Dataset Information

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

ABSTRACT:

Background

Cardiovascular 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.

Methods

A 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.

Results

The FCN achieved fast segmentation (1 values (1091?±?59?ms and 1089?±?59?ms, respectively) were highly correlated in per-patient (r?=?0.82; slope?=?1.01; p?1 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).

Conclusion

The 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.

SUBMITTER: Fahmy AS

PROVIDER: S-EPMC6330747 | biostudies-literature | 2019 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated analysis of cardiovascular magnetic resonance myocardial native T<sub>1</sub> mapping images using fully convolutional neural networks.

Fahmy Ahmed S AS El-Rewaidy Hossam H Nezafat Maryam M Nakamori Shiro S Nezafat Reza R

Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance 20190114 1

<h4>Background</h4>Cardiovascular magnetic resonance (CMR) myocardial native T<sub>1</sub> mapping allows assessment of interstitial diffuse fibrosis. In this technique, the global and regional T<sub>1</sub> are measured manually by drawing region of interest in motion-corrected T<sub>1</sub> 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 ...[more]

PMID: 30636630

Similar Datasets

Project description:Cardiovascular resonance (CMR) imaging is a standard imaging modality for assessing cardiovascular diseases (CVDs), the leading cause of death globally. CMR enables accurate quantification of the cardiac chamber volume, ejection fraction and myocardial mass, providing information for diagnosis and monitoring of CVDs. However, for years, clinicians have been relying on manual approaches for CMR image analysis, which is time consuming and prone to subjective errors. It is a major clinical challenge to automatically derive quantitative and clinically relevant information from CMR images.Deep neural networks have shown a great potential in image pattern recognition and segmentation for a variety of tasks. Here we demonstrate an automated analysis method for CMR images, which is based on a fully convolutional network (FCN). The network is trained and evaluated on a large-scale dataset from the UK Biobank, consisting of 4,875 subjects with 93,500 pixelwise annotated images. The performance of the method has been evaluated using a number of technical metrics, including the Dice metric, mean contour distance and Hausdorff distance, as well as clinically relevant measures, including left ventricle (LV) end-diastolic volume (LVEDV) and end-systolic volume (LVESV), LV mass (LVM); right ventricle (RV) end-diastolic volume (RVEDV) and end-systolic volume (RVESV).By combining FCN with a large-scale annotated dataset, the proposed automated method achieves a high performance in segmenting the LV and RV on short-axis CMR images and the left atrium (LA) and right atrium (RA) on long-axis CMR images. On a short-axis image test set of 600 subjects, it achieves an average Dice metric of 0.94 for the LV cavity, 0.88 for the LV myocardium and 0.90 for the RV cavity. The mean absolute difference between automated measurement and manual measurement is 6.1 mL for LVEDV, 5.3 mL for LVESV, 6.9 gram for LVM, 8.5 mL for RVEDV and 7.2 mL for RVESV. On long-axis image test sets, the average Dice metric is 0.93 for the LA cavity (2-chamber view), 0.95 for the LA cavity (4-chamber view) and 0.96 for the RA cavity (4-chamber view). The performance is comparable to human inter-observer variability.We show that an automated method achieves a performance on par with human experts in analysing CMR images and deriving clinically relevant measures.

Project description:ObjectivesThe authors developed a fully automated framework to quantify myocardial blood flow (MBF) from contrast-enhanced cardiac magnetic resonance (CMR) perfusion imaging and evaluated its diagnostic performance in patients.BackgroundFully quantitative CMR perfusion pixel maps were previously validated with microsphere MBF measurements and showed potential in clinical applications, but the methods required laborious manual processes and were excessively time-consuming.MethodsCMR perfusion imaging was performed on 80 patients with known or suspected coronary artery disease (CAD) and 17 healthy volunteers. Significant CAD was defined by quantitative coronary angiography (QCA) as ≥70% stenosis. Nonsignificant CAD was defined by: 1) QCA as <70% stenosis; or 2) coronary computed tomography angiography as <30% stenosis and a calcium score of 0 in all vessels. Automatically generated MBF maps were compared with manual quantification on healthy volunteers. Diagnostic performance of the automated MBF pixel maps was analyzed on patients using absolute MBF, myocardial perfusion reserve (MPR), and relative measurements of MBF and MPR.ResultsThe correlation between automated and manual quantification was excellent (r = 0.96). Stress MBF and MPR in the ischemic zone were lower than those in the remote myocardium in patients with significant CAD (both p < 0.001). Stress MBF and MPR in the remote zone of the patients were lower than those in the normal volunteers (both p < 0.001). All quantitative metrics had good area under the curve (0.864 to 0.926), sensitivity (82.9% to 91.4%), and specificity (75.6% to 91.1%) on per-patient analysis. On a per-vessel analysis of the quantitative metrics, area under the curve (0.837 to 0.864), sensitivity (75.0% to 82.7%), and specificity (71.8% to 80.9%) were good.ConclusionsFully quantitative CMR MBF pixel maps can be generated automatically, and the results agree well with manual quantification. These methods can discriminate regional perfusion variations and have high diagnostic performance for detecting significant CAD. (Technical Development of Cardiovascular Magnetic Resonance Imaging; NCT00027170).

