Cargando…

Automated Multiclass Artifact Detection in Diffusion MRI Volumes via 3D Residual Squeeze-and-Excitation Convolutional Neural Networks

Diffusion MRI (dMRI) is widely used to investigate neuronal and structural development of brain. dMRI data is often contaminated with various types of artifacts. Hence, artifact type identification in dMRI volumes is an essential pre-processing step prior to carrying out any further analysis. Manual...

Descripción completa

Detalles Bibliográficos
Autores principales: Ettehadi, Nabil, Kashyap, Pratik, Zhang, Xuzhe, Wang, Yun, Semanek, David, Desai, Karan, Guo, Jia, Posner, Jonathan, Laine, Andrew F.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9005752/
https://www.ncbi.nlm.nih.gov/pubmed/35431841
http://dx.doi.org/10.3389/fnhum.2022.877326
_version_ 1784686525321052160
author Ettehadi, Nabil
Kashyap, Pratik
Zhang, Xuzhe
Wang, Yun
Semanek, David
Desai, Karan
Guo, Jia
Posner, Jonathan
Laine, Andrew F.
author_facet Ettehadi, Nabil
Kashyap, Pratik
Zhang, Xuzhe
Wang, Yun
Semanek, David
Desai, Karan
Guo, Jia
Posner, Jonathan
Laine, Andrew F.
author_sort Ettehadi, Nabil
collection PubMed
description Diffusion MRI (dMRI) is widely used to investigate neuronal and structural development of brain. dMRI data is often contaminated with various types of artifacts. Hence, artifact type identification in dMRI volumes is an essential pre-processing step prior to carrying out any further analysis. Manual artifact identification amongst a large pool of dMRI data is a highly labor-intensive task. Previous attempts at automating this process are often limited to a binary classification (“poor” vs. “good” quality) of the dMRI volumes or focus on detecting a single type of artifact (e.g., motion, Eddy currents, etc.). In this work, we propose a deep learning-based automated multiclass artifact classifier for dMRI volumes. Our proposed framework operates in 2 steps. In the first step, the model predicts labels associated with 3D mutually exclusive collectively exhaustive (MECE) sub-volumes or “slabs” extracted from whole dMRI volumes. In the second step, through a voting process, the model outputs the artifact class present in the whole volume under investigation. We used two different datasets for training and evaluating our model. Specifically, we utilized 2,494 poor-quality dMRI volumes from the Adolescent Brain Cognitive Development (ABCD) and 4,226 from the Healthy Brain Network (HBN) dataset. Our results demonstrate accurate multiclass volume-level main artifact type prediction with 96.61 and 97.52% average accuracies on the ABCD and HBN test sets, respectively. Finally, in order to demonstrate the effectiveness of the proposed framework in dMRI pre-processing pipelines, we conducted a proof-of-concept dMRI analysis exploring the relationship between whole-brain fractional anisotropy (FA) and participant age, to test whether the use of our model improves the brain-age association.
format Online
Article
Text
id pubmed-9005752
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-90057522022-04-14 Automated Multiclass Artifact Detection in Diffusion MRI Volumes via 3D Residual Squeeze-and-Excitation Convolutional Neural Networks Ettehadi, Nabil Kashyap, Pratik Zhang, Xuzhe Wang, Yun Semanek, David Desai, Karan Guo, Jia Posner, Jonathan Laine, Andrew F. Front Hum Neurosci Neuroscience Diffusion MRI (dMRI) is widely used to investigate neuronal and structural development of brain. dMRI data is often contaminated with various types of artifacts. Hence, artifact type identification in dMRI volumes is an essential pre-processing step prior to carrying out any further analysis. Manual artifact identification amongst a large pool of dMRI data is a highly labor-intensive task. Previous attempts at automating this process are often limited to a binary classification (“poor” vs. “good” quality) of the dMRI volumes or focus on detecting a single type of artifact (e.g., motion, Eddy currents, etc.). In this work, we propose a deep learning-based automated multiclass artifact classifier for dMRI volumes. Our proposed framework operates in 2 steps. In the first step, the model predicts labels associated with 3D mutually exclusive collectively exhaustive (MECE) sub-volumes or “slabs” extracted from whole dMRI volumes. In the second step, through a voting process, the model outputs the artifact class present in the whole volume under investigation. We used two different datasets for training and evaluating our model. Specifically, we utilized 2,494 poor-quality dMRI volumes from the Adolescent Brain Cognitive Development (ABCD) and 4,226 from the Healthy Brain Network (HBN) dataset. Our results demonstrate accurate multiclass volume-level main artifact type prediction with 96.61 and 97.52% average accuracies on the ABCD and HBN test sets, respectively. Finally, in order to demonstrate the effectiveness of the proposed framework in dMRI pre-processing pipelines, we conducted a proof-of-concept dMRI analysis exploring the relationship between whole-brain fractional anisotropy (FA) and participant age, to test whether the use of our model improves the brain-age association. Frontiers Media S.A. 2022-03-30 /pmc/articles/PMC9005752/ /pubmed/35431841 http://dx.doi.org/10.3389/fnhum.2022.877326 Text en Copyright © 2022 Ettehadi, Kashyap, Zhang, Wang, Semanek, Desai, Guo, Posner and Laine. 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
Ettehadi, Nabil
Kashyap, Pratik
Zhang, Xuzhe
Wang, Yun
Semanek, David
Desai, Karan
Guo, Jia
Posner, Jonathan
Laine, Andrew F.
Automated Multiclass Artifact Detection in Diffusion MRI Volumes via 3D Residual Squeeze-and-Excitation Convolutional Neural Networks
title Automated Multiclass Artifact Detection in Diffusion MRI Volumes via 3D Residual Squeeze-and-Excitation Convolutional Neural Networks
title_full Automated Multiclass Artifact Detection in Diffusion MRI Volumes via 3D Residual Squeeze-and-Excitation Convolutional Neural Networks
title_fullStr Automated Multiclass Artifact Detection in Diffusion MRI Volumes via 3D Residual Squeeze-and-Excitation Convolutional Neural Networks
title_full_unstemmed Automated Multiclass Artifact Detection in Diffusion MRI Volumes via 3D Residual Squeeze-and-Excitation Convolutional Neural Networks
title_short Automated Multiclass Artifact Detection in Diffusion MRI Volumes via 3D Residual Squeeze-and-Excitation Convolutional Neural Networks
title_sort automated multiclass artifact detection in diffusion mri volumes via 3d residual squeeze-and-excitation convolutional neural networks
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9005752/
https://www.ncbi.nlm.nih.gov/pubmed/35431841
http://dx.doi.org/10.3389/fnhum.2022.877326
work_keys_str_mv AT ettehadinabil automatedmulticlassartifactdetectionindiffusionmrivolumesvia3dresidualsqueezeandexcitationconvolutionalneuralnetworks
AT kashyappratik automatedmulticlassartifactdetectionindiffusionmrivolumesvia3dresidualsqueezeandexcitationconvolutionalneuralnetworks
AT zhangxuzhe automatedmulticlassartifactdetectionindiffusionmrivolumesvia3dresidualsqueezeandexcitationconvolutionalneuralnetworks
AT wangyun automatedmulticlassartifactdetectionindiffusionmrivolumesvia3dresidualsqueezeandexcitationconvolutionalneuralnetworks
AT semanekdavid automatedmulticlassartifactdetectionindiffusionmrivolumesvia3dresidualsqueezeandexcitationconvolutionalneuralnetworks
AT desaikaran automatedmulticlassartifactdetectionindiffusionmrivolumesvia3dresidualsqueezeandexcitationconvolutionalneuralnetworks
AT guojia automatedmulticlassartifactdetectionindiffusionmrivolumesvia3dresidualsqueezeandexcitationconvolutionalneuralnetworks
AT posnerjonathan automatedmulticlassartifactdetectionindiffusionmrivolumesvia3dresidualsqueezeandexcitationconvolutionalneuralnetworks
AT laineandrewf automatedmulticlassartifactdetectionindiffusionmrivolumesvia3dresidualsqueezeandexcitationconvolutionalneuralnetworks