Dataset Information

Improvement of late gadolinium enhancement image quality using a deep learning-based reconstruction algorithm and its influence on myocardial scar quantification.

ABSTRACT:

Objectives

The aim of this study was to assess the effect of a deep learning (DL)-based reconstruction algorithm on late gadolinium enhancement (LGE) image quality and to evaluate its influence on scar quantification.

Methods

Sixty patients (46 ± 17 years, 50% male) with suspected or known cardiomyopathy underwent CMR. Short-axis LGE images were reconstructed using the conventional reconstruction and a DL network (DLRecon) with tunable noise reduction (NR) levels from 0 to 100%. Image quality of standard LGE images and DLRecon images with 75% NR was scored using a 5-point scale (poor to excellent). In 30 patients with LGE, scar size was quantified using thresholding techniques with different standard deviations (SD) above remote myocardium, and using full width at half maximum (FWHM) technique in images with varying NR levels.

Results

DLRecon images were of higher quality than standard LGE images (subjective quality score 3.3 ± 0.5 vs. 3.6 ± 0.7, p < 0.001). Scar size increased with increasing NR levels using the SD methods. With 100% NR level, scar size increased 36%, 87%, and 138% using 2SD, 4SD, and 6SD quantification method, respectively, compared to standard LGE images (all p values < 0.001). However, with the FWHM method, no differences in scar size were found (p = 0.06).

Conclusions

LGE image quality improved significantly using a DL-based reconstruction algorithm. However, this algorithm has an important impact on scar quantification depending on which quantification technique is used. The FWHM method is preferred because of its independency of NR. Clinicians should be aware of this impact on scar quantification, as DL-based reconstruction algorithms are being used.

Key points

• The image quality based on (subjective) visual assessment and image sharpness of late gadolinium enhancement images improved significantly using a deep learning-based reconstruction algorithm that aims to reconstruct high signal-to-noise images using a denoising technique. • Special care should be taken when scar size is quantified using thresholding techniques with different standard deviations above remote myocardium because of the large impact of these advanced image enhancement algorithms. • The full width at half maximum method is recommended to quantify scar size when deep learning algorithms based on noise reduction are used, as this method is the least sensitive to the level of noise and showed the best agreement with visual late gadolinium enhancement assessment.

SUBMITTER: van der Velde N

PROVIDER: S-EPMC8128730 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundQuantification of myocardium scarring in late gadolinium enhanced (LGE) cardiac magnetic resonance imaging can be challenging due to low scar-to-background contrast and low image quality. To resolve ambiguous LGE regions, experienced readers often use conventional cine sequences to accurately identify the myocardium borders.PurposeTo develop a deep learning model for combining LGE and cine images to improve the robustness and accuracy of LGE scar quantification.Study typeRetrospective.PopulationA total of 191 hypertrophic cardiomyopathy patients: 1) 162 patients from two sites randomly split into training (50%; 81 patients), validation (25%, 40 patients), and testing (25%; 41 patients); and 2) an external testing dataset (29 patients) from a third site.Field strength/sequence1.5T, inversion-recovery segmented gradient-echo LGE and balanced steady-state free-precession cine sequences ASSESSMENT: Two convolutional neural networks (CNN) were trained for myocardium and scar segmentation, one with and one without LGE-Cine fusion. For CNN with fusion, the input was two aligned LGE and cine images at matched cardiac phase and anatomical location. For CNN without fusion, only LGE images were used as input. Manual segmentation of the datasets was used as reference standard.Statistical testsManual and CNN-based quantifications of LGE scar burden and of myocardial volume were assessed using Pearson linear correlation coefficients (r) and Bland-Altman analysis.ResultsBoth CNN models showed strong agreement with manual quantification of LGE scar burden and myocardium volume. CNN with LGE-Cine fusion was more robust than CNN without LGE-Cine fusion, allowing for successful segmentation of significantly more slices (603 [95%] vs. 562 (89%) of 635 slices; P < 0.001). Also, CNN with LGE-Cine fusion showed better agreement with manual quantification of LGE scar burden than CNN without LGE-Cine fusion (%ScarLGE-cine = 0.82 × %Scarmanual , r = 0.84 vs. %ScarLGE = 0.47 × %Scarmanual , r = 0.81) and myocardium volume (VolumeLGE-cine = 1.03 × Volumemanual , r = 0.96 vs. VolumeLGE = 0.91 × Volumemanual , r = 0.91).Data conclusionCNN based LGE-Cine fusion can improve the robustness and accuracy of automated scar quantification.Level of evidence3 TECHNICAL EFFICACY: 1.

