Quantitative Brain Morphometry of Portable Low-Field-Strength MRI                     Using Super-Resolution Machine Learning

Iglesias, Juan Eugenio; Schleicher, Riana; Laguna, Sonia; Billot, Benjamin; Schaefer, Pamela W.; McKaig, Brenna; Goldstein, Joshua N.; Sheth, Kevin N; Rosen, Matthew S.; Kimberly, W. Taylor

doi:10.1148/radiol.220522

Cited by 38 publications

(42 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 24 , 25 Deep learning reconstruction methods use neural networks to learn robust transformation mappings from sensor space to the image domain. Image postprocessing has also benefited from deep learning, with applications in super‐resolution, 26 , 27 , 28 segmentation, 29 simulation, 30 denoising, 31 and artifact rejection. 32 However, analytical software development typically lags hardware advances.…”

Section: Hardware and Software Advancesmentioning

confidence: 99%

“…The group has demonstrated high correlation for key brain regions (eg hippocampus, thalamus, ventricles, cortical gray matter [GM]) between 3T and SynthSR‐enhanced lower‐field images. 27 , 103 Deoni et al demonstrated the ability to generate 1.5 mm isotropic T2w images by registering and averaging three orthogonal slice plane acquisitions. 26 Although high‐field biomarkers have yet to be validated on very‐low‐field imaging, these initial super‐resolution results provide a promising avenue.…”

Section: Outpatient Neuroimagingmentioning

confidence: 99%

See 1 more Smart Citation

Low‐field MRI: Clinical promise and challenges

Arnold

Freeman

Litt

et al. 2022

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Modern MRI scanners have trended toward higher field strengths to maximize signal and resolution while minimizing scan time. However, high-field devices remain expensive to install and operate, making them scarce outside of high-income countries and major population centers. Low-field strength scanners have drawn renewed academic, industry, and philanthropic interest due to advantages that could dramatically increase imaging access, including lower cost and portability. Nevertheless, low-field MRI still faces inherent limitations in image quality that come with decreased signal. In this article, we review advantages and disadvantages of low-field MRI scanners, describe hardware and software innovations that accentuate advantages and mitigate disadvantages, and consider clinical applications for a new generation of low-field devices. In our review, we explore how these devices are being or could be used for high acuity brain imaging, outpatient neuroimaging, MRI-guided procedures, pediatric imaging, and musculoskeletal imaging. Challenges for their successful clinical translation include selecting and validating appropriate use cases, integrating with standards of care in high resource settings, expanding options with actionable information in low resource settings, and facilitating health care providers and clinical practice in new ways. By embracing both the promise and challenges of low-field MRI, clinicians and researchers have an opportunity to transform medical care for patients around the world.

show abstract

Section: Hardware and Software Advancesmentioning

confidence: 99%

Section: Outpatient Neuroimagingmentioning

confidence: 99%

Low‐field MRI: Clinical promise and challenges

Arnold

Freeman

Litt

et al. 2022

Magnetic Resonance Imaging

View full text Add to dashboard Cite

show abstract

“…One very recent study (LF‐SynthSR 50 ) explores deep learning superresolution for enhancing ULF MRI, which is based largely on a previously developed method (SynthSR 51 ) from the same group. It shows promising T1W brain image results from commercial 0.065T Hyperfine MRI data.…”

Section: Discussionmentioning

confidence: 99%

Pushing the limits of low‐cost ultra‐low‐field MRI by dual‐acquisition deep learning 3D superresolution

Lau

Xiao

Zhao

et al. 2023

Magnetic Resonance in Med

View full text Add to dashboard Cite

Recent development of ultra-low-field (ULF) MRI presents opportunities for low-power, shielding-free, and portable clinical applications at a fraction of the cost. However, its performance remains limited by poor image quality. Here, a computational approach is formulated to advance ULF MR brain imaging through deep learning of large-scale publicly available 3T brain data. Methods: A dual-acquisition 3D superresolution model is developed for ULF brain MRI at 0.055 T. It consists of deep cross-scale feature extraction, attentional fusion of two acquisitions, and reconstruction. Models for T 1 -weighted and T 2 -weighted imaging were trained with 3D ULF image data sets synthesized from the high-resolution 3T brain data from the Human Connectome Project.They were applied to 0.055T brain MRI with two repetitions and isotropic 3-mm acquisition resolution in healthy volunteers, young and old, as well as patients. Results:The proposed approach significantly enhanced image spatial resolution and suppressed noise/artifacts. It yielded high 3D image quality at 0.055 T for the two most common neuroimaging protocols with isotropic 1.5-mm synthetic resolution and total scan time under 20 min. Fine anatomical details were restored with intrasubject reproducibility, intercontrast consistency, and confirmed by 3T MRI. Conclusion:The proposed dual-acquisition 3D superresolution approach advances ULF MRI for quality brain imaging through deep learning of high-field brain data. Such strategy can empower ULF MRI for low-cost brain imaging, especially in point-of-care scenarios or/and in low-income and mid-income countries.

show abstract

“…Excluding review papers, a study actually treating Alzheimer's patients and a study that did not use neuroimaging data for modeling, the majority of retrieved studies used CNNs for detecting stroke, segmenting lesions, white matter hyperintensities, or other regions of the brain that may be affected by atrophy [28][29][30][31][32][33][34][35][36][37][38][39] (N = 12; see Figure S7 and Table S3). Two studies relied on CNNs to accelerate sequence acquisition or increase sequence resolution 40,41 , and another two studies leveraged CNNs for outcome prediction, but in the acute setting 22,42 . Nishi and colleagues 42 used a CNN to predict good outcome on the Rankin scale of disability after stroke using Diffusion Weighted Images, finding that the CNN outperformed logistic regression applied to the same data as well as a linear regression that was trained purely on lesion size.…”

Section: Recent Work Has Indicated Cnns Can Adequately Discriminate T...mentioning

confidence: 99%

Distinct brain morphometry patterns revealed by deep learning improve prediction of aphasia severity

Teghipco

Newman‐Norlund

Fridriksson

et al. 2023

Preprint

View full text Add to dashboard Cite

Emerging evidence suggests that post-stroke aphasia severity depends on the integrity of the brain beyond the stroke lesion. While measures of lesion anatomy and brain integrity combine synergistically to explain aphasic symptoms, significant interindividual variability remains unaccounted for. A possible explanatory factor may be the spatial distribution of brain atrophy beyond the lesion. This includes not just the specific brain areas showing atrophy, but also distinct three-dimensional patterns of atrophy. Here, we tested whether deep learning with Convolutional Neural Networks (CNN) on whole brain morphometry (i.e., segmented tissue volumes) and lesion anatomy can better predict which individuals with chronic stroke (N=231) have severe aphasia, and whether encoding spatial dependencies in the data might be capable of improving predictions by identifying unique individualized spatial patterns. We observed that CNN achieves significantly higher accuracy and F1 scores than Support Vector Machine (SVM), even when the SVM is nonlinear or integrates linear and nonlinear dimensionality reduction techniques. Performance parity was only achieved when the SVM was directly trained on the latent features learned by the CNN. Saliency maps demonstrated that the CNN leveraged widely distributed patterns of brain atrophy predictive of aphasia severity, whereas the SVM focused almost exclusively on the area around the lesion. Ensemble clustering of CNN saliency maps revealed distinct morphometry patterns that were unrelated to lesion size, highly consistent across individuals, and implicated unique brain networks associated with different cognitive processes as measured by the wider neuroimaging literature. Individualized predictions of severity depended on both ipsilateral and contralateral features outside of the location of stroke. Our findings illustrate that three-dimensional network distributions of atrophy in individuals with aphasia are directly associated with aphasia severity, underscoring the potential for deep learning to improve prognostication of behavioral outcomes from neuroimaging data, and highlighting the prospective benefits of interrogating spatial dependence at different scales in multivariate feature space.

show abstract

Quantitative Brain Morphometry of Portable Low-Field-Strength MRI Using Super-Resolution Machine Learning

Cited by 38 publications

References 21 publications

Low‐field MRI: Clinical promise and challenges

Low‐field MRI: Clinical promise and challenges

Pushing the limits of low‐cost ultra‐low‐field MRI by dual‐acquisition deep learning 3D superresolution

Distinct brain morphometry patterns revealed by deep learning improve prediction of aphasia severity

Contact Info

Product

Resources

About