Dataset Information

Automated inversion time selection for black-blood late gadolinium enhancement cardiac imaging in clinical practice.

ABSTRACT:

Objective

To simplify black-blood late gadolinium enhancement (BL-LGE) cardiac imaging in clinical practice using an image-based algorithm for automated inversion time (TI) selection.

Materials and methods

The algorithm selects from BL-LGE TI scout images, the TI corresponding to the image with the highest number of sub-threshold pixels within a region of interest (ROI) encompassing the blood-pool and myocardium. The threshold value corresponds to the most recurrent pixel intensity of all scout images within the ROI. ROI dimensions were optimized in 40 patients' scans. The algorithm was validated retrospectively (80 patients) versus two experts and tested prospectively (5 patients) on a 1.5 T clinical scanner.

Results

Automated TI selection took ~ 40 ms per dataset (manual: ~ 17 s). Fleiss' kappa coefficient for automated-manual, intra-observer and inter-observer agreements were [Formula: see text]= 0.73, [Formula: see text] = 0.70 and [Formula: see text] = 0.63, respectively. The agreement between the algorithm and any expert was better than the agreement between the two experts or between two selections of one expert.

Discussion

Thanks to its good performance and simplicity of implementation, the proposed algorithm is a good candidate for automated BL-LGE imaging in clinical practice.

SUBMITTER: Maillot A

PROVIDER: S-EPMC10667449 | biostudies-literature | 2023 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated inversion time selection for black-blood late gadolinium enhancement cardiac imaging in clinical practice.

Maillot Aurélien A Sridi Soumaya S Pineau Xavier X André-Billeau Amandine A Hosteins Stéphanie S Maes Jean-David JD Montier Géraldine G Nuñez-Garcia Marta M Quesson Bruno B Sermesant Maxime M Cochet Hubert H Stuber Matthias M Bustin Aurélien A

Magma (New York, N.Y.) 20230609 6

<h4>Objective</h4>To simplify black-blood late gadolinium enhancement (BL-LGE) cardiac imaging in clinical practice using an image-based algorithm for automated inversion time (TI) selection.<h4>Materials and methods</h4>The algorithm selects from BL-LGE TI scout images, the TI corresponding to the image with the highest number of sub-threshold pixels within a region of interest (ROI) encompassing the blood-pool and myocardium. The threshold value corresponds to the most recurrent pixel intensit ...[more]

PMID: 37294423

Similar Datasets

Project description:ObjectivesTo develop and share a deep learning method that can accurately identify optimal inversion time (TI) from multi-vendor, multi-institutional and multi-field strength inversion scout (TI scout) sequences for late gadolinium enhancement cardiac MRI.Materials and methodsRetrospective multicentre study conducted on 1136 1.5-T and 3-T cardiac MRI examinations from four centres and three scanner vendors. Deep learning models, comprising a convolutional neural network (CNN) that provides input to a long short-term memory (LSTM) network, were trained on TI scout pixel data from centres 1 to 3 to identify optimal TI, using ground truth annotations by two readers. Accuracy within 50 ms, mean absolute error (MAE), Lin's concordance coefficient (LCCC) and reduced major axis regression (RMAR) were used to select the best model from validation results, and applied to holdout test data. Robustness of the best-performing model was also tested on imaging data from centre 4.ResultsThe best model (SE-ResNet18-LSTM) produced accuracy of 96.1%, MAE 22.9 ms and LCCC 0.47 compared to ground truth on the holdout test set and accuracy of 97.3%, MAE 15.2 ms and LCCC 0.64 when tested on unseen external (centre 4) data. Differences in vendor performance were observed, with greatest accuracy for the most commonly represented vendor in the training data.ConclusionA deep learning model was developed that can identify optimal inversion time from TI scout images on multi-vendor data with high accuracy, including on previously unseen external data. We make this model available to the scientific community for further assessment or development.Clinical relevance statementA robust automated inversion time selection tool for late gadolinium-enhanced imaging allows for reproducible and efficient cross-vendor inversion time selection.Key points• A model comprising convolutional and recurrent neural networks was developed to extract optimal TI from TI scout images. • Model accuracy within 50 ms of ground truth on multi-vendor holdout and external data of 96.1% and 97.3% respectively was achieved. • This model could improve workflow efficiency and standardise optimal TI selection for consistent LGE imaging.