Project description:BACKGROUND:T1 mapping based on cardiovascular magnetic resonance (CMR) is a novel approach using the magnetic relaxation T1 time as a quantitative marker for myocardial tissue composition. Various T1 mapping sequences are being used, with different strengths and weaknesses. Data comparing different sequences head to head however are sparse. METHODS:We compared three T1 mapping sequences, ShMOLLI, MOLLI and SASHA in phantoms and in a mid-ventricular slice of 40 healthy individuals (mean age 59?±?7 years, 45 % male) with low (68 %) or moderate cardiovascular risk. We calculated global and segmental T1 in vivo through exponential curve fitting and subsequent parametric mapping. We also analyzed image quality and inter-observer reproducibility. RESULTS:There was no association of T1 with cardiovascular risk groups. T1 however differed significantly depending on the sequence, with SASHA providing consistently higher mean values than ShMOLLI and MOLLI (1487?±?36 ms vs. 1174?±?37 ms and 1199?±?28 ms, respectively; p?<?0.001). This difference between sequences was much smaller in phantom measurements. In patients, segmental values were lower in the anterior wall for all sequences. Image quality, in general good for the steady-state-free-precession readouts in all sequences, was lower for SASHA parametric maps. On multivariate regression analysis, a longer T1 measured by MOLLI was correlated with lower ejection fraction and female gender. Inter-observer variability as assessed by intra-class correlation coefficients was excellent for all sequences (ShMOLLI: 0.995; MOLLI: 0.991; SASHA: 0.961; all p?<?0.001). CONCLUSION:In a cross-sectional population with low to moderate cardiovascular risk, we observed a variation in T1 mapping results between inversion-recovery vs. saturation-recovery sequences in vivo, which were less evident in phantom images, despite a small interobserver variability. Thus, physiological factors, most likely related to B1 inhomogeneities, and tissue-specific properties, like magnetization transfer, that impact T1 values in vivo, render phantom validation insufficient, and have to be further investigated for a better understanding of the clinical utility of different T1 mapping approaches. TRIAL REGISTRATION:"Canadian Alliance For Healthy Hearts and Minds" - ClinicalTrials.gov NCT02220582 ; registered August 18, 2014.

Project description:Quantitative analysis of craniofacial morphology is of interest to scholars working in a wide variety of disciplines, such as anthropology, developmental biology, and medicine. T1-weighted (anatomical) magnetic resonance images (MRI) provide excellent contrast between soft tissues. Given its three-dimensional nature, MRI represents an ideal imaging modality for the analysis of craniofacial structure in living individuals. Here we describe how T1-weighted MR images, acquired to examine brain anatomy, can also be used to analyze facial features. Using a sample of typically developing adolescents from the Saguenay Youth Study (N?=?597; 292 male, 305 female, ages: 12 to 18 years), we quantified inter-individual variations in craniofacial structure in two ways. First, we adapted existing nonlinear registration-based morphological techniques to generate iteratively a group-wise population average of craniofacial features. The nonlinear transformations were used to map the craniofacial structure of each individual to the population average. Using voxel-wise measures of expansion and contraction, we then examined the effects of sex and age on inter-individual variations in facial features. Second, we employed a landmark-based approach to quantify variations in face surfaces. This approach involves: (a) placing 56 landmarks (forehead, nose, lips, jaw-line, cheekbones, and eyes) on a surface representation of the MRI-based group average; (b) warping the landmarks to the individual faces using the inverse nonlinear transformation estimated for each person; and (3) using a principal components analysis (PCA) of the warped landmarks to identify facial features (i.e. clusters of landmarks) that vary in our sample in a correlated fashion. As with the voxel-wise analysis of the deformation fields, we examined the effects of sex and age on the PCA-derived spatial relationships between facial features. Both methods demonstrated significant sexual dimorphism in craniofacial structure in areas such as the chin, mandible, lips, and nose.

