Dataset Information

Automated cardiovascular magnetic resonance image analysis with fully convolutional networks.

ABSTRACT: 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.

SUBMITTER: Bai W

PROVIDER: S-EPMC6138894 | biostudies-other | 2018 Sep

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Automated cardiovascular magnetic resonance image analysis with fully convolutional networks.

Bai Wenjia W Sinclair Matthew M Tarroni Giacomo G Oktay Ozan O Rajchl Martin M Vaillant Ghislain G Lee Aaron M AM Aung Nay N Lukaschuk Elena E Sanghvi Mihir M MM Zemrak Filip F Fung Kenneth K Paiva Jose Miguel JM Carapella Valentina V Kim Young Jin YJ Suzuki Hideaki H Kainz Bernhard B Matthews Paul M PM Petersen Steffen E SE Piechnik Stefan K SK Neubauer Stefan S Glocker Ben B Rueckert Daniel D

Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance 20180914 1

<h4>Background</h4>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 majo ...[more]

PMID: 30217194

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: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:BackgroundCardiovascular magnetic resonance (CMR) cine displacement encoding with stimulated echoes (DENSE) measures heart motion by encoding myocardial displacement into the signal phase, facilitating high accuracy and reproducibility of global and segmental myocardial strain and providing benefits in clinical performance. While conventional methods for strain analysis of DENSE images are faster than those for myocardial tagging, they still require manual user assistance. The present study developed and evaluated deep learning methods for fully-automatic DENSE strain analysis.MethodsConvolutional neural networks (CNNs) were developed and trained to (a) identify the left-ventricular (LV) epicardial and endocardial borders, (b) identify the anterior right-ventricular (RV)-LV insertion point, and (c) perform phase unwrapping. Subsequent conventional automatic steps were employed to compute strain. The networks were trained using 12,415 short-axis DENSE images from 45 healthy subjects and 19 heart disease patients and were tested using 10,510 images from 25 healthy subjects and 19 patients. Each individual CNN was evaluated, and the end-to-end fully-automatic deep learning pipeline was compared to conventional user-assisted DENSE analysis using linear correlation and Bland Altman analysis of circumferential strain.ResultsLV myocardial segmentation U-Nets achieved a DICE similarity coefficient of 0.87 ± 0.04, a Hausdorff distance of 2.7 ± 1.0 pixels, and a mean surface distance of 0.41 ± 0.29 pixels in comparison with manual LV myocardial segmentation by an expert. The anterior RV-LV insertion point was detected within 1.38 ± 0.9 pixels compared to manually annotated data. The phase-unwrapping U-Net had similar or lower mean squared error vs. ground-truth data compared to the conventional path-following method for images with typical signal-to-noise ratio (SNR) or low SNR (p < 0.05), respectively. Bland-Altman analyses showed biases of 0.00 ± 0.03 and limits of agreement of - 0.04 to 0.05 or better for deep learning-based fully-automatic global and segmental end-systolic circumferential strain vs. conventional user-assisted methods.ConclusionsDeep learning enables fully-automatic global and segmental circumferential strain analysis of DENSE CMR providing excellent agreement with conventional user-assisted methods. Deep learning-based automatic strain analysis may facilitate greater clinical use of DENSE for the quantification of global and segmental strain in patients with cardiac disease.

Project description:BACKGROUND:Phase contrast (PC) cardiovascular magnetic resonance (CMR) is widely employed for flow quantification, but analysis typically requires time consuming manual segmentation which can require human correction. Advances in machine learning have markedly improved automated processing, but have yet to be applied to PC-CMR. This study tested a novel machine learning model for fully automated analysis of PC-CMR aortic flow. METHODS:A machine learning model was designed to track aortic valve borders based on neural network approaches. The model was trained in a derivation cohort encompassing 150 patients who underwent clinical PC-CMR then compared to manual and commercially-available automated segmentation in a prospective validation cohort. Further validation testing was performed in an external cohort acquired from a different site/CMR vendor. RESULTS:Among 190 coronary artery disease patients prospectively undergoing CMR on commercial scanners (84% 1.5T, 16% 3T), machine learning segmentation was uniformly successful, requiring no human intervention: Segmentation time was <?0.01?min/case (1.2?min for entire dataset); manual segmentation required 3.96?±?0.36?min/case (12.5?h for entire dataset). Correlations between machine learning and manual segmentation-derived flow approached unity (r?=?0.99, p?<?0.001). Machine learning yielded smaller absolute differences with manual segmentation than did commercial automation (1.85?±?1.80 vs. 3.33?±?3.18?mL, p?<?0.01): Nearly all (98%) of cases differed by ?5?mL between machine learning and manual methods. Among patients without advanced mitral regurgitation, machine learning correlated well (r?=?0.63, p?<?0.001) and yielded small differences with cine-CMR stroke volume (? 1.3?±?17.7?mL, p?=?0.36). Among advanced mitral regurgitation patients, machine learning yielded lower stroke volume than did volumetric cine-CMR (? 12.6?±?20.9?mL, p?=?0.005), further supporting validity of this method. Among the external validation cohort (n?=?80) acquired using a different CMR vendor, the algorithm yielded equivalently small differences (? 1.39?±?1.77?mL, p?=?0.4) and high correlations (r?=?0.99, p?<?0.001) with manual segmentation, including similar results in 20 patients with bicuspid or stenotic aortic valve pathology (? 1.71?±?2.25?mL, p?=?0.25). CONCLUSION:Fully automated machine learning PC-CMR segmentation performs robustly for aortic flow quantification - yielding rapid segmentation, small differences with manual segmentation, and identification of differential forward/left ventricular volumetric stroke volume in context of concomitant mitral regurgitation. Findings support use of machine learning for analysis of large scale CMR datasets.

Project description:BackgroundCardiovascular magnetic resonance (CMR) represents the clinical gold standard for the assessment of biventricular morphology and function. Since manual post-processing is time-consuming and prone to observer variability, efforts have been directed towards automated volumetric quantification. In this study, we sought to validate the accuracy of a novel approach providing fully automated quantification of biventricular volumes and function in a "real-world" clinical setting.MethodsThree-hundred CMR examinations were randomly selected from the local data base. Fully automated quantification of left ventricular (LV) mass, LV and right ventricular (RV) end-diastolic and end-systolic volumes (EDV/ESV), stroke volume (SV) and ejection fraction (EF) were performed overnight using commercially available software (suiteHEART®, Neosoft, Pewaukee, Wisconsin, USA). Parameters were compared to manual assessments (QMass®, Medis Medical Imaging Systems, Leiden, Netherlands). Sub-group analyses were further performed according to image quality, scanner field strength, the presence of implanted aortic valves and repaired Tetralogy of Fallot (ToF).ResultsBiventricular automated segmentation was feasible in all 300 cases. Overall agreement between fully automated and manually derived LV parameters was good (LV-EF: intra-class correlation coefficient [ICC] 0.95; bias - 2.5% [SD 5.9%]), whilst RV agreement was lower (RV-EF: ICC 0.72; bias 5.8% [SD 9.6%]). Lowest agreement was observed in case of severely altered anatomy, e.g. marked RV dilation but normal LV dimensions in repaired ToF (LV parameters ICC 0.73-0.91; RV parameters ICC 0.41-0.94) and/or reduced image quality (LV parameters ICC 0.86-0.95; RV parameters ICC 0.56-0.91), which was more common on 3.0 T than on 1.5 T.ConclusionsFully automated assessments of biventricular morphology and function is robust and accurate in a clinical routine setting with good image quality and can be performed without any user interaction. However, in case of demanding anatomy (e.g. repaired ToF, severe LV hypertrophy) or reduced image quality, quality check and manual re-contouring are still required.

Dataset Information

Automated cardiovascular magnetic resonance image analysis with fully convolutional networks.

Publications

Automated cardiovascular magnetic resonance image analysis with fully convolutional networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets