Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast

Iglesias, Juan Eugenio; Billot, Benjamin; Balbastre, Yaël; Tabari, Azadeh; Conklin, John; González, R. Gilberto; Alexander, Daniel C.; Golland, Polina; Edlow, Brian L.; Fischl, Bruce; Initiative, Alzheimer’s Disease Neuroimaging

doi:10.1016/j.neuroimage.2021.118206

Cited by 67 publications

(70 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We cannot determine whether HippUnfold will work as intended on all new datasets, but within the generalization datasets examined here, results were excellent. Some work has already demonstrated it is possible to synthesize or convert between MRI modalities [35], which could be used to alleviate the dependency on any single MR contrast.…”

Section: Resultsmentioning

confidence: 99%

Automated hippocampal unfolding for morphometry and subfield segmentation with HippUnfold

DeKraker

Haast

Yousif

et al. 2021

Preprint

View full text Add to dashboard Cite

The archicortical hippocampus differs, like the neocortex, in its folding patterns between individuals. Here, we present an automated and robust BIDS-App, HippUnfold, for defining and indexing subject-specific hippocampal folding in MRI, analogous to popular tools used in neocortical reconstruction. This is critical for inter-individual alignment, with topology as the basis for homology. This topological framework enables qualitatively new analyses of morphological and laminar structure in the hippocampus or hippocampal subfields, and is critical for the advancement of neuroimaging analyses at a meso- or micro-scale. HippUnfold uses state-of-the-art deep learning combined with previously developed topological constraints on hippocampal tissue. It is designed to work with commonly employed sub-millimetric MRI acquisitions, with extensibility to microscopic resolutions as well. In this paper we illustrate the power of HippUnfold in feature extraction, and its construct validity compared to several extant hippocampal subfield analysis methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Automated hippocampal unfolding for morphometry and subfield segmentation with HippUnfold

DeKraker

Haast

Yousif

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Different scientific organizations in Europe (MAGNIMS) and in North America (CMSC, NAIMS) have actively worked to provide standardized protocols that can be easily implemented in clinical practice ( Wattjes et al, 2021a ). In this context, the use of synthetic images (e.g., Fingerprinting ( Hsieh and Svalbe, 2020 ), Synthetic MR ( Gonçalves et al, 2018 ) could be of extremely high value as they can provide harmonized, co-registered and simultaneous measures of different contrast-weighted images ( Iglesias et al, 2021 ).…”

Section: Future Perspectives and Conclusionmentioning

confidence: 99%

MAGNIMS recommendations for harmonization of MRI data in MS multicenter studies

Stefano

Battaglini

Pareto

et al. 2022

NeuroImage: Clinical

View full text Add to dashboard Cite

“…Built-in resolution-independence in CNNs has not been described for brain segmentation nor -to our knowledge -for any other segmentation tasks. Approaches such as [34,35] pre-sample input images (with associated reliability maps) to a common resolution (here 1.0 mm) and provide outputs there, which makes them inherently fixedresolution techniques. While they can provide 1.0 mm segmentations (and even images) for lower resolutional clinical scans via heavy augmentation, they can neither profit from submillimeter details, nor provide native HiRes segmentations.…”

Section: Resolution-independence In Deep Learningmentioning

confidence: 99%

“…Testing Mix (Big) HCP (80), RS (80), ABIDE-II (25), ABIDE-I (20), ADNI (40), IXI (43), LA5C (15), OASIS1 (35), OASIS2 (17) 355…”

Section: Appendixmentioning

confidence: 99%

FastSurferVINN: Building Resolution-Independence into Deep Learning Segmentation Methods -- A Solution for HighRes Brain MRI

Henschel¹,

Kügler²,

Reuter³

2021

Preprint

View full text Add to dashboard Cite

Leading neuroimaging studies have pushed 3T MRI acquisition resolutions below 1.0 mm for improved structure definition and morphometry. Yet, only few, time-intensive automated image analysis pipelines have been validated for high-resolution (HiRes) settings. Efficient deep learning approaches, on the other hand, rarely support more than one fixed resolution (usually 1.0 mm). Furthermore, the lack of a standard submillimeter resolution as well as limited availability of diverse HiRes data with sufficient coverage of scanner, age, diseases, or genetic variance poses additional, unsolved challenges for training HiRes networks. Incorporating resolution-independence into deep learning-based segmentation, i.e., the ability to segment images at their native resolution across a range of different voxel sizes, promises to overcome these challenges, yet no such approach currently exists. We now fill this gap by introducing a Voxelsize Independent Neural Network (VINN) for resolution-independent segmentation tasks and present FastSurferVINN, which (i) establishes and implements resolution-independence for deep learning as the first method simultaneously supporting 0.7-1.0 mm whole brain segmentation, (ii) significantly outperforms state-of-the-art methods across resolutions, and (iii) mitigates the data imbalance problem present in HiRes datasets. Overall, internal resolution-independence mutually benefits both HiRes and 1.0 mm MRI segmentation. With our rigorously validated FastSurferVINN we distribute a rapid tool for morphometric neuroimage analysis. The VINN architecture, furthermore, represents an efficient resolution-independent segmentation method for wider application.

show abstract

Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast

Cited by 67 publications

References 74 publications

Automated hippocampal unfolding for morphometry and subfield segmentation with HippUnfold

Automated hippocampal unfolding for morphometry and subfield segmentation with HippUnfold

MAGNIMS recommendations for harmonization of MRI data in MS multicenter studies

FastSurferVINN: Building Resolution-Independence into Deep Learning Segmentation Methods -- A Solution for HighRes Brain MRI

Contact Info

Product

Resources

About