Brain Age Prediction Using Multi-Hop Graph Attention Combined with Convolutional Neural Network
Bioengineering · 08.03.2024 · 11 (3) · 265
DOI: 10.3390/bioengineering11030265 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering, online erschienen am 08.03.2024. Verfasst von Heejoo Lim und 5 weiteren Autor:innen. Beteiligte Einrichtung: Division of Mechanical and Biomedical Engineering, Ewha W. University, Seoul 03760, Republic of Korea. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Institute of Information & communications Technology Planning & Evaluation (IITP), FromBIO Inc. Research Funding.
Abstract (Originalsprache)
Convolutional neural networks (CNNs) have been used widely to predict biological brain age based on brain magnetic resonance (MR) images. However, CNNs focus mainly on spatially local features and their aggregates and barely on the connective information between distant regions. To overcome this issue, we propose a novel multi-hop graph attention (MGA) module that exploits both the local and global connections of image features when combined with CNNs. After insertion between convolutional layers, MGA first converts the convolution-derived feature map into graph-structured data by using patch embedding and embedding-distance-based scoring. Multi-hop connections between the graph nodes are modeled by using the Markov chain process. After performing multi-hop graph attention, MGA re-converts the graph into an updated feature map and transfers it to the next convolutional layer. We combined the MGA module with sSE (spatial squeeze and excitation)-ResNet18 for our final prediction model (MGA-sSE-ResNet18) and performed various hyperparameter evaluations to identify the optimal parameter combinations. With 2788 three-dimensional T1-weighted MR images of healthy subjects, we verified the effectiveness of MGA-sSE-ResNet18 with comparisons to four established, general-purpose CNNs and two representative brain age prediction models. The proposed model yielded an optimal performance with a mean absolute error of 2.822 years and Pearson’s correlation coefficient (PCC) of 0.968, demonstrating the potential of the MGA module to improve the accuracy of brain age prediction.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Mechanical and Biomedical Engineering, Ewha W. University, Seoul 03760, Republic of Korea.
- Graduate Program in Smart Factory, Ewha W. University, Seoul 03760, Republic of Korea.
- Ewha Brain Institute, Ewha W. University, Seoul 03760, Republic of Korea.
- Department of Brain and Cognitive Sciences, Ewha W. University, Seoul 03760, Republic of Korea.
ORCID-Profile: Yumi Song
Förderung
- National Research Foundation of Korea
- Institute of Information & communications Technology Planning & Evaluation (IITP)
- FromBIO Inc. Research Funding
- Institute of Information and Communications Technology Planning and Evaluation (IITP) Grant
Zitieren
APA
Lim, H., Joo, Y., Ha, E., Song, Y., Yoon, S., & Shin, T. (2024). Brain Age Prediction Using Multi-Hop Graph Attention Combined with Convolutional Neural Network. Bioengineering, 11(3), 265. https://doi.org/10.3390/bioengineering11030265
Vancouver
Lim H, Joo Y, Ha E, Song Y, Yoon S, Shin T. Brain Age Prediction Using Multi-Hop Graph Attention Combined with Convolutional Neural Network. Bioengineering. 2024;11(3):265. doi:10.3390/bioengineering11030265
BibTeX
@article{Lim2024,
author = {Lim, Heejoo and Joo, Yoonji and Ha, Eunji and Song, Yumi and Yoon, Sujung and Shin, Taehoon},
title = {Brain Age Prediction Using Multi-Hop Graph Attention Combined with Convolutional Neural Network},
journal = {Bioengineering},
year = {2024},
volume = {11},
number = {3},
pages = {265},
doi = {10.3390/bioengineering11030265}
}
EUVIMED