Dataset Information

Deep learning denoising reconstruction for improved image quality in fetal cardiac cine MRI.

ABSTRACT:

Purpose

This study aims to evaluate deep learning (DL) denoising reconstructions for image quality improvement of Doppler ultrasound (DUS)-gated fetal cardiac MRI in congenital heart disease (CHD).

Methods

Twenty-five fetuses with CHD (mean gestational age: 35 ± 1 weeks) underwent fetal cardiac MRI at 3T. Cine imaging was acquired using a balanced steady-state free precession (bSSFP) sequence with Doppler ultrasound gating. Images were reconstructed using both compressed sensing (bSSFP CS) and a pre-trained convolutional neural network trained for DL denoising (bSSFP DL). Images were compared qualitatively based on a 5-point Likert scale (from 1 = non-diagnostic to 5 = excellent) and quantitatively by calculating the apparent signal-to-noise ratio (aSNR) and contrast-to-noise ratio (aCNR). Diagnostic confidence was assessed for the atria, ventricles, foramen ovale, valves, great vessels, aortic arch, and pulmonary veins.

Results

Fetal cardiac cine MRI was successful in 23 fetuses (92%), with two studies excluded due to extensive fetal motion. The image quality of bSSFP DL cine reconstructions was rated superior to standard bSSFP CS cine images in terms of contrast [3 (interquartile range: 2-4) vs. 5 (4-5), P < 0.001] and endocardial edge definition [3 (2-4) vs. 4 (4-5), P < 0.001], while the extent of artifacts was found to be comparable [4 (3-4.75) vs. 4 (3-4), P = 0.40]. bSSFP DL images had higher aSNR and aCNR compared with the bSSFP CS images (aSNR: 13.4 ± 6.9 vs. 8.3 ± 3.6, P < 0.001; aCNR: 26.6 ± 15.8 vs. 14.4 ± 6.8, P < 0.001). Diagnostic confidence of the bSSFP DL images was superior for the evaluation of cardiovascular structures (e.g., atria and ventricles: P = 0.003).

Conclusion

DL image denoising provides superior quality for DUS-gated fetal cardiac cine imaging of CHD compared to standard CS image reconstruction.

SUBMITTER: Vollbrecht TM

PROVIDER: S-EPMC10894983 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning denoising reconstruction for improved image quality in fetal cardiac cine MRI.

Vollbrecht Thomas M TM Hart Christopher C Zhang Shuo S Katemann Christoph C Sprinkart Alois M AM Isaak Alexander A Attenberger Ulrike U Pieper Claus C CC Kuetting Daniel D Geipel Annegret A Strizek Brigitte B Luetkens Julian A JA

Frontiers in cardiovascular medicine 20240212

<h4>Purpose</h4>This study aims to evaluate deep learning (DL) denoising reconstructions for image quality improvement of Doppler ultrasound (DUS)-gated fetal cardiac MRI in congenital heart disease (CHD).<h4>Methods</h4>Twenty-five fetuses with CHD (mean gestational age: 35 ± 1 weeks) underwent fetal cardiac MRI at 3T. Cine imaging was acquired using a balanced steady-state free precession (bSSFP) sequence with Doppler ultrasound gating. Images were reconstructed using both compressed sensing ( ...[more]

PMID: 38410246

Similar Datasets

Project description:Automatic cerebral cortical surface reconstruction is a useful tool for cortical anatomy quantification, analysis and visualization. Recently, the Human Connectome Project and several studies have shown the advantages of using T1-weighted magnetic resonance (MR) images with sub-millimeter isotropic spatial resolution instead of the standard 1-mm isotropic resolution for improved accuracy of cortical surface positioning and thickness estimation. Nonetheless, sub-millimeter resolution images are noisy by nature and require averaging multiple repetitions to increase the signal-to-noise ratio for precisely delineating the cortical boundary. The prolonged acquisition time and potential motion artifacts pose significant barriers to the wide adoption of cortical surface reconstruction at sub-millimeter resolution for a broad range of neuroscientific and clinical applications. We address this challenge by evaluating the cortical surface reconstruction resulting from denoised single-repetition sub-millimeter T1-weighted images. We systematically characterized the effects of image denoising on empirical data acquired at 0.6 mm isotropic resolution using three classical denoising methods, including denoising convolutional neural network (DnCNN), block-matching and 4-dimensional filtering (BM4D) and adaptive optimized non-local means (AONLM). The denoised single-repetition images were found to be highly similar to 6-repetition averaged images, with a low whole-brain averaged mean absolute difference of ~0.016, high whole-brain averaged peak signal-to-noise ratio of ~33.5 dB and structural similarity index of ~0.92, and minimal gray matter-white matter contrast loss (2% to 9%). The whole-brain mean absolute discrepancies in gray matter-white matter surface placement, gray matter-cerebrospinal fluid surface placement and cortical thickness estimation were lower than 165 μm, 155 μm and 145 μm-sufficiently accurate for most applications. These discrepancies were approximately one third to half of those from 1-mm isotropic resolution data. The denoising performance was equivalent to averaging ~2.5 repetitions of the data in terms of image similarity, and 1.6-2.2 repetitions in terms of the cortical surface placement accuracy. The scan-rescan variability of the cortical surface positioning and thickness estimation was lower than 170 μm. Our unique dataset and systematic characterization support the use of denoising methods for improved cortical surface reconstruction at sub-millimeter resolution.

