A foundation model for enhancing magnetic resonance images and downstream segmentation, registration and diagnostic tasks. Sun, Y., Wang, L., Li, G., Lin, W., & Wang, L. Nature Biomedical Engineering, December, 2024. Publisher: Nature Publishing Group![A foundation model for enhancing magnetic resonance images and downstream segmentation, registration and diagnostic tasks [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex In structural magnetic resonance (MR) imaging, motion artefacts, low resolution, imaging noise and variability in acquisition protocols frequently degrade image quality and confound downstream analyses. Here we report a foundation model for the motion correction, resolution enhancement, denoising and harmonization of MR images. Specifically, we trained a tissue-classification neural network to predict tissue labels, which are then leveraged by a ‘tissue-aware’ enhancement network to generate high-quality MR images. We validated the model’s effectiveness on a large and diverse dataset comprising 2,448 deliberately corrupted images and 10,963 images spanning a wide age range (from foetuses to elderly individuals) acquired using a variety of clinical scanners across 19 public datasets. The model consistently outperformed state-of-the-art algorithms in improving the quality of MR images, handling pathological brains with multiple sclerosis or gliomas, generating 7-T-like images from 3 T scans and harmonizing images acquired from different scanners. The high-quality, high-resolution and harmonized images generated by the model can be used to enhance the performance of models for tissue segmentation, registration, diagnosis and other downstream tasks.
@article{sun_foundation_2024,
title = {A foundation model for enhancing magnetic resonance images and downstream segmentation, registration and diagnostic tasks},
copyright = {2024 The Author(s), under exclusive licence to Springer Nature Limited},
issn = {2157-846X},
url = {https://www.nature.com/articles/s41551-024-01283-7},
doi = {10.1038/s41551-024-01283-7},
abstract = {In structural magnetic resonance (MR) imaging, motion artefacts, low resolution, imaging noise and variability in acquisition protocols frequently degrade image quality and confound downstream analyses. Here we report a foundation model for the motion correction, resolution enhancement, denoising and harmonization of MR images. Specifically, we trained a tissue-classification neural network to predict tissue labels, which are then leveraged by a ‘tissue-aware’ enhancement network to generate high-quality MR images. We validated the model’s effectiveness on a large and diverse dataset comprising 2,448 deliberately corrupted images and 10,963 images spanning a wide age range (from foetuses to elderly individuals) acquired using a variety of clinical scanners across 19 public datasets. The model consistently outperformed state-of-the-art algorithms in improving the quality of MR images, handling pathological brains with multiple sclerosis or gliomas, generating 7-T-like images from 3 T scans and harmonizing images acquired from different scanners. The high-quality, high-resolution and harmonized images generated by the model can be used to enhance the performance of models for tissue segmentation, registration, diagnosis and other downstream tasks.},
language = {en},
urldate = {2025-01-06},
journal = {Nature Biomedical Engineering},
author = {Sun, Yue and Wang, Limei and Li, Gang and Lin, Weili and Wang, Li},
month = dec,
year = {2024},
note = {Publisher: Nature Publishing Group},
keywords = {Computational models, Image processing, Machine learning},
pages = {1--18},
}
Downloads: 0
{"_id":"Rvpd6CFwF7FpHgsT3","bibbaseid":"sun-wang-li-lin-wang-afoundationmodelforenhancingmagneticresonanceimagesanddownstreamsegmentationregistrationanddiagnostictasks-2024","author_short":["Sun, Y.","Wang, L.","Li, G.","Lin, W.","Wang, L."],"bibdata":{"bibtype":"article","type":"article","title":"A foundation model for enhancing magnetic resonance images and downstream segmentation, registration and diagnostic tasks","copyright":"2024 The Author(s), under exclusive licence to Springer Nature Limited","issn":"2157-846X","url":"https://www.nature.com/articles/s41551-024-01283-7","doi":"10.1038/s41551-024-01283-7","abstract":"In structural magnetic resonance (MR) imaging, motion artefacts, low resolution, imaging noise and variability in acquisition protocols frequently degrade image quality and confound downstream analyses. Here we report a foundation model for the motion correction, resolution