Cargando…
MISPEL: A supervised deep learning harmonization method for multi-scanner neuroimaging data
Large-scale data obtained from aggregation of already collected multi-site neuroimaging datasets has brought benefits such as higher statistical power, reliability, and robustness to the studies. Despite these promises from growth in sample size, substantial technical variability stemming from diffe...
Autores principales: | , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10529705/ https://www.ncbi.nlm.nih.gov/pubmed/37595405 http://dx.doi.org/10.1016/j.media.2023.102926 |
_version_ | 1785111423138922496 |
---|---|
author | Torbati, Mahbaneh Eshaghzadeh Minhas, Davneet S. Laymon, Charles M. Maillard, Pauline Wilson, James D. Chen, Chang-Le Crainiceanu, Ciprian M. DeCarli, Charles S. Hwang, Seong Jae Tudorascu, Dana L. |
author_facet | Torbati, Mahbaneh Eshaghzadeh Minhas, Davneet S. Laymon, Charles M. Maillard, Pauline Wilson, James D. Chen, Chang-Le Crainiceanu, Ciprian M. DeCarli, Charles S. Hwang, Seong Jae Tudorascu, Dana L. |
author_sort | Torbati, Mahbaneh Eshaghzadeh |
collection | PubMed |
description | Large-scale data obtained from aggregation of already collected multi-site neuroimaging datasets has brought benefits such as higher statistical power, reliability, and robustness to the studies. Despite these promises from growth in sample size, substantial technical variability stemming from differences in scanner specifications exists in the aggregated data and could inadvertently bias any downstream analyses on it. Such a challenge calls for data normalization and/or harmonization frameworks, in addition to comprehensive criteria to estimate the scanner-related variability and evaluate the harmonization frameworks. In this study, we propose MISPEL (Multi-scanner Image harmonization via Structure Preserving Embedding Learning), a supervised multi-scanner harmonization method that is naturally extendable to more than two scanners. We also designed a set of criteria to investigate the scanner-related technical variability and evaluate the harmonization techniques. As an essential requirement of our criteria, we introduced a multi-scanner matched dataset of 3T [Formula: see text] images across four scanners, which, to the best of our knowledge is one of the few datasets of this kind. We also investigated our evaluations using two popular segmentation frameworks: FSL and segmentation in statistical parametric mapping (SPM). Lastly, we compared MISPEL to popular methods of normalization and harmonization, namely White Stripe, RAVEL, and CALAMITI. MISPEL outperformed these methods and is promising for many other neuroimaging modalities. |
format | Online Article Text |
id | pubmed-10529705 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
record_format | MEDLINE/PubMed |
spelling | pubmed-105297052023-10-01 MISPEL: A supervised deep learning harmonization method for multi-scanner neuroimaging data Torbati, Mahbaneh Eshaghzadeh Minhas, Davneet S. Laymon, Charles M. Maillard, Pauline Wilson, James D. Chen, Chang-Le Crainiceanu, Ciprian M. DeCarli, Charles S. Hwang, Seong Jae Tudorascu, Dana L. Med Image Anal Article Large-scale data obtained from aggregation of already collected multi-site neuroimaging datasets has brought benefits such as higher statistical power, reliability, and robustness to the studies. Despite these promises from growth in sample size, substantial technical variability stemming from differences in scanner specifications exists in the aggregated data and could inadvertently bias any downstream analyses on it. Such a challenge calls for data normalization and/or harmonization frameworks, in addition to comprehensive criteria to estimate the scanner-related variability and evaluate the harmonization frameworks. In this study, we propose MISPEL (Multi-scanner Image harmonization via Structure Preserving Embedding Learning), a supervised multi-scanner harmonization method that is naturally extendable to more than two scanners. We also designed a set of criteria to investigate the scanner-related technical variability and evaluate the harmonization techniques. As an essential requirement of our criteria, we introduced a multi-scanner matched dataset of 3T [Formula: see text] images across four scanners, which, to the best of our knowledge is one of the few datasets of this kind. We also investigated our evaluations using two popular segmentation frameworks: FSL and segmentation in statistical parametric mapping (SPM). Lastly, we compared MISPEL to popular methods of normalization and harmonization, namely White Stripe, RAVEL, and CALAMITI. MISPEL outperformed these methods and is promising for many other neuroimaging modalities. 2023-10 2023-08-09 /pmc/articles/PMC10529705/ /pubmed/37595405 http://dx.doi.org/10.1016/j.media.2023.102926 Text en https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/ (https://creativecommons.org/licenses/by-nc-nd/4.0/) ). |
spellingShingle | Article Torbati, Mahbaneh Eshaghzadeh Minhas, Davneet S. Laymon, Charles M. Maillard, Pauline Wilson, James D. Chen, Chang-Le Crainiceanu, Ciprian M. DeCarli, Charles S. Hwang, Seong Jae Tudorascu, Dana L. MISPEL: A supervised deep learning harmonization method for multi-scanner neuroimaging data |
title | MISPEL: A supervised deep learning harmonization method for multi-scanner neuroimaging data |
title_full | MISPEL: A supervised deep learning harmonization method for multi-scanner neuroimaging data |
title_fullStr | MISPEL: A supervised deep learning harmonization method for multi-scanner neuroimaging data |
title_full_unstemmed | MISPEL: A supervised deep learning harmonization method for multi-scanner neuroimaging data |
title_short | MISPEL: A supervised deep learning harmonization method for multi-scanner neuroimaging data |
title_sort | mispel: a supervised deep learning harmonization method for multi-scanner neuroimaging data |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10529705/ https://www.ncbi.nlm.nih.gov/pubmed/37595405 http://dx.doi.org/10.1016/j.media.2023.102926 |
work_keys_str_mv | AT torbatimahbaneheshaghzadeh mispelasuperviseddeeplearningharmonizationmethodformultiscannerneuroimagingdata AT minhasdavneets mispelasuperviseddeeplearningharmonizationmethodformultiscannerneuroimagingdata AT laymoncharlesm mispelasuperviseddeeplearningharmonizationmethodformultiscannerneuroimagingdata AT maillardpauline mispelasuperviseddeeplearningharmonizationmethodformultiscannerneuroimagingdata AT wilsonjamesd mispelasuperviseddeeplearningharmonizationmethodformultiscannerneuroimagingdata AT chenchangle mispelasuperviseddeeplearningharmonizationmethodformultiscannerneuroimagingdata AT crainiceanuciprianm mispelasuperviseddeeplearningharmonizationmethodformultiscannerneuroimagingdata AT decarlicharless mispelasuperviseddeeplearningharmonizationmethodformultiscannerneuroimagingdata AT hwangseongjae mispelasuperviseddeeplearningharmonizationmethodformultiscannerneuroimagingdata AT tudorascudanal mispelasuperviseddeeplearningharmonizationmethodformultiscannerneuroimagingdata |