Cargando…

A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI

Most data-driven methods are very susceptible to data variability. This problem is particularly apparent when applying Deep Learning (DL) to brain Magnetic Resonance Imaging (MRI), where intensities and contrasts vary due to acquisition protocol, scanner- and center-specific factors. Most publicly a...

Descripción completa

Detalles Bibliográficos
Autores principales: Meyer, Maria Ines, de la Rosa, Ezequiel, Pedrosa de Barros, Nuno, Paolella, Roberto, Van Leemput, Koen, Sima, Diana M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8439197/
https://www.ncbi.nlm.nih.gov/pubmed/34531715
http://dx.doi.org/10.3389/fnins.2021.708196
_version_ 1783752488363491328
author Meyer, Maria Ines
de la Rosa, Ezequiel
Pedrosa de Barros, Nuno
Paolella, Roberto
Van Leemput, Koen
Sima, Diana M.
author_facet Meyer, Maria Ines
de la Rosa, Ezequiel
Pedrosa de Barros, Nuno
Paolella, Roberto
Van Leemput, Koen
Sima, Diana M.
author_sort Meyer, Maria Ines
collection PubMed
description Most data-driven methods are very susceptible to data variability. This problem is particularly apparent when applying Deep Learning (DL) to brain Magnetic Resonance Imaging (MRI), where intensities and contrasts vary due to acquisition protocol, scanner- and center-specific factors. Most publicly available brain MRI datasets originate from the same center and are homogeneous in terms of scanner and used protocol. As such, devising robust methods that generalize to multi-scanner and multi-center data is crucial for transferring these techniques into clinical practice. We propose a novel data augmentation approach based on Gaussian Mixture Models (GMM-DA) with the goal of increasing the variability of a given dataset in terms of intensities and contrasts. The approach allows to augment the training dataset such that the variability in the training set compares to what is seen in real world clinical data, while preserving anatomical information. We compare the performance of a state-of-the-art U-Net model trained for segmenting brain structures with and without the addition of GMM-DA. The models are trained and evaluated on single- and multi-scanner datasets. Additionally, we verify the consistency of test-retest results on same-patient images (same and different scanners). Finally, we investigate how the presence of bias field influences the performance of a model trained with GMM-DA. We found that the addition of the GMM-DA improves the generalization capability of the DL model to other scanners not present in the training data, even when the train set is already multi-scanner. Besides, the consistency between same-patient segmentation predictions is improved, both for same-scanner and different-scanner repetitions. We conclude that GMM-DA could increase the transferability of DL models into clinical scenarios.
format Online
Article
Text
id pubmed-8439197
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-84391972021-09-15 A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI Meyer, Maria Ines de la Rosa, Ezequiel Pedrosa de Barros, Nuno Paolella, Roberto Van Leemput, Koen Sima, Diana M. Front Neurosci Neuroscience Most data-driven methods are very susceptible to data variability. This problem is particularly apparent when applying Deep Learning (DL) to brain Magnetic Resonance Imaging (MRI), where intensities and contrasts vary due to acquisition protocol, scanner- and center-specific factors. Most publicly available brain MRI datasets originate from the same center and are homogeneous in terms of scanner and used protocol. As such, devising robust methods that generalize to multi-scanner and multi-center data is crucial for transferring these techniques into clinical practice. We propose a novel data augmentation approach based on Gaussian Mixture Models (GMM-DA) with the goal of increasing the variability of a given dataset in terms of intensities and contrasts. The approach allows to augment the training dataset such that the variability in the training set compares to what is seen in real world clinical data, while preserving anatomical information. We compare the performance of a state-of-the-art U-Net model trained for segmenting brain structures with and without the addition of GMM-DA. The models are trained and evaluated on single- and multi-scanner datasets. Additionally, we verify the consistency of test-retest results on same-patient images (same and different scanners). Finally, we investigate how the presence of bias field influences the performance of a model trained with GMM-DA. We found that the addition of the GMM-DA improves the generalization capability of the DL model to other scanners not present in the training data, even when the train set is already multi-scanner. Besides, the consistency between same-patient segmentation predictions is improved, both for same-scanner and different-scanner repetitions. We conclude that GMM-DA could increase the transferability of DL models into clinical scenarios. Frontiers Media S.A. 2021-08-31 /pmc/articles/PMC8439197/ /pubmed/34531715 http://dx.doi.org/10.3389/fnins.2021.708196 Text en Copyright © 2021 Meyer, de la Rosa, Pedrosa de Barros, Paolella, Van Leemput and Sima. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Meyer, Maria Ines
de la Rosa, Ezequiel
Pedrosa de Barros, Nuno
Paolella, Roberto
Van Leemput, Koen
Sima, Diana M.
A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI
title A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI
title_full A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI
title_fullStr A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI
title_full_unstemmed A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI
title_short A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI
title_sort contrast augmentation approach to improve multi-scanner generalization in mri
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8439197/
https://www.ncbi.nlm.nih.gov/pubmed/34531715
http://dx.doi.org/10.3389/fnins.2021.708196
work_keys_str_mv AT meyermariaines acontrastaugmentationapproachtoimprovemultiscannergeneralizationinmri
AT delarosaezequiel acontrastaugmentationapproachtoimprovemultiscannergeneralizationinmri
AT pedrosadebarrosnuno acontrastaugmentationapproachtoimprovemultiscannergeneralizationinmri
AT paolellaroberto acontrastaugmentationapproachtoimprovemultiscannergeneralizationinmri
AT vanleemputkoen acontrastaugmentationapproachtoimprovemultiscannergeneralizationinmri
AT simadianam acontrastaugmentationapproachtoimprovemultiscannergeneralizationinmri
AT meyermariaines contrastaugmentationapproachtoimprovemultiscannergeneralizationinmri
AT delarosaezequiel contrastaugmentationapproachtoimprovemultiscannergeneralizationinmri
AT pedrosadebarrosnuno contrastaugmentationapproachtoimprovemultiscannergeneralizationinmri
AT paolellaroberto contrastaugmentationapproachtoimprovemultiscannergeneralizationinmri
AT vanleemputkoen contrastaugmentationapproachtoimprovemultiscannergeneralizationinmri
AT simadianam contrastaugmentationapproachtoimprovemultiscannergeneralizationinmri