enhancement, denoising and harmonization of MR images. Specifically, we trained a tissue-classification neural network to predict tissue labels, which are then leveraged by a ‘tissue-aware’ enhancement network to generate high-quality MR images. We validated the model’s effectiveness on a large and diverse dataset comprising 2,448 deliberately corrupted images and 10,963 images spanning a wide age range (from foetuses to elderly individuals) acquired using a variety of clinical scanners across 19 public datasets. The model consistently outperformed state-of-the-art algorithms in improving the quality of MR images, handling pathological brains with multiple sclerosis or gliomas, generating 7-T-like images from 3 T scans and harmonizing images acquired from different scanners. The high-quality, high-resolution and harmonized images generated by the model can be used to enhance the performance of models for tissue segmentation, registration, diagnosis and other downstream tasks.","language":"en","urldate":"2025-01-06","journal":"Nature Biomedical Engineering","author":[{"propositions":[],"lastnames":["Sun"],"firstnames":["Yue"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Limei"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Gang"],"suffixes":[]},{"propositions":[],"lastnames":["Lin"],"firstnames":["Weili"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Li"],"suffixes":[]}],"month":"December","year":"2024","note":"Publisher: Nature Publishing Group","keywords":"Computational models, Image processing, Machine learning","pages":"1–18","bibtex":"@article{sun_foundation_2024,\n\ttitle = {A foundation model for enhancing magnetic resonance images and downstream segmentation, registration and diagnostic tasks},\n\tcopyright = {2024 The Author(s), under exclusive licence to Springer Nature Limited},\n\tissn = {2157-846X},\n\turl = {https://www.nature.com/articles/s41551-024-01283-7},\n\tdoi = {10.1038/s41551-024-01283-7},\n\tabstract = {In structural magnetic resonance (MR) imaging, motion artefacts, low resolution, imaging noise and variability in acquisition protocols frequently degrade image quality and confound downstream analyses. Here we report a foundation model for the motion correction, resolution enhancement, denoising and harmonization of MR images. Specifically, we trained a tissue-classification neural network to predict tissue labels, which are then leveraged by a ‘tissue-aware’ enhancement network to generate high-quality MR images. We validated the model’s effectiveness on a large and diverse dataset comprising 2,448 deliberately corrupted images and 10,963 images spanning a wide age range (from foetuses to elderly individuals) acquired using a variety of clinical scanners across 19 public datasets. The model consistently outperformed state-of-the-art algorithms in improving the quality of MR images, handling pathological brains with multiple sclerosis or gliomas, generating 7-T-like images from 3 T scans and harmonizing images acquired from different scanners. The high-quality, high-resolution and harmonized images generated by the model can be used to enhance the performance of models for tissue segmentation, registration, diagnosis and other downstream tasks.},\n\tlanguage = {en},\n\turldate = {2025-01-06},\n\tjournal = {Nature Biomedical Engineering},\n\tauthor = {Sun, Yue and Wang, Limei and Li, Gang and Lin, Weili and Wang, Li},\n\tmonth = dec,\n\tyear = {2024},\n\tnote = {Publisher: Nature Publishing Group},\n\tkeywords = {Computational models, Image processing, Machine learning},\n\tpages = {1--18},\n}\n\n\n\n\n\n\n\n\n\n\n\n","author_short":["Sun, Y.","Wang, L.","Li, G.","Lin, W.","Wang, L."],"key":"sun_foundation_2024","id":"sun_foundation_2024","bibbaseid":"sun-wang-li-lin-wang-afoundationmodelforenhancingmagneticresonanceimagesanddownstreamsegmentationregistrationanddiagnostictasks-2024","role":"author","urls":{"Paper":"https://www.nature.com/articles/s41551-024-01283-7"},"keyword":["Computational models","Image processing","Machine learning"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/zotero-group/peerherholz/5704536","dataSources":["6GhResmoSoCCHimNC"],"keywords":["computational models","image processing","machine learning"],"search_terms":["foundation","model","enhancing","magnetic","resonance","images","downstream","segmentation","registration","diagnostic","tasks","sun","wang","li","lin","wang"],"title":"A foundation model for enhancing magnetic resonance images and downstream segmentation, registration and diagnostic tasks","year":2024}