Automated analysis of cardiovascular magnetic resonance myocardial native T1 mapping images using fully convolutional neural networks

Abstract

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.Electronic supplementary materialThe online version of this article (10.1186/s12968-018-0516-1) contains supplementary material, which is available to authorized users.

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

“…In the context of CMR imaging, semi-automatic and automatic techniques for cardiac cine [9,10] and flow [12] imaging have been developed. One paper has proposed an automated segmentation method for native T 1 maps [11]. However, this method only extracted global left ventricle (LV) myocardial T 1 values, whereas regional assessment of septal and/or focal lesion T 1 values is typically used to characterise diseases [13,14].…”

Cardiac T1 mapping: Techniques and applications

“…Such techniques have already been applied to CMR image analysis, where it has been used for segmentation of cine images and automatic calculation of functional and anatomical parameters, including ejection fraction and myocardial mass. Similarly, a fully convolutional neural network has been proposed for the automated segmentation of native T 1 maps, potentially offering a faster and less operator‐dependent workflow …”

Artificial intelligence in pediatric and adult congenital cardiac MRI: an unmet clinical need

“…Fahmy et al (100) initially introduced the proofof-concept for using deep convolutional neural networks (DCN) to automatically quantify LV mass and scar volume on CMR data with late gadolinium enhancement in patients with hypertrophic cardiomyopathy. More recently, they (99) have developed and evaluated a fully automated analysis platform for myocardial T 1 mapping using FCNs. Their method automates the analysis of short-axis T 1 weighted images to estimate the myocardium T 1 values and was evaluated against manual T 1 calculation.…”