Generating Longitudinal Atrophy Evaluation Datasets on Brain Magnetic Resonance Images Using Convolutional Neural Networks and Segmentation Priors

Brain atrophy quantification plays a fundamental role in neuroinformatics since it permits studying brain development and neurological disorders. However, the lack of a ground truth prevents testing the accuracy of longitudinal atrophy quantification methods. We propose a deep learning framework to...

Full description

Saved in:
Bibliographic Details
Published in:Neuroinformatics (Totowa, N.J.) N.J.), 2021-07, Vol.19 (3), p.477-492
Main Authors: Bernal, Jose, Valverde, Sergi, Kushibar, Kaisar, Cabezas, Mariano, Oliver, Arnau, Lladó, Xavier
Format: Article
Language:English
Subjects:
Atrophy
Bioinformatics
Biomedical and Life Sciences
Biomedicine
Brain - diagnostic imaging
Brain - pathology
Brain mapping
Computational Biology/Bioinformatics
Computer Appl. in Life Sciences
Datasets
Deep learning
Humans
Image processing
Image Processing, Computer-Assisted
Integration
Magnetic Resonance Imaging
Neural networks
Neural Networks, Computer
Neurodevelopmental disorders
Neuroimaging
Neurological diseases
Neurology
Neurosciences
Original Article
Segmentation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Brain atrophy quantification plays a fundamental role in neuroinformatics since it permits studying brain development and neurological disorders. However, the lack of a ground truth prevents testing the accuracy of longitudinal atrophy quantification methods. We propose a deep learning framework to generate longitudinal datasets by deforming T1-w brain magnetic resonance imaging scans as requested through segmentation maps. Our proposal incorporates a cascaded multi-path U-Net optimised with a multi-objective loss which allows its paths to generate different brain regions accurately. We provided our model with baseline scans and real follow-up segmentation maps from two longitudinal datasets, ADNI and OASIS, and observed that our framework could produce synthetic follow-up scans that matched the real ones (Total scans= 584; Median absolute error: 0.03 ± 0.02; Structural similarity index: 0.98 ± 0.02; Dice similarity coefficient: 0.95 ± 0.02; Percentage of brain volume change: 0.24 ± 0.16; Jacobian integration: 1.13 ± 0.05). Compared to two relevant works generating brain lesions using U-Nets and conditional generative adversarial networks (CGAN), our proposal outperformed them significantly in most cases ( p
ISSN:1539-2791
1559-0089
DOI:10.1007/s12021-020-09499-z