Project description:BackgroundLate gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) offers the potential to noninvasively characterize the phenotypic substrate for sudden cardiac death (SCD).ObjectivesThe authors assessed the utility of infarct characterization by CMR, including scar microstructure analysis, to predict SCD in patients with coronary artery disease (CAD).MethodsPatients with stable CAD were prospectively recruited into a CMR registry. LGE quantification of core infarction and the peri-infarct zone (PIZ) was performed alongside computational image analysis to extract morphologic and texture scar microstructure features. The primary outcome was SCD or aborted SCD.ResultsOf 437 patients (mean age: 64 years; mean left ventricular ejection fraction [LVEF]: 47%) followed for a median of 6.3 years, 49 patients (11.2%) experienced the primary outcome. On multivariable analysis, PIZ mass and core infarct mass were independently associated with the primary outcome (per gram: HR: 1.07 [95% CI: 1.02-1.12]; P = 0.002 and HR: 1.03 [95% CI: 1.01-1.05]; P = 0.01, respectively), and the addition of both parameters improved discrimination of the model (Harrell's C-statistic: 0.64-0.79). PIZ mass, however, did not provide incremental prognostic value over core infarct mass based on Harrell's C-statistic or risk reclassification analysis. Severely reduced LVEF did not predict the primary endpoint after adjustment for scar mass. On scar microstructure analysis, the number of LGE islands in addition to scar transmurality, radiality, interface area, and entropy were all associated with the primary outcome after adjustment for severely reduced LVEF and New York Heart Association functional class of >1. No scar microstructure feature remained associated with the primary endpoint when PIZ mass and core infarct mass were added to the regression models.ConclusionsComprehensive LGE characterization independently predicted SCD risk beyond conventional predictors used in implantable cardioverter-defibrillator (ICD) insertion guidelines. These results signify the potential for a more personalized approach to determining ICD candidacy in CAD.

Project description:BackgroundLate gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) is widely used to identify cardiac neoplasms, for which diagnosis is predicated on enhancement stemming from lesion vascularity: Impact of contrast-enhancement pattern on clinical outcomes is unknown. The objective of this study was to determine whether cardiac metastasis (CMET) enhancement pattern on LGE-CMR impacts prognosis, with focus on heterogeneous lesion enhancement as a marker of tumor avascularity.MethodsAdvanced (stage IV) systemic cancer patients with and without CMET matched (1:1) by cancer etiology underwent a standardized CMR protocol. CMET was identified via established LGE-CMR criteria based on lesion enhancement; enhancement pattern was further classified as heterogeneous (enhancing and non-enhancing components) or diffuse and assessed via quantitative (contrast-to-noise ratio (CNR); signal-to-noise ratio (SNR)) analyses. Embolic events and mortality were tested in relation to lesion location and contrast-enhancement pattern.Results224 patients were studied, including 112 patients with CMET and unaffected (CMET -) controls matched for systemic cancer etiology/stage. CMET enhancement pattern varied (53% heterogeneous, 47% diffuse). Quantitative analyses were consistent with lesion classification; CNR was higher and SNR lower in heterogeneously enhancing CMET (p < 0.001)-paralleled by larger size based on linear dimensions (p < 0.05). Contrast-enhancement pattern did not vary based on lesion location (p = NS). Embolic events were similar between patients with diffuse and heterogeneous lesions (p = NS) but varied by location: Patients with right-sided lesions had threefold more pulmonary emboli (20% vs. 6%, p = 0.02); those with left-sided lesions had lower rates equivalent to controls (4% vs. 5%, p = 1.00). Mortality was higher among patients with CMET (hazard ratio [HR] = 1.64 [CI 1.17-2.29], p = 0.004) compared to controls, but varied by contrast-enhancement pattern: Diffusely enhancing CMET had equivalent mortality to controls (p = 0.21) whereas prognosis was worse with heterogeneous CMET (p = 0.005) and more strongly predicted by heterogeneous enhancement (HR = 1.97 [CI 1.23-3.15], p = 0.005) than lesion size (HR = 1.11 per 10 cm [CI 0.53-2.33], p = 0.79).ConclusionsContrast-enhancement pattern and location of CMET on CMR impacts prognosis. Embolic events vary by CMET location, with likelihood of PE greatest with right-sided lesions. Heterogeneous enhancement-a marker of tumor avascularity on LGE-CMR-is a novel marker of increased mortality risk.

Dataset Information

Automated inversion time selection for black-blood late gadolinium enhancement cardiac imaging in clinical practice.

Objective

Materials and methods

Results

Discussion

Publications

Automated inversion time selection for black-blood late gadolinium enhancement cardiac imaging in clinical practice.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets