New Prospects for Ultra-High-Field Magnetic Resonance Imaging in Multiple Sclerosis

Ineichen, Benjamin Victor; Beck, Erin; Piccirelli, Marco; Reich, Daniel S.

doi:10.1097/rli.0000000000000804

Cited by 23 publications

(19 citation statements)

References 166 publications

(363 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These are increased SNR and improved sensitivity to susceptibility changes. 34 The increase in SNR comes primarily from the increase in field strength. Improved SNR makes possible higher spatial resolution, as well as achieved tissue CNR.…”

Section: Multiple Sclerosis-where 7 T Excelsmentioning

confidence: 99%

“…Likely reasons include the small size of some lesions, CSF partial volume effects, and the different intrinsic signal intensity of the cortex (due to lower myelination). Both in vivo clinical MR evaluations and postmortem MRI have shown the higher sensitivity of 7 T, in comparison to 3 T, to cortical lesions in MS. 34,35 Use of advanced/innovative imaging sequences can also be very important. 36 7 T makes possible as well improved classification of lesions as cortical or subcortical in location, which is important for the specificity of diagnosis (given that subpial lesions are felt to be pathognomonic for MS).…”

Section: Multiple Sclerosis-where 7 T Excelsmentioning

confidence: 99%

See 1 more Smart Citation

The Clinical Utility of Magnetic Resonance Imaging According to Field Strength, Specifically Addressing the Breadth of Current State-of-the-Art Systems, Which Include 0.55 T, 1.5 T, 3 T, and 7 T

Runge

Heverhagen

2021

Invest Radiol

View full text Add to dashboard Cite

This review provides a balanced perspective regarding the clinical utility of magnetic resonance systems across the range of field strengths for which current state-of-the-art units exist (0.55 T, 1.5 T, 3 T, and 7 T). Guidance regarding this issue is critical to appropriate purchasing, usage, and further dissemination of this important imaging modality, both in the industrial world and in developing nations. The review serves to provide an important update, although to a large extent this information has never previously been openly presented.In that sense, it serves also as a position paper, with statements and recommendations as appropriate.

show abstract

Section: Multiple Sclerosis-where 7 T Excelsmentioning

confidence: 99%

Section: Multiple Sclerosis-where 7 T Excelsmentioning

confidence: 99%

The Clinical Utility of Magnetic Resonance Imaging According to Field Strength, Specifically Addressing the Breadth of Current State-of-the-Art Systems, Which Include 0.55 T, 1.5 T, 3 T, and 7 T

Runge

Heverhagen

2021

Invest Radiol

View full text Add to dashboard Cite

show abstract

“…7 Thus, 7 T imaging is essential for expanding our understanding of cortical demyelination. 14 With the recent FDA approval of 7 T scanners for clinical use, we can expect an increasing number of scans on these devices in the coming years. However, even with the most sensitive imaging methods, identification and segmentation of CLs is very time consuming and requires significant experience.…”

Section: Introductionmentioning

confidence: 99%

“…For example, compared with the combined use of 7 T MP2RAGE and T2*w images, 3 T double inversion recovery was 6% sensitive for subpial lesions and 3 T MP2RAGE was 5% sensitive 7 . Thus, 7 T imaging is essential for expanding our understanding of cortical demyelination 14 . With the recent FDA approval of 7 T scanners for clinical use, we can expect an increasing number of scans on these devices in the coming years.…”

Section: Introductionmentioning

confidence: 99%

Multiple sclerosis cortical lesion detection with deep learning at ultra‐high‐field MRI