Project description:PurposeTo apply Doppler US (DUS)-gated fetal cardiac cine MRI in clinical routine and investigate diagnostic performance in complex congenital heart disease (CHD) compared with that of fetal echocardiography.Materials and methodsIn this prospective study (May 2021 to March 2022), women with fetuses with CHD underwent fetal echocardiography and DUS-gated fetal cardiac MRI on the same day. For MRI, balanced steady-state free precession cine images were acquired in the axial and optional sagittal and/or coronal orientations. Overall image quality was assessed on a four-point Likert scale (from 1 = nondiagnostic to 4 = good image quality). The presence of abnormalities in 20 fetal cardiovascular features was independently assessed by using both modalities. The reference standard was postnatal examination results. Differences in sensitivities and specificities were determined by using a random-effects model.ResultsThe study included 23 participants (mean age, 32 years ± 5 [SD]; mean gestational age, 36 weeks ± 1). Fetal cardiac MRI was completed in all participants. The median overall image quality of DUS-gated cine images was 3 (IQR, 2.5-4). In 21 of 23 participants (91%), underlying CHD was correctly assessed by using fetal cardiac MRI. In one case, the correct diagnosis was made by using MRI only (situs inversus and congenitally corrected transposition of the great arteries). Sensitivities (91.8% [95% CI: 85.7, 95.1] vs 93.6% [95% CI: 88.8, 96.2]; P = .53) and specificities (99.9% [95% CI: 99.2, 100] vs 99.9% [95% CI: 99.5, 100]; P > .99) for the detection of abnormal cardiovascular features were comparable between MRI and echocardiography, respectively.ConclusionUsing DUS-gated fetal cine cardiac MRI resulted in performance comparable with that of using fetal echocardiography for diagnosing complex fetal CHD.Keywords: Pediatrics, MR-Fetal (Fetal MRI), Cardiac, Heart, Congenital, Fetal Imaging, Cardiac MRI, Prenatal, Congenital Heart DiseaseClinical trial registration no. NCT05066399 Supplemental material is available for this article. © RSNA, 2023See also the commentary by Biko and Fogel in this issue.

Project description:PurposeTo develop a three-dimensional (two dimensions + time) convolutional neural network trained with displacement encoding with stimulated echoes (DENSE) data for displacement and strain analysis of cine MRI.Materials and methodsIn this retrospective multicenter study, a deep learning model (StrainNet) was developed to predict intramyocardial displacement from contour motion. Patients with various heart diseases and healthy controls underwent cardiac MRI examinations with DENSE between August 2008 and January 2022. Network training inputs were a time series of myocardial contours from DENSE magnitude images, and ground truth data were DENSE displacement measurements. Model performance was evaluated using pixelwise end-point error (EPE). For testing, StrainNet was applied to contour motion from cine MRI. Global and segmental circumferential strain (Ecc) derived from commercial feature tracking (FT), StrainNet, and DENSE (reference) were compared using intraclass correlation coefficients (ICCs), Pearson correlations, Bland-Altman analyses, paired t tests, and linear mixed-effects models.ResultsThe study included 161 patients (110 men; mean age, 61 years ± 14 [SD]), 99 healthy adults (44 men; mean age, 35 years ± 15), and 45 healthy children and adolescents (21 males; mean age, 12 years ± 3). StrainNet showed good agreement with DENSE for intramyocardial displacement, with an average EPE of 0.75 mm ± 0.35. The ICCs between StrainNet and DENSE and FT and DENSE were 0.87 and 0.72, respectively, for global Ecc and 0.75 and 0.48, respectively, for segmental Ecc. Bland-Altman analysis showed that StrainNet had better agreement than FT with DENSE for global and segmental Ecc.ConclusionStrainNet outperformed FT for global and segmental Ecc analysis of cine MRI.Keywords: Image Postprocessing, MR Imaging, Cardiac, Heart, Pediatrics, Technical Aspects, Technology Assessment, Strain, Deep Learning, DENSE Supplemental material is available for this article. © RSNA, 2023.

Dataset Information

Deep learning denoising reconstruction for improved image quality in fetal cardiac cine MRI.

Purpose

Methods

Results

Conclusion

Publications

Deep learning denoising reconstruction for improved image quality in fetal cardiac cine MRI.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets