useful biomarker to support diagnostic, therapeutic and prognostic decision-making in ischaemic and non-ischaemic cardiomyopathies.

Methods

Convolutional neural networks (CNNs) with Bayesian inference are a category of artificial neural networks which model the uncertainty of the network output. This study presents an automated framework for tissue characterisation from native shortened modified Look-Locker inversion recovery ShMOLLI T₁ mapping at 1.5 T using a Probabilistic Hierarchical Segmentation (PHiSeg) network (PHCUMIS 119-127, 2019). In addition, we use the uncertainty information provided by the PHiSeg network in a novel automated quality control (QC) step to identify uncertain T₁ values. The PHiSeg network and QC were validated against manual analysis on a cohort of the UK Biobank containing healthy subjects and chronic cardiomyopathy patients (N=100 for the PHiSeg network and N=700 for the QC). We used the proposed method to obtain reference T₁ ranges for the left ventricular (LV) myocardium in healthy subjects as well as common clinical cardiac conditions.

Results

T₁ values computed from automatic and manual segmentations were highly correlated (r=0.97). Bland-Altman analysis showed good agreement between the automated and manual measurements. The average Dice metric was 0.84 for the LV myocardium. The sensitivity of detection of erroneous outputs was 91%. Finally, T₁ values were automatically derived from 11,882 CMR exams from the UK Biobank. For the healthy cohort, the mean (SD) corrected T₁ values were 926.61 (45.26), 934.39 (43.25) and 927.56 (50.36) for global, interventricular septum and free-wall respectively.

Conclusions

The proposed pipeline allows for automatic analysis of myocardial native T₁ mapping and includes a QC process to detect potentially erroneous results. T₁ reference values were presented for healthy subjects and common clinical cardiac conditions from the largest cohort to date using T₁-mapping images.

SUBMITTER: Puyol-Anton E

PROVIDER: S-EPMC7439533 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated quantification of myocardial tissue characteristics from native T<sub>1</sub> mapping using neural networks with uncertainty-based quality-control.

Puyol-Antón Esther E Ruijsink Bram B Baumgartner Christian F CF Masci Pier-Giorgio PG Sinclair Matthew M Konukoglu Ender E Razavi Reza R King Andrew P AP

Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance 20200820 1

<h4>Background</h4>Tissue characterisation with cardiovascular magnetic resonance (CMR) parametric mapping has the potential to detect and quantify both focal and diffuse alterations in myocardial structure not assessable by late gadolinium enhancement. Native T<sub>1</sub> mapping in particular has shown promise as a useful biomarker to support diagnostic, therapeutic and prognostic decision-making in ischaemic and non-ischaemic cardiomyopathies.<h4>Methods</h4>Convolutional neural networks (CN ...[more]

PMID: 32814579

Similar Datasets

Project description:BackgroundCardiovascular magnetic resonance (CMR) myocardial native T1 mapping allows assessment of interstitial diffuse fibrosis. In this technique, the global and regional T1 are measured manually by drawing region of interest in motion-corrected T1 maps. The manual analysis contributes to an already lengthy CMR analysis workflow and impacts measurements reproducibility. In this study, we propose an automated method for combined myocardium segmentation, alignment, and T1 calculation for myocardial T1 mapping.MethodsA deep fully convolutional neural network (FCN) was used for myocardium segmentation in T1 weighted images. The segmented myocardium was then resampled on a polar grid, whose origin is located at the center-of-mass of the segmented myocardium. Myocardium T1 maps were reconstructed from the resampled T1 weighted images using curve fitting. The FCN was trained and tested using manually segmented images for 210 patients (5 slices, 11 inversion times per patient). An additional image dataset for 455 patients (5 slices and 11 inversion times per patient), analyzed by an expert reader using a semi-automatic tool, was used to validate the automatically calculated global and regional T1 values. Bland-Altman analysis, Pearson correlation coefficient, r, and the Dice similarity coefficient (DSC) were used to evaluate the performance of the FCN-based analysis on per-patient and per-slice basis. Inter-observer variability was assessed using intraclass correlation coefficient (ICC) of the T1 values calculated by the FCN-based automatic method and two readers.ResultsThe FCN achieved fast segmentation (<?0.3?s/image) with high DSC (0.85?±?0.07). The automatically and manually calculated T1 values (1091?±?59?ms and 1089?±?59?ms, respectively) were highly correlated in per-patient (r?=?0.82; slope?=?1.01; p?<?0.0001) and per-slice (r?=?0.72; slope?=?1.01; p?<?0.0001) analyses. Bland-Altman analysis showed good agreement between the automated and manual measurements with 95% of measurements within the limits-of-agreement in both per-patient and per-slice analyses. The intraclass correllation of the T1 calculations by the automatic method vs reader 1 and reader 2 was respectively 0.86/0.56 and 0.74/0.49 in the per-patient/per-slice analyses, which were comparable to that between two expert readers (=0.72/0.58 in per-patient/per-slice analyses).ConclusionThe proposed FCN-based image processing platform allows fast and automatic analysis of myocardial native T1 mapping images mitigating the burden and observer-related variability of manual analysis.

Project description:Background Cardiac MRI late gadolinium enhancement (LGE) scar volume is an important marker for outcome prediction in patients with hypertrophic cardiomyopathy (HCM); however, its clinical application is hindered by a lack of measurement standardization. Purpose To develop and evaluate a three-dimensional (3D) convolutional neural network (CNN)-based method for automated LGE scar quantification in patients with HCM. Materials and Methods We retrospectively identified LGE MRI data in a multicenter (n = 7) and multivendor (n = 3) HCM study obtained between November 2001 and November 2011. A deep 3D CNN based on U-Net architecture was used for LGE scar quantification. Independent CNN training and testing data sets were maintained with a 4:1 ratio. Stacks of short-axis MRI slices were split into overlapping substacks that were segmented and then merged into one volume. The 3D CNN per-site and per-vendor performances were evaluated with respect to manual scar quantification performed in a core laboratory setting using Dice similarity coefficient (DSC), Pearson correlation, and Bland-Altman analyses. Furthermore, the performance of 3D CNN was compared with that of two-dimensional (2D) CNN. Results This study included 1073 patients with HCM (733 men; mean age, 49 years ± 17 [standard deviation]). The 3D CNN-based quantification was fast (0.15 second per image) and demonstrated excellent correlation with manual scar volume quantification (r = 0.88, P < .001) and ratio of scar volume to total left ventricle myocardial volume (%LGE) (r = 0.91, P < .001). The 3D CNN-based quantification strongly correlated with manual quantification of scar volume (r = 0.82-0.99, P < .001) and %LGE (r = 0.90-0.97, P < .001) for all sites and vendors. The 3D CNN identified patients with a large scar burden (>15%) with 98% accuracy (202 of 207) (95% confidence interval [CI]: 95%, 99%). When compared with 3D CNN, 2D CNN underestimated scar volume (r = 0.85, P < .001) and %LGE (r = 0.83, P < .001). The DSC of 3D CNN segmentation was comparable among different vendors (P = .07) and higher than that of 2D CNN (DSC, 0.54 ± 0.26 vs 0.48 ± 0.29; P = .02). Conclusion In the hypertrophic cardiomyopathy population, a three-dimensional convolutional neural network enables fast and accurate quantification of myocardial scar volume, outperforms a two-dimensional convolutional neural network, and demonstrates comparable performance across different vendors. © RSNA, 2019 Online supplemental material is available for this article.

Project description:BackgroundQuantification of myocardial blood flow (MBF) from dynamic contrast-enhanced (DCE) MRI can be performed using a signal intensity model that incorporates T1 values of blood and myocardium.PurposeTo assess the impact of T1 values on pixelwise MBF quantification, specifically to evaluate the influence of 1) study population-averaged vs. subject-specific, 2) diastolic vs. systolic, and 3) regional vs. global myocardial T1 values.Study typeProspective.SubjectsFifteen patients with chronic coronary heart disease.Field strength/sequence3T; modified Look-Locker inversion recovery for T1 mapping and saturation recovery gradient echo for DCE imaging, both acquired in a mid-ventricular short-axis slice in systole and diastole.AssessmentMBF was estimated using Fermi modeling and signal intensity nonlinearity correction with different T1 values: study population-averaged blood and myocardial, subject-specific systolic and diastolic, and segmental T1 values. Myocardial segments with perfusion deficits were identified visually from DCE series.Statistical testsThe relationships between MBF parameters derived by different methods were analyzed by Bland-Altman analysis; corresponding mean values were compared by t-test.ResultsUsing subject-specific diastolic T1 values, global diastolic MBF was 0.61?±?0.13?mL/(min·g). It did not differ from global MBF derived from the study population-averaged T1 (P = 0.88), but the standard deviation of differences was large (0.07?mL/(min·g), 11% of mean MBF). Global diastolic and systolic MBF did not differ (P = 0.12), whereas global diastolic MBF using systolic (0.62?±?0.13?mL/(min·g)) and diastolic T1 values differed (P?<?0.05). If regional instead of global T1 values were used, segmental MBF was lower in segments with perfusion deficits (bias = -0.03?mL/(min·g), -7% of mean MBF, P?<?0.05) but higher in segments without perfusion deficits (bias = 0.01?mL/(min·g), 1% of mean MBF, P?<?0.05).Data conclusionWhereas cardiac phase-specific T1 values have a minor impact on MBF estimates, subject-specific and myocardial segment-specific T1 values substantially affect MBF quantification.Level of evidence3 TECHNICAL EFFICACY STAGE: 3.

Dataset Information

Automated quantification of myocardial tissue characteristics from native T₁ mapping using neural networks with uncertainty-based quality-control.

Background

Methods

Results

Conclusions

Publications

Automated quantification of myocardial tissue characteristics from native T<sub>1</sub> mapping using neural networks with uncertainty-based quality-control.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Dataset Information

Automated quantification of myocardial tissue characteristics from native T1 mapping using neural networks with uncertainty-based quality-control.

Background

Methods

Results

Conclusions

Publications

Automated quantification of myocardial tissue characteristics from native T<sub>1</sub> mapping using neural networks with uncertainty-based quality-control.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Automated quantification of myocardial tissue characteristics from native T₁ mapping using neural networks with uncertainty-based quality-control.