Dataset Information

Motion compensated self supervised deep learning for highly accelerated 3D ultrashort Echo time pulmonary MRI.

ABSTRACT:

Purpose

To investigate motion compensated, self-supervised, model based deep learning (MBDL) as a method to reconstruct free breathing, 3D pulmonary UTE acquisitions.

Theory and methods

A self-supervised eXtra dimension MBDL architecture (XD-MBDL) was developed that combined respiratory states to reconstruct a single high-quality 3D image. Non-rigid motion fields were incorporated into this architecture by estimating motion fields from a lower resolution motion resolved (XD-GRASP) reconstruction. Motion compensated XD-MBDL was evaluated on lung UTE datasets with and without contrast and compared to constrained reconstructions and variants of self-supervised MBDL that do not account for dynamic respiratory states or leverage motion correction.

Results

Images reconstructed using XD-MBDL demonstrate improved image quality as measured by apparent SNR (aSNR), contrast to noise ratio (CNR), and visual assessment relative to self-supervised MBDL approaches that do not account for dynamic respiratory states, XD-GRASP and a recently proposed motion compensated iterative reconstruction strategy (iMoCo). Additionally, XD-MBDL reduced reconstruction time relative to both XD-GRASP and iMoCo.

Conclusion

A method was developed to allow self-supervised MBDL to combine multiple respiratory states to reconstruct a single image. This method was combined with graphics processing unit (GPU)-based image registration to further improve reconstruction quality. This approach showed promising results reconstructing a user-selected respiratory phase from free breathing 3D pulmonary UTE acquisitions.

SUBMITTER: Miller Z

PROVIDER: S-EPMC10590257 | biostudies-literature | 2023 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Motion compensated self supervised deep learning for highly accelerated 3D ultrashort Echo time pulmonary MRI.

Miller Zachary Z Johnson Kevin M KM

Magnetic resonance in medicine 20230206 6

<h4>Purpose</h4>To investigate motion compensated, self-supervised, model based deep learning (MBDL) as a method to reconstruct free breathing, 3D pulmonary UTE acquisitions.<h4>Theory and methods</h4>A self-supervised eXtra dimension MBDL architecture (XD-MBDL) was developed that combined respiratory states to reconstruct a single high-quality 3D image. Non-rigid motion fields were incorporated into this architecture by estimating motion fields from a lower resolution motion resolved (XD-GRASP) ...[more]

PMID: 36744745

Similar Datasets

Project description:Background Signal contamination from long T2 water is a major challenge in direct imaging of myelin with MRI. Nulling of the unwanted long T2 signals can be achieved with an inversion recovery (IR) preparation pulse to null long T2 white matter within the brain. The remaining ultrashort T2 signal from myelin can be detected with an ultrashort echo time (UTE) sequence. Purpose To develop patient-specific whole-brain myelin imaging with a three-dimensional double-echo sliding inversion recovery (DESIRE) UTE sequence. Materials and Methods The DESIRE UTE sequence generates a series of IR images with different inversion times during a single scan. The optimal inversion time for nulling long T2 signal is determined by finding minimal signal on the second echo. Myelin images are generated by subtracting the second echo image from the first UTE image. To validate this method, a prospective study was performed in phantoms, cadaveric brain specimens, healthy volunteers, and patients with multiple sclerosis (MS). A total of 20 healthy volunteers (mean age, 40 years ± 13 [standard deviation], 10 women) and 20 patients with MS (mean age, 58 years ± 8; 15 women) who underwent MRI between November 2017 and February 2019 were prospectively included. Analysis of variance was performed to evaluate the signal difference between MS lesions and normal-appearing white matter in patients with MS. Results High signal intensity and corresponding T2* and T1 of the extracted myelin vesicles provided evidence for direct imaging of ultrashort-T2 myelin protons using the UTE sequence. Gadobenate dimeglumine phantoms with a wide range of T1 values were selectively suppressed with DESIRE UTE. In the ex vivo brain study of MS lesions, signal loss was observed in MS lesions and was conformed with histologic analysis. In the human study, there was a significant reduction in normalized signal intensity in MS lesions compared with that in normal-appearing white matter (0.19 ± 0.10 vs 0.76 ± 0.11, respectively; P < .001). Conclusion The double-echo sliding inversion recovery ultrashort echo time sequence can generate whole-brain myelin images specifically with a clinical 3-T scanner. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Port in this issue.

Project description:ObjectiveTo compare compressed sensing (CS) and the Cascades of Independently Recurrent Inference Machines (CIRIM) with respect to image quality and reconstruction times when 12-fold accelerated scans of patients with neurological deficits are reconstructed.Materials and methodsTwelve-fold accelerated 3D T2-FLAIR images were obtained from a cohort of 62 patients with neurological deficits on 3 T MRI. Images were reconstructed offline via CS and the CIRIM. Image quality was assessed in a blinded and randomized manner by two experienced interventional neuroradiologists and one experienced pediatric neuroradiologist on imaging artifacts, perceived spatial resolution (sharpness), anatomic conspicuity, diagnostic confidence, and contrast. The methods were also compared in terms of self-referenced quality metrics, image resolution, patient groups and reconstruction time. In ten scans, the contrast ratio (CR) was determined between lesions and white matter. The effect of acceleration factor was assessed in a publicly available fully sampled dataset, since ground truth data are not available in prospectively accelerated clinical scans. Specifically, 451 FLAIR scans, including scans with white matter lesions, were adopted from the FastMRI database to evaluate structural similarity (SSIM) and the CR of lesions and white matter on ranging acceleration factors from four-fold up to 12-fold.ResultsInterventional neuroradiologists significantly preferred the CIRIM for imaging artifacts, anatomic conspicuity, and contrast. One rater significantly preferred the CIRIM in terms of sharpness and diagnostic confidence. The pediatric neuroradiologist preferred CS for imaging artifacts and sharpness. Compared to CS, the CIRIM reconstructions significantly improved in terms of imaging artifacts and anatomic conspicuity (p < 0.01) for higher resolution scans while yielding a 28% higher SNR (p = 0.001) and a 5.8% lower CR (p = 0.04). There were no differences between patient groups. Additionally, CIRIM was five times faster than CS was. An increasing acceleration factor did not lead to changes in CR (p = 0.92), but led to lower SSIM (p = 0.002).DiscussionPatients with neurological deficits can undergo MRI at a range of moderate to high acceleration. DL reconstruction outperforms CS in terms of image resolution, efficient denoising with a modest reduction in contrast and reduced reconstruction times.

Project description:BackgroundComputed tomography (CT) and spirometry are the current standard methods for assessing lung anatomy and pulmonary ventilation, respectively. However, CT provides limited ventilation information and spirometry only provides global measures of lung ventilation. Thus, a method that can enable simultaneous examination of lung anatomy and ventilation is of clinical interest.PurposeTo develop and test a 4D respiratory-resolved sparse lung MRI (XD-UTE: eXtra-Dimensional Ultrashort TE imaging) approach for simultaneous evaluation of lung anatomy and pulmonary ventilation.Study typeProspective.PopulationIn all, 23 subjects (11 volunteers and 12 patients, mean age = 63.6 ± 8.4).Field strength/sequence3T MR; a prototype 3D golden-angle radial UTE sequence, a Cartesian breath-hold volumetric-interpolated examination (BH-VIBE) sequence.AssessmentAll subjects were scanned using the 3D golden-angle radial UTE sequence during normal breathing. Ten subjects underwent an additional scan during alternating normal and deep breathing. Respiratory-motion-resolved sparse reconstruction was performed for all the acquired data to generate dynamic normal-breathing or deep-breathing image series. For comparison, BH-VIBE was performed in 12 subjects. Lung images were visually scored by three experienced chest radiologists and were analyzed by two observers who segmented the left and right lung to derive ventilation parameters in comparison with spirometry.Statistical testsNonparametric paired two-tailed Wilcoxon signed-rank test; intraclass correlation coefficient, Pearson correlation coefficient.ResultsXD-UTE achieved significantly improved image quality compared both with Cartesian BH-VIBE and radial reconstruction without motion compensation (P < 0.05). The global ventilation parameters (a sum of the left and right lung measures) were in good correlation with spirometry in the same subjects (correlation coefficient = 0.724). There were excellent correlations between the results obtained by two observers (intraclass correlation coefficient ranged from 0.8855-0.9995).Data conclusionSimultaneous evaluation of lung anatomy and ventilation using XD-UTE is demonstrated, which have shown good potential for improved diagnosis and management of patients with heterogeneous lung diseases.Level of evidence2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:411-422.