et al. 2022

Self Cite

View full text Add to dashboard Cite

Manually segmenting multiple sclerosis (MS) cortical lesions (CLs) is extremely time consuming, and past studies have shown only moderate inter‐rater reliability. To accelerate this task, we developed a deep‐learning‐based framework (CLAIMS: Cortical Lesion AI‐Based Assessment in Multiple Sclerosis) for the automated detection and classification of MS CLs with 7 T MRI. Two 7 T datasets, acquired at different sites, were considered. The first consisted of 60 scans that include 0.5 mm isotropic MP2RAGE acquired four times (MP2RAGE×4), 0.7 mm MP2RAGE, 0.5 mm T2*‐weighted GRE, and 0.5 mm T2*‐weighted EPI. The second dataset consisted of 20 scans including only 0.75 × 0.75 × 0.9 mm3 MP2RAGE. CLAIMS was first evaluated using sixfold cross‐validation with single and multi‐contrast 0.5 mm MRI input. Second, the performance of the model was tested on 0.7 mm MP2RAGE images after training with either 0.5 mm MP2RAGE×4, 0.7 mm MP2RAGE, or alternating the two. Third, its generalizability was evaluated on the second external dataset and compared with a state‐of‐the‐art technique based on partial volume estimation and topological constraints (MSLAST). CLAIMS trained only with MP2RAGE×4 achieved results comparable to those of the multi‐contrast model, reaching a CL true positive rate of 74% with a false positive rate of 30%. Detection rate was excellent for leukocortical and subpial lesions (83%, and 70%, respectively), whereas it reached 53% for intracortical lesions. The correlation between disability measures and CL count was similar for manual and CLAIMS lesion counts. Applying a domain‐scanner adaptation approach and testing CLAIMS on the second dataset, the performance was superior to MSLAST when considering a minimum lesion volume of 6 μL (lesion‐wise detection rate of 71% versus 48%). The proposed framework outperforms previous state‐of‐the‐art methods for automated CL detection across scanners and protocols. In the future, CLAIMS may be useful to support clinical decisions at 7 T MRI, especially in the field of diagnosis and differential diagnosis of MS patients.

show abstract

“…For example, compared to the combined use of 7T MP2RAGE and T2*w images, 3T double inversion recovery was 6% sensitive for subpial lesions and 3T MP2RAGE was 5% sensitive 6 . Thus, 7T imaging is essential for expanding our understanding of cortical demyelination 13 . With the recent FDA approval of 7T scanners for clinical use, we can expect an increasing number of scans on these devices in the coming years.…”

Section: Introductionmentioning

confidence: 99%

Multiple sclerosis cortical lesion detection with deep learning at ultra-high-field MRI

Rosa

Beck

Maranzano

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Manually segmenting multiple sclerosis (MS) cortical lesions (CL) is extremely time-consuming, and past studies have shown only moderate inter-rater reliability. To accelerate this task, we developed a deep learning-based framework (CLAIMS: Cortical Lesion Artificial Intelligence-based assessment in Multiple Sclerosis) for the automated detection and classification of MS CL with 7T MRI.Two 7T datasets, acquired at different sites, were considered. The first consisted of 60 scans that include 0.5mm isotropic MP2RAGE acquired 4 times (MP2RAGEx4), 0.7mm MP2RAGE, 0.5mm T2*-weighted GRE, and 0.5mm T2*-weighted EPI. The second dataset consisted of 20 scans including only 0.75×0.75×0.9 mm MP2RAGE. CLAIMS was first evaluated using 6-fold cross-validation with single and multi-contrast 0.5mm MRI input. Second, performance of the model was tested on 0.7mm MP2RAGE images after training with either 0.5mm MP2RAGEx4, 0.7mm MP2RAGE, or alternating the two. Third, its generalizability was evaluated on the second external dataset and compared with a state-of-the-art technique based on partial volume estimation and topological constraints (MSLAST). CLAIMS trained only with MP2RAGEx4 achieved comparable results to the multi-contrast model, reaching a CL true positive rate of 74% with a false positive rate of 30%. Detection rate was excellent for leukocortical and subpial lesions (83%, and 70%, respectively), whereas it reached 53% for intracortical lesions. The correlation between disability measures and CL count was similar for manual and CLAIMS lesion counts. Applying a domain-scanner adaptation approach and testing CLAIMS on the second dataset, the performance was superior to MSLAST when considering a minimum lesion volume of 6μL (lesion-wise detection rate of 71% vs 48%).The proposed framework outperforms previous state-of-the-art methods for automated CL detection across scanners and protocols. In the future, CLAIMS may be useful to support clinical decisions at 7T MRI, especially in the field of diagnosis and differential diagnosis of multiple sclerosis patients.

show abstract

New Prospects for Ultra-High-Field Magnetic Resonance Imaging in Multiple Sclerosis

Cited by 23 publications

References 166 publications

The Clinical Utility of Magnetic Resonance Imaging According to Field Strength, Specifically Addressing the Breadth of Current State-of-the-Art Systems, Which Include 0.55 T, 1.5 T, 3 T, and 7 T

The Clinical Utility of Magnetic Resonance Imaging According to Field Strength, Specifically Addressing the Breadth of Current State-of-the-Art Systems, Which Include 0.55 T, 1.5 T, 3 T, and 7 T

Multiple sclerosis cortical lesion detection with deep learning at ultra‐high‐field MRI

Multiple sclerosis cortical lesion detection with deep learning at ultra-high-field MRI

Contact Info

Product

Resources

About