Graph-based deep learning for medical diagnosis and analysis: past, present and future

D Ahmedt-Aristizabal, MA Armin, S Denman, C Fookes… - Sensors, 2021 - mdpi.com
With the advances of data-driven machine learning research, a wide variety of prediction
problems have been tackled. It has become critical to explore how machine learning and …

Graph convolutional networks for multi-modality medical imaging: Methods, architectures, and clinical applications

K Ding, M Zhou, Z Wang, Q Liu, CW Arnold… - arXiv preprint arXiv …, 2022 - arxiv.org
Image-based characterization and disease understanding involve integrative analysis of
morphological, spatial, and topological information across biological scales. The …

Training data distribution significantly impacts the estimation of tissue microstructure with machine learning

NG Gyori, M Palombo, CA Clark… - Magnetic resonance …, 2022 - Wiley Online Library
Purpose Supervised machine learning (ML) provides a compelling alternative to traditional
model fitting for parameter mapping in quantitative MRI. The aim of this work is to …

A microstructure estimation Transformer inspired by sparse representation for diffusion MRI

T Zheng, G Yan, H Li, W Zheng, W Shi, Y Zhang… - Medical Image …, 2023 - Elsevier
Diffusion magnetic resonance imaging (dMRI) is an important tool in characterizing tissue
microstructure based on biophysical models, which are typically multi-compartmental …

Hybrid graph transformer for tissue microstructure estimation with undersampled diffusion MRI data

G Chen, H Jiang, J Liu, J Ma, H Cui, Y Xia… - … Conference on Medical …, 2022 - Springer
Advanced contemporary diffusion models for tissue microstructure often require diffusion
MRI (DMRI) data with sufficiently dense sampling in the diffusion wavevector space for …

Mesh-based graph convolutional neural networks for modeling materials with microstructure

AL Frankel, C Safta, C Alleman… - Journal of Machine …, 2022 - dl.begellhouse.com
Predicting the evolution of a representative sample of a material with microstructure is a
fundamental problem in homogenization. In this work we propose a graph convolutional …

[HTML][HTML] Optimisation of quantitative brain diffusion-relaxation MRI acquisition protocols with physics-informed machine learning

Á Planchuelo-Gómez, M Descoteaux, H Larochelle… - Medical Image …, 2024 - Elsevier
Diffusion-relaxation MRI aims to extract quantitative measures that characterise
microstructural tissue properties such as orientation, size, and shape, but long acquisition …

Multimodal super-resolved q-space deep learning

Y Qin, Y Li, Z Zhuo, Z Liu, Y Liu, C Ye - Medical Image Analysis, 2021 - Elsevier
Super-resolved q-space deep learning (SR-q-DL) has been developed to estimate high-
resolution (HR) tissue microstructure maps from low-quality diffusion magnetic resonance …

Angular super-resolution in diffusion MRI with a 3D recurrent convolutional autoencoder

M Lyon, P Armitage, MA Álvarez - … Conference on Medical …, 2022 - proceedings.mlr.press
High resolution diffusion MRI (dMRI) data is often constrained by limited scanning time in
clinical settings, thus restricting the use of downstream analysis techniques that would …

How can spherical CNNs benefit ML-based diffusion MRI parameter estimation?

T Goodwin-Allcock, J McEwen, R Gray… - International Workshop …, 2022 - Springer
This paper demonstrates spherical convolutional neural networks (S-CNN) offer distinct
advantages over conventional fully-connected networks (FCN) at estimating scalar …