Project description:BackgroundA previous study demonstrated the feasibility of using 3D radial ultrashort echo time (UTE) oxygen-enhanced MRI (UTE OE-MRI) for functional imaging of healthy human lungs. The repeatability of quantitative measures from UTE OE-MRI needs to be established prior to its application in clinical research.PurposeTo evaluate repeatability of obstructive patterns in asthma and cystic fibrosis (CF) with UTE OE-MRI with isotropic spatial resolution and full chest coverage.Study typeVolunteer and patient repeatability.PopulationEighteen human subjects (five asthma, six CF, and seven normal subjects).Field strength/sequenceRespiratory-gated free-breathing 3D radial UTE (80 μs) sequence at 1.5T.AssessmentTwo 3D radial UTE volumes were acquired sequentially under normoxic and hyperoxic conditions. A subset of subjects underwent repeat acquisitions on either the same day or ≤15 days apart. Asthma and CF subjects also underwent spirometry. A workflow including deformable registration and retrospective lung density correction was used to compute 3D isotropic percent signal enhancement (PSE) maps. Median PSE (MPSE) and ventilation defect percent (VDP) of the lung were measured from the PSE map.Statistical testsThe relations between MPSE, VDP, and spirometric measures were assessed using Spearman correlations. The test-retest repeatability was evaluated using Bland-Altman analysis and intraclass correlation coefficients (ICC).ResultsVentilation measures in normal subjects (MPSE = 8.0%, VDP = 3.3%) were significantly different from those in asthma (MPSE = 6.0%, P = 0.042; VDP = 21.7%, P = 0.018) and CF group (MPSE = 4.5%, P = 0.0006; VDP = 27.2%, P = 0.002). MPSE correlated significantly with forced expiratory lung volume in 1 second percent predicted (ρ = 0.72, P = 0.017). The ICC of the test-retest VDP and MPSE were both ≥0.90. In all subject groups, an anterior/posterior gradient was observed with higher MPSE and lower VDP in the posterior compared to anterior regions (P ≤ 0.0021 for all comparisons).Data conclusion3D radial UTE OE-MRI supports quantitative differentiation of diseased vs. healthy lungs using either whole lung VDP or MPSE with excellent test-retest repeatability.Level of evidence2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2018;47:1287-1297.

Project description:BackgroundQuantitative MRI of patellar tendinopathy (PT) can be challenging due to spatial variation of T2 * relaxation times.Purpose1) To compare T2 * quantification using a standard approach with analysis in specific tissue compartments of the patellar tendon. 2) To evaluate test-retest reliability of different methods for fitting ultrashort echo time (UTE)-relaxometry data.Study typeProspective.SubjectsSixty-five athletes with PT.Field strength/sequence3D UTE scans covering the patellar tendon were acquired using a 3.0T scanner and a 16-channel surface coil.AssessmentVoxelwise median T2 * was quantified with monoexponential, fractional-order, and biexponential fitting. We applied two methods for T2 * analysis: first, a standard approach by analyzing all voxels covering the proximal patellar tendon. Second, within subregions of the patellar tendon, by using thresholds on biexponential fitting parameter percentage short T2 * (0-30% for mostly long T2 *, 30-60% for mixed T2 *, and 60-100% for mostly short T2 *).Statistical testsAverage test-retest reliability was assessed in three athletes using coefficients-of-variation (CV) and coefficients-of-repeatability (CR).ResultsWith standard image analysis, we found a median [interquartile range, IQR] monoexponential T2 * of 6.43 msec [4.32-8.55] and fractional order T2 * 4.39 msec [3.06-5.78]. The percentage of short T2 * components was 52.9% [35.5-69.6]. Subregional monoexponential T2 * was 13.78 msec [12.11-16.46], 7.65 msec [6.49-8.61], and 3.05 msec [2.52-3.60] and fractional order T2 * 11.82 msec [10.09-14.44], 5.14 msec [4.25-5.96], and 2.19 msec [1.82-2.64] for 0-30%, 30-60%, and 60-100% short T2 *, respectively. Biexponential component short T2 * was 1.693 msec [1.417-2.003] for tissue with mostly short T2 * and long T2 * of 15.79 msec [13.47-18.61] for mostly long T2 *. The average CR (CV) was 2 msec (15%), 2 msec (19%) and 10% (22%) for monoexponential, fractional order and percentage short T2 *, respectively.Data conclusionPatellar tendinopathy is characterized by regional variability in binding states of water. Quantitative multicompartment T2 * analysis in PT can be facilitated using a voxel selection method based on using biexponential fitting parameters.Level of evidence1 TECHNICAL EFFICACY STAGE: 1 J. Magn. Reson. Imaging 2020;52:420-430.

Dataset Information

Motion compensated self supervised deep learning for highly accelerated 3D ultrashort Echo time pulmonary MRI.

Purpose

Theory and methods

Results

Conclusion

Publications

Motion compensated self supervised deep learning for highly accelerated 3D ultrashort Echo time pulmonary MRI.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets