Cargando…

Prediction of fluid intelligence from T1-w MRI images: A precise two-step deep learning framework

The Adolescent Brain Cognitive Development (ABCD) Neurocognitive Prediction Challenge (ABCD-NP-Challenge) is a community-driven competition that challenges competitors to develop algorithms to predict fluid intelligence scores from T1-w MRI images. In this work, a two-step deep learning pipeline is...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Mingliang, Jiang, Mingfeng, Zhang, Guangming, Liu, Yujun, Zhou, Xiaobo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9345352/
https://www.ncbi.nlm.nih.gov/pubmed/35917308
http://dx.doi.org/10.1371/journal.pone.0268707
_version_ 1784761412915036160
author Li, Mingliang
Jiang, Mingfeng
Zhang, Guangming
Liu, Yujun
Zhou, Xiaobo
author_facet Li, Mingliang
Jiang, Mingfeng
Zhang, Guangming
Liu, Yujun
Zhou, Xiaobo
author_sort Li, Mingliang
collection PubMed
description The Adolescent Brain Cognitive Development (ABCD) Neurocognitive Prediction Challenge (ABCD-NP-Challenge) is a community-driven competition that challenges competitors to develop algorithms to predict fluid intelligence scores from T1-w MRI images. In this work, a two-step deep learning pipeline is proposed to improve the prediction accuracy of fluid intelligence scores. In terms of the first step, the main contributions of this study include the following: (1) the concepts of the residual network (ResNet) and the squeeze-and-excitation network (SENet) are utilized to improve the original 3D U-Net; (2) in the segmentation process, the pixels in symmetrical brain regions are assigned the same label; (3) to remove redundant background information from the segmented regions of interest (ROIs), a minimum bounding cube (MBC) is used to enclose the ROIs. This new segmentation structure can greatly improve the segmentation performance of the ROIs in the brain as compared with the classical convolutional neural network (CNN), which yields a Dice coefficient of 0.8920. In the second stage, MBCs are used to train neural network regression models for enhanced nonlinearity. The fluid intelligence score prediction results of the proposed method are found to be superior to those of current state-of-the-art approaches, and the proposed method achieves a mean square error (MSE) of 82.56 on a test data set, which reflects a very competitive performance.
format Online
Article
Text
id pubmed-9345352
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-93453522022-08-03 Prediction of fluid intelligence from T1-w MRI images: A precise two-step deep learning framework Li, Mingliang Jiang, Mingfeng Zhang, Guangming Liu, Yujun Zhou, Xiaobo PLoS One Research Article The Adolescent Brain Cognitive Development (ABCD) Neurocognitive Prediction Challenge (ABCD-NP-Challenge) is a community-driven competition that challenges competitors to develop algorithms to predict fluid intelligence scores from T1-w MRI images. In this work, a two-step deep learning pipeline is proposed to improve the prediction accuracy of fluid intelligence scores. In terms of the first step, the main contributions of this study include the following: (1) the concepts of the residual network (ResNet) and the squeeze-and-excitation network (SENet) are utilized to improve the original 3D U-Net; (2) in the segmentation process, the pixels in symmetrical brain regions are assigned the same label; (3) to remove redundant background information from the segmented regions of interest (ROIs), a minimum bounding cube (MBC) is used to enclose the ROIs. This new segmentation structure can greatly improve the segmentation performance of the ROIs in the brain as compared with the classical convolutional neural network (CNN), which yields a Dice coefficient of 0.8920. In the second stage, MBCs are used to train neural network regression models for enhanced nonlinearity. The fluid intelligence score prediction results of the proposed method are found to be superior to those of current state-of-the-art approaches, and the proposed method achieves a mean square error (MSE) of 82.56 on a test data set, which reflects a very competitive performance. Public Library of Science 2022-08-02 /pmc/articles/PMC9345352/ /pubmed/35917308 http://dx.doi.org/10.1371/journal.pone.0268707 Text en https://creativecommons.org/publicdomain/zero/1.0/This is an open access article, free of all copyright, and may be freely reproduced, distributed, transmitted, modified, built upon, or otherwise used by anyone for any lawful purpose. The work is made available under the Creative Commons CC0 (https://creativecommons.org/publicdomain/zero/1.0/) public domain dedication.
spellingShingle Research Article
Li, Mingliang
Jiang, Mingfeng
Zhang, Guangming
Liu, Yujun
Zhou, Xiaobo
Prediction of fluid intelligence from T1-w MRI images: A precise two-step deep learning framework
title Prediction of fluid intelligence from T1-w MRI images: A precise two-step deep learning framework
title_full Prediction of fluid intelligence from T1-w MRI images: A precise two-step deep learning framework
title_fullStr Prediction of fluid intelligence from T1-w MRI images: A precise two-step deep learning framework
title_full_unstemmed Prediction of fluid intelligence from T1-w MRI images: A precise two-step deep learning framework
title_short Prediction of fluid intelligence from T1-w MRI images: A precise two-step deep learning framework
title_sort prediction of fluid intelligence from t1-w mri images: a precise two-step deep learning framework
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9345352/
https://www.ncbi.nlm.nih.gov/pubmed/35917308
http://dx.doi.org/10.1371/journal.pone.0268707
work_keys_str_mv AT limingliang predictionoffluidintelligencefromt1wmriimagesaprecisetwostepdeeplearningframework
AT jiangmingfeng predictionoffluidintelligencefromt1wmriimagesaprecisetwostepdeeplearningframework
AT zhangguangming predictionoffluidintelligencefromt1wmriimagesaprecisetwostepdeeplearningframework
AT liuyujun predictionoffluidintelligencefromt1wmriimagesaprecisetwostepdeeplearningframework
AT zhouxiaobo predictionoffluidintelligencefromt1wmriimagesaprecisetwostepdeeplearningframework