Project description:BackgroundAutomatic myocardial scar segmentation from late gadolinium enhancement (LGE) images using neural networks promises an alternative to time-consuming and observer-dependent semi-automatic approaches. However, alterations in data acquisition, reconstruction as well as post-processing may compromise network performance. The objective of the present work was to systematically assess network performance degradation due to a mismatch of point-spread function between training and testing data.MethodsThirty-six high-resolution (0.7×0.7×2.0 mm3) LGE k-space datasets were acquired post-mortem in porcine models of myocardial infarction. The in-plane point-spread function and hence in-plane resolution Δx was retrospectively degraded using k-space lowpass filtering, while field-of-view and matrix size were kept constant. Manual segmentation of the left ventricle (LV) and healthy remote myocardium was performed to quantify location and area (% of myocardium) of scar by thresholding (≥ SD5 above remote). Three standard U-Nets were trained on training resolutions Δxtrain = 0.7, 1.2 and 1.7 mm to predict endo- and epicardial borders of LV myocardium and scar. The scar prediction of the three networks for varying test resolutions (Δxtest = 0.7 to 1.7 mm) was compared against the reference SD5 thresholding at 0.7 mm. Finally, a fourth network trained on a combination of resolutions (Δxtrain = 0.7 to 1.7 mm) was tested.ResultsThe prediction of relative scar areas showed the highest precision when the resolution of the test data was identical to or close to the resolution used during training. The median fractional scar errors and precisions (IQR) from networks trained and tested on the same resolution were 0.0 percentage points (p.p.) (1.24 - 1.45), and - 0.5 - 0.0 p.p. (2.00 - 3.25) for networks trained and tested on the most differing resolutions, respectively. Deploying the network trained on multiple resolutions resulted in reduced resolution dependency with median scar errors and IQRs of 0.0 p.p. (1.24 - 1.69) for all investigated test resolutions.ConclusionA mismatch of the imaging point-spread function between training and test data can lead to degradation of scar segmentation when using current U-Net architectures as demonstrated on LGE porcine myocardial infarction data. Training networks on multi-resolution data can alleviate the resolution dependency.

Project description:BackgroundLate gadolinium enhancement (LGE) by cardiac magnetic resonance (CMR) is useful for the detection of cardiac amyloidosis (CA), but characteristic LGE patterns do not always occur or they appear late in the disease. Native T1 and extracellular volume (ECV) by T1 mapping may improve disease detection and quantify myocardial amyloid load.MethodsThirty patients with definite CA, 10 patients with possible CA, 20 patients with hypertrophic cardiomyopathy (HCM) and 40 healthy volunteers were performed 3.0-T CMR including cine, pre- and postcontrast T1 mapping and LGE. Receiver-operating characteristic (ROC) curves were constructed to assess the diagnostic ability of native T1 and ECV for CA. Correlation analysis between native T1 or ECV and cardiac biomarkers, structure, and function indexes were assessed using Pearson or Spearman correlation, as appropriate.ResultsNative T1 values were 1,429±93, 1,290±49, 1,304±42, and 1,225±21 ms, in definite CA, possible CA, HCM, and healthy controls, respectively. ECV values were 44%±9%, 34%±5%, 33%±4%, and 24%±3%, in definite CA, possible CA, HCM, and healthy controls, respectively. Native T1 [area under curve (AUC) =0.89, 95% confidence interval (CI): 0.75-1.00, P<0.001] and ECV (AUC =0.99, 95% CI: 0.98-1.00, P<0.001) showed good ability to differentiate LGE-negative patients with possible CA from healthy controls, especially ECV. Positive correlations were found between native T1 or ECV and New York Heart Association (NYHA) functional class (r=0.673 and r=0.594, respectively; P<0.001), NT-proBNP (r=0.668 and r=0.603, respectively; P<0.001), troponin T (r=0.724 and r=0.591, respectively; P<0.001), left ventricular (LV) mass index (r=0.668 and r=0.579, respectively; P<0.001), and global LV wall thickness (r=0.765 and r=0.629, respectively; P<0.001). Negative correlations were found between native T1 or ECV and left ventricular ejection fraction (LVEF) (r=-0.761 and r=-0.668, respectively; P<0.001) and left ventricular stroke volume (LVSV) (r=-0.777 and r=-0.729, respectively; P<0.001).ConclusionsNative T1 and ECV, which are able to reflect cardiac biochemistry, structure, and function, have high diagnostic accuracy for detecting CA, especially in LGE-negative patients, and thus could be used for early diagnosis of CA.

Project description:BackgroundDuchenne muscular dystrophy (DMD) is an X-linked recessive disease that occurs in males leading to immobility and death in early adulthood. Female carriers of DMD are generally asymptomatic, yet frequently develop dilated cardiomyopathy. This study aims to detect early cardiac manifestation in DMD using cardiovascular magnetic resonance (CMR) and to evaluate its association with clinical symptoms.MethodsClinical assessment of DMD carriers included six minutes walk tests (6MWT), blood analysis, electrocardiography, echocardiography, and CMR using FLASH sequences to detect late gadolinium enhancement (LGE). T1-mapping using the Modified Look-Locker Inversion recovery (MOLLI) sequence was performed quantify extracellular volume (ECV).ResultsOf 20 carriers (age 39.47 ± 12.96 years) 17 (89.5 %) were clinically asymptomatic. ECV was mildly elevated (29.79 ± 2.92 %) and LGE was detected in nine cases (45 %). LGE positive carriers had lower left ventricular ejection fraction in CMR (64.36 ± 5.78 vs. 56.67 ± 6.89 %, p = 0.014), higher bothCK (629.89 ± 317.48 vs. 256.18 ± 109.10 U/l, p = 0.002) and CK-MB (22.13 ± 5.25 vs. 12.11 ± 2.21 U/l, p = 0.001), as well as shorter walking distances during the 6MWT (432.44 ± 96.72 vs. 514.91 ± 66.80 m, p = 0.037). 90.9 % of subjects without LGE had normal pro-BNP, whereas in 66.7 % of those presenting LGE pro-BNP was elevated (p = 0.027). All individuals without LGE were in the NYHA class I, whereas all those in NYHA classes II and III showed positive for LGE (p = 0.066).ConclusionsMyocardial involvement shown as LGE in CMR occurs in a substantial number of DMD carriers; it is associated with clinical and morphometric signs of incipient heart failure. LGE is thus a sensitive parameter for the early diagnosis of cardiomyopathy in DMD carriers.Trial registrationClinicaltrials.gov, NCT01712152 Trial registration: October 19, 2012. First patient enrolled: September 27, 2012 (retrospectively registered).

Project description:BACKGROUND:Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) using magnitude inversion recovery (IR) or phase sensitive inversion recovery (PSIR) has become clinical standard for assessment of myocardial infarction (MI). However, there is no clinical standard for quantification of MI even though multiple methods have been proposed. Simple thresholds have yielded varying results and advanced algorithms have only been validated in single center studies. Therefore, the aim of this study was to develop an automatic algorithm for MI quantification in IR and PSIR LGE images and to validate the new algorithm experimentally and compare it to expert delineations in multi-center, multi-vendor patient data. METHODS:The new automatic algorithm, EWA (Expectation Maximization, weighted intensity, a priori information), was implemented using an intensity threshold by Expectation Maximization (EM) and a weighted summation to account for partial volume effects. The EWA algorithm was validated in-vivo against triphenyltetrazolium-chloride (TTC) staining (n?=?7 pigs with paired IR and PSIR images) and against ex-vivo high resolution T1-weighted images (n?=?23 IR and n?=?13 PSIR images). The EWA algorithm was also compared to expert delineation in 124 patients from multi-center, multi-vendor clinical trials 2-6 days following first time ST-elevation myocardial infarction (STEMI) treated with percutaneous coronary intervention (PCI) (n?=?124 IR and n?=?49 PSIR images). RESULTS:Infarct size by the EWA algorithm in vivo in pigs showed a bias to ex-vivo TTC of -1?±?4%LVM (R?=?0.84) in IR and -2?±?3%LVM (R?=?0.92) in PSIR images and a bias to ex-vivo T1-weighted images of 0?±?4%LVM (R?=?0.94) in IR and 0?±?5%LVM (R?=?0.79) in PSIR images. In multi-center patient studies, infarct size by the EWA algorithm showed a bias to expert delineation of -2?±?6 %LVM (R?=?0.81) in IR images (n?=?124) and 0?±?5%LVM (R?=?0.89) in PSIR images (n?=?49). CONCLUSIONS:The EWA algorithm was validated experimentally and in patient data with a low bias in both IR and PSIR LGE images. Thus, the use of EM and a weighted intensity as in the EWA algorithm, may serve as a clinical standard for the quantification of myocardial infarction in LGE CMR images. CLINICAL TRIAL REGISTRATION:CHILL-MI: NCT01379261 . MITOCARE:NCT01374321 .

Project description:BackgroundCardiovascular magnetic resonance (CMR) imaging may be used to visualize post-ablation atrial scar (PAAS), and three-dimensional late gadolinium enhancement (3D LGE) is the most widely employed technique for imaging of chronic scar. Detection of PAAS provides a unique non-invasive insight into the effects of the ablation and may help guide further ablation procedures. However, there is evidence that PAAS is often not detected by CMR, implying a significant sensitivity problem, and imaging parameters vary between leading centres. Therefore, there is a need to establish the optimal imaging parameters to detect PAAS.MethodsForty subjects undergoing their first pulmonary vein isolation procedure for AF had detailed CMR assessment of atrial scar: one scan pre-ablation, and two scans post-ablation at 3 months (separated by 48 h). Each scan session included ECG- and respiratory-navigated 3D LGE acquisition at 10, 20 and 30 min post injection of a gadolinium-based contrast agent (GBCA). The first post-procedural scan was performed on a 1.5 T scanner with standard acquisition parameters, including double dose (0.2 mmol/kg) Gadovist and 4 mm slice thickness. Ten patients subsequently underwent identical scan as controls, and the other 30 underwent imaging with a reduced, single, dose GBCA (n = 10), half slice thickness (n = 10) or on a 3 T scanner (n = 10). Apparent signal-to-noise (aSNR), contrast-to-noise (aCNR) and imaging quality (Likert Scale, 3 independent observers) were assessed. PAAS location and area (%PAAS scar) were assessed following manual segmentation. Atrial shells with standardised %PAAS at each timepoint were then compared to ablation lesion locations to assess quality of scar delineation.ResultsA total of 271 3D acquisitions (out of maximum 280, 96.7%) were acquired. Likert scale of imaging quality had high interobserver and intraobserver intraclass correlation coefficients (0.89 and 0.96 respectively), and showed lower overall imaging quality on 3 T and at half-slice thickness. aCNR, and quality of scar delineation increased significantly with time. aCNR was higher with reduced, single, dose of GBCA (p = 0.005).Conclusion3D LGE CMR atrial scar imaging, as assessed qualitatively and quantitatively, improves with time from GBCA administration, with some indices continuing to improve from 20 to 30 min. Imaging should be performed at least 20 min post-GBCA injection, and a single dose of contrast should be considered.Trial registrationTrial registry- United Kingdom National Research Ethics Service 08/H0802/68 - 30th September 2008.

Project description:BackgroundLate gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging has enabled the accurate assessment of myocardial infarction (MI). However, LGE CMR has not been performed successfully in the fetus, where it could be useful for animal studies of interventions to promote cardiac regeneration. We believe that LGE imaging could allow us to document the presence, extent and effect of MI in utero and would thereby expand our capacity for conducting fetal sheep MI research. We therefore aimed to investigate the feasibility of using LGE to detect MI in sheep fetuses.MethodsSix sheep fetuses underwent a thoracotomy and ligation of a left anterior descending (LAD) coronary artery branch; while two fetuses underwent a sham surgery. LGE CMR was performed in a subset of fetuses immediately after the surgery and three days later. Early gadolinium enhancement (EGE) CMR was also performed in a subset of fetuses on both days. Cine imaging of the heart was performed to measure ventricular function.ResultsThe imaging performed immediately after LAD ligation revealed no evidence of infarct on LGE (n=3). Two of four infarcted fetuses (50%) showed hypoenhancement at the infarct site on the EGE images. Three days after the ligation, LGE images revealed a clear, hyper-enhanced infarct zone in four of the five infarcted fetuses (80%). No hyper-enhanced infarct zone was seen on the one sham fetus that underwent LGE CMR. No hypoenhancement could be seen in the EGE images in either the sham (n=1) or the infarcted fetus (n=1). No regional wall motion abnormalities were apparent in two of the five infarcted fetuses.ConclusionLGE CMR detected the MI three days after LAD ligation, but not immediately after. Using available methods, EGE imaging was less useful for detecting deficits in perfusion. Our study provides evidence for the ability of a non-invasive tool to monitor the progression of cardiac repair and damage in fetuses with MI. However, further investigation into the optimal timing of LGE and EGE scans and improvement of the sequences should be pursued with the aim of expanding our capacity to monitor cardiac regeneration after MI in fetal sheep.