scholarly journals MOCOnet: Robust Motion Correction of Cardiovascular Magnetic Resonance T1 Mapping Using Convolutional Neural Networks

2021 ◽  
Vol 8 ◽  
Author(s):  
Ricardo A. Gonzales ◽  
Qiang Zhang ◽  
Bartłomiej W. Papież ◽  
Konrad Werys ◽  
Elena Lukaschuk ◽  
...  
Keyword(s):  
Cardiovascular Magnetic Resonance ◽  
Magnetic Resonance ◽  
Image Registration ◽  
Range Of Motion ◽  
Motion Correction ◽  
T1 Mapping ◽  
Motion Artefacts ◽  
Baseline Method ◽  
Clinical Interpretation ◽  
Wide Range

Background: Quantitative cardiovascular magnetic resonance (CMR) T1 mapping has shown promise for advanced tissue characterisation in routine clinical practise. However, T1 mapping is prone to motion artefacts, which affects its robustness and clinical interpretation. Current methods for motion correction on T1 mapping are model-driven with no guarantee on generalisability, limiting its widespread use. In contrast, emerging data-driven deep learning approaches have shown good performance in general image registration tasks. We propose MOCOnet, a convolutional neural network solution, for generalisable motion artefact correction in T1 maps.Methods: The network architecture employs U-Net for producing distance vector fields and utilises warping layers to apply deformation to the feature maps in a coarse-to-fine manner. Using the UK Biobank imaging dataset scanned at 1.5T, MOCOnet was trained on 1,536 mid-ventricular T1 maps (acquired using the ShMOLLI method) with motion artefacts, generated by a customised deformation procedure, and tested on a different set of 200 samples with a diverse range of motion. MOCOnet was compared to a well-validated baseline multi-modal image registration method. Motion reduction was visually assessed by 3 human experts, with motion scores ranging from 0% (strictly no motion) to 100% (very severe motion).Results: MOCOnet achieved fast image registration (<1 second per T1 map) and successfully suppressed a wide range of motion artefacts. MOCOnet significantly reduced motion scores from 37.1±21.5 to 13.3±10.5 (p < 0.001), whereas the baseline method reduced it to 15.8±15.6 (p < 0.001). MOCOnet was significantly better than the baseline method in suppressing motion artefacts and more consistently (p = 0.007).Conclusion: MOCOnet demonstrated significantly better motion correction performance compared to a traditional image registration approach. Salvaging data affected by motion with robustness and in a time-efficient manner may enable better image quality and reliable images for immediate clinical interpretation.

scholarly journals Motion correction for myocardial T1 mapping using image registration with synthetic image estimation

2011 ◽  
Vol 67 (6) ◽  
pp. 1644-1655 ◽  
Author(s):  
Hui Xue ◽  
Saurabh Shah ◽  
Andreas Greiser ◽  
Christoph Guetter ◽  
Arne Littmann ◽  
...  
Keyword(s):  
Image Registration ◽  
Motion Correction ◽  
T1 Mapping ◽  
Synthetic Image ◽  
Image Estimation ◽  
Myocardial T1

scholarly journals Identification and Assessment of Anderson-Fabry Disease by Cardiovascular Magnetic Resonance Noncontrast Myocardial T1 Mapping

2013 ◽  
Vol 6 (3) ◽  
pp. 392-398 ◽  
Author(s):  
Daniel M. Sado ◽  
Steven K. White ◽  
Stefan K. Piechnik ◽  
Sanjay M. Banypersad ◽  
Thomas Treibel ◽  
...  
Keyword(s):  
Cardiovascular Magnetic Resonance ◽  
Magnetic Resonance ◽  
Fabry Disease ◽  
T1 Mapping ◽  
Myocardial T1

Insight form cardiovascular magnetic resonance on cardiac sarcoidosis: a single centre experience

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
C Alderighi ◽  
A Baritussio ◽  
O Ozden Tok ◽  
M Perazzolo Marra ◽  
S Iliceto ◽  
...  
Keyword(s):  
Cardiovascular Magnetic Resonance ◽  
Magnetic Resonance ◽  
T1 Mapping ◽  
Cardiac Involvement ◽  
Cardiac Sarcoidosis ◽  
T2 Mapping ◽  
Left Ventricular ◽  
Lv Function ◽  
Post Contrast ◽  
Lv Volumes

Abstract Background Clinically manifest cardiac sarcoidosis (CS) has a prevalence of 5%, but is more frequent in autoptic series (25%). Diagnosis is multiparametric and relies on clinical criteria and imaging findings, although a certain diagnosis, especially in the case of isolated CS (ICS), can only be based on endomyocardial biopsy. Cardiovascular magnetic resonance (CMR) has a comprehensive role in the assessment of CS: left ventricular (LV) dysfunction and extent of late gadolinium enhancement (LGE)are important predictors of prognosis, T2 mapping provides information on disease activity and global longitudinal strain (GLS) analysis can uncover subclinical LV impairment. Purpose To assess the prevalence of CS by CMR in patients with biopsy-proven extracardiacsarcoidosis (ECS); to describe the imaging characteristics of patients with ECS and those with high clinical suspicionof ICS; to investigate the contribution of more recent techniques to the diagnosis of CS alongside traditional LGE assessment. Methods We retrospectively enrolled 84 patients (66% males, mean age 59±13 years) referred to our centreforsuspected CS (biopsy-proven ECS, n=61; clinical presentation suggestive of CS,, n=23). CMR was performed on a 1.5T scanner, with a protocol comprehensive of biventricular functional assessment and post-contrast images; T2-STIR images (n=30), native myocardial T1 mapping (n=24) and T2 mapping (n=19) were also performed in selected patients. Tissue tracking analysis was perfomed in all patients using a dedicated software. Results Based on CMR findings, 35 patients (42%) with ECS did not show cardiac involvement (SS), 26 (31%) showed both cardiac and systemic involvement (CS-SS) and 23 (27%) had evidence of ICS (ICS). 43% of patients had history of arrhythmias, but life-threatening tachyarrhythmiaswere more frequent in patients with CS (p=0.02).Patients with CS had significantly lower LVEF (p<0,01), larger LV volumes (p<0,01) and greater LV mass (p<0,01). GLS values were impaired in all the groups but significantly more in patients with CS (p<0,01). With regards to LGE distribution, ICS patients showed a higher number of segments involved (p=0,011) as compared to CS patients. T2-STIRimages were positive in 3 out of 30 patients; T2 mapping detected myocardial oedema in 1 patient with negative T2- STIR and was positive in 7 who did not undergo traditional oedema evaluation. T1 mapping mainly confirmed the results provided by LGE, but was altered in 1 patient who could not receive gadolinium. Conclusions CMR findings consistent with CS were found in 49 patients referred for suspected CS. Patients with cardiac involvement, particularly if isolated, had significantly lower LVEF, greater LV volumes and more impaired GLS. Patients with SS, despite a normal LV function, showed mildly impaired GLS, subtending subclinical cardiac involvement. Funding Acknowledgement Type of funding source: None

scholarly journals Cardiovascular magnetic resonance in hypertrophic cardiomyopathy and infiltrative cardiomyopathy

2016 ◽  
Vol 20 (2) ◽  
Author(s):  
Rebecca Schofield ◽  
Katia Manacho ◽  
Silvia Castelletti ◽  
James C. Moon
Keyword(s):  
Cardiovascular Magnetic Resonance ◽  
Hypertrophic Cardiomyopathy ◽  
Magnetic Resonance ◽  
T1 Mapping ◽  
Strong Predictor ◽  
Extracellular Volume ◽  
Hypertensive Heart Disease ◽  
Left Ventricular ◽  
Tissue Characterisation ◽  
Alcohol Ablation

Hypertrophic cardiomyopathy (HCM) is the most common inherited cardiac disease. Cardiac imaging plays a key role in the diagnosis and management, with cardiovascular magnetic resonance (CMR) an important modality. CMR provides a number of different techniques in one examination: structure and function, flow imaging and tissue characterisation particularly with the late gadolinium enhancement (LGE) technique. Other techniques include vasodilator perfusion, mapping (especially T1 mapping and extracellular volume quantification [ECV]) and diffusion-weighted imaging with its potential to detect disarray. Clinically, the uses of CMR are diverse. The imaging must be considered within the context of work-up, particularly the personal and family history, Electrocardiogram (ECG) and echocardiogram findings. Subtle markers of possible HCM can be identified in genotype positive left ventricular hypertrophy (LVH)-negative subjects. CMR has particular advantages for assessment of the left ventricle (LV) apex and is able to detect both missed LVH (apical and basal antero-septum), when the echocardiography is normal but the ECG abnormal. CMR is important in distinguishing HCM from both common phenocopies (hypertensive heart disease, athletic adaptation, ageing related changes) and rarer pheno and/or genocopies such as Fabry disease and amyloidosis. For these, in particular the LGE technique and T1 mapping are very useful with a low T1 in Fabry’s, and high T1 and very high ECV in amyloidosis. Moreover, the tissue characterisation that is possible using CMR offers a potential role in patient risk stratification, as scar is a very strong predictor of future heart failure. Scar may also play a role in the prediction of sudden death. CMR is helpful in follow-up assessment, especially after septal alcohol ablation and myomectomy.

Sign in / Sign up

Export Citation Format

Share Document