Project description:PurposeThe deformable nature of the liver can make focal treatment challenging and is not adequately addressed with simple rigid registration techniques. More advanced registration techniques can take deformations into account (eg, biomechanical modeling) but require segmentations of the whole liver for each scan, which is a time-intensive process. We hypothesize that fully convolutional networks can be used to rapidly and accurately autosegment the liver, removing the temporal bottleneck for biomechanical modeling.Methods and materialsManual liver segmentations on computed tomography scans from 183 patients treated at our institution and 30 scans from the Medical Image Computing & Computer Assisted Intervention challenges were collected for this study. Three architectures were investigated for rapid automated segmentation of the liver (VGG-16, DeepLabv3 +, and a 3-dimensional UNet). Fifty-six cases were set aside as a final test set for quantitative model evaluation. Accuracy of the autosegmentations was assessed using Dice similarity coefficient and mean surface distance. Qualitative evaluation was also performed by 3 radiation oncologists on 50 independent cases with previously clinically treated liver contours.ResultsThe mean (minimum-maximum) mean surface distance for the test groups with the final model, DeepLabv3 +, were as follows: μContrast(N = 17): 0.99 mm (0.47-2.2), μNon_Contrast(N = 19)l: 1.12 mm (0.41-2.87), and μMiccai(N = 30)t: 1.48 mm (0.82-3.96). The qualitative evaluation showed that 30 of 50 autosegmentations (60%) were preferred to manual contours (majority voting) in a blinded comparison, and 48 of 50 autosegmentations (96%) were deemed clinically acceptable by at least 1 reviewing physician.ConclusionsThe autosegmentations were preferred compared with manually defined contours in the majority of cases. The ability to rapidly segment the liver with high accuracy achieved in this investigation has the potential to enable the efficient integration of biomechanical model-based registration into a clinical workflow.

Project description:BackgroundNon-invasive assessment of myocardial ischaemia is a cornerstone of the diagnosis of coronary artery disease. Measurement of myocardial blood flow (MBF) using positron emission tomography (PET) is the current reference standard for non-invasive quantification of myocardial ischaemia. Dynamic myocardial perfusion cardiovascular magnetic resonance (CMR) offers an alternative to PET and a recently developed method with automated inline perfusion mapping has shown good correlation of MBF values between CMR and PET. This study assessed the repeatability of myocardial perfusion mapping by CMR in healthy subjects.MethodsForty-two healthy subjects were recruited and underwent adenosine stress and rest perfusion CMR on two visits. Scans were repeated with a minimum interval of 7 days. Intrastudy rest and stress MBF repeatability were assessed with a 15-min interval between acquisitions. Interstudy rest and stress MBF and myocardial perfusion reserve (MPR) were measured for global myocardium and regionally for coronary territories and slices.ResultsThere was no significant difference in intrastudy repeated global rest MBF (0.65 ± 0.13 ml/g/min vs 0.62 ± 0.12 ml/g/min, p = 0.24, repeatability coefficient (RC) =24%) or stress (2.89 ± 0.56 ml/g/min vs 2.83 ± 0.64 ml/g/min, p = 0.41, RC = 29%) MBF. No significant difference was seen in interstudy repeatability for global rest MBF (0.64 ± 0.13 ml/g/min vs 0.64 ± 0.15 ml/g/min, p = 0.80, RC = 32%), stress MBF (2.71 ± 0.61 ml/g/min vs 2.55 ± 0.57 ml/g/min, p = 0.12, RC = 33%) or MPR (4.24 ± 0.69 vs 3.73 ± 0.76, p = 0.25, RC = 36%). Regional repeatability was good for stress (RC = 30-37%) and rest MBF (RC = 32-36%) but poorer for MPR (RC = 35-43%). Within subject coefficient of variation was 8% for rest and 11% for stress within the same study, and 11% for rest and 12% for stress between studies.ConclusionsFully automated, inline, myocardial perfusion mapping by CMR shows good repeatability that is similar to the published PET literature. Both rest and stress MBF show better repeatability than MPR, particularly in regional analysis.

Dataset Information

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

Background

Methods

Results

Conclusion

Publications

Automated analysis of cardiovascular magnetic resonance myocardial native T<sub>1</sub> mapping images using fully convolutional neural networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Dataset Information

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

Background

Methods

Results

Conclusion

Publications

Automated analysis of cardiovascular magnetic resonance myocardial native T<sub>1</sub> mapping images using fully convolutional neural networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

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