Published on Mon Sep 07 2020

Going deeper with brain morphometry using neural networks

Rodrigo Santa Cruz, Léo Lebrat, Pierrick Bourgeat, Vincent Doré, Jason Dowling, Jurgen Fripp, Clinton Fookes, Olivier Salvado

Brain morphometry from magnetic resonance imaging (MRI) is a consolidated biomarker for many neurodegenerative diseases. Recent advances in this domain demonstrate that deep convolutional neural networks can infer morphometric measurements within a few seconds.

0
0
0
Abstract

Brain morphometry from magnetic resonance imaging (MRI) is a consolidated biomarker for many neurodegenerative diseases. Recent advances in this domain indicate that deep convolutional neural networks can infer morphometric measurements within a few seconds. Nevertheless, the accuracy of the devised model for insightful bio-markers (mean curvature and thickness) remains unsatisfactory. In this paper, we propose a more accurate and efficient neural network model for brain morphometry named HerstonNet. More specifically, we develop a 3D ResNet-based neural network to learn rich features directly from MRI, design a multi-scale regression scheme by predicting morphometric measures at feature maps of different resolutions, and leverage a robust optimization method to avoid poor quality minima and reduce the prediction variance. As a result, HerstonNet improves the existing approach by 24.30% in terms of intraclass correlation coefficient (agreement measure) to FreeSurfer silver-standards while maintaining a competitive run-time.

Sun Oct 04 2020
Machine Learning
Surface Agnostic Metrics for Cortical Volume Segmentation and Regression
The cerebral cortex performs higher-order brain functions and is thus implicated in a range of cognitive disorders. Current analysis of cortical variation is typically performed by fitting surface mesh models to inner and outer cortical boundaries. Our proposed model is tested on a clinical cohort for which surface-based modelling often fails.
0
0
0
Fri May 11 2018
Computer Vision
Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration
Traditional deformable registration techniques achieve impressive results andoffer a rigorous theoretical treatment. They are computationally intensive since they solve an optimization problem for each image pair. We present a probabilistic generative model and derive an unsupervised learning-based inference algorithm.
0
0
0
Wed Jun 02 2021
Computer Vision
Benchmarking CNN on 3D Anatomical Brain MRI: Architectures, Data Augmentation and Deep Ensemble Learning
Deep Learning (DL) and specifically CNN models have become a de facto method for a wide range of vision tasks. We found that all models provide significantly better predictions with VBM images than quasi-raw data. We also showed that linear models perform comparably with SOTA CNN on VBM data. Surprisingly, we did not find any clear benefit from data augmentation techniques.
4
2
0
Wed May 24 2017
Computer Vision
Deep Learning Improves Template Matching by Normalized Cross Correlation
Template matching by normalized cross correlation (NCC) is widely used for finding image correspondences. We improve the robustness of this algorithm by preprocessing images with "siamese" convolutional networks trained to maximize the contrast between NCC values of true and false matches.
0
0
0
Mon Jun 04 2018
Computer Vision
Deep Multi-Structural Shape Analysis: Application to Neuroanatomy
We propose a deep neural network for supervised learning on neuroanatomical shapes. The network directly operates on raw point clouds without the need foresh processing or the identification of point correspondences. The proposed network consists of multiple branches, so that features for multiple structures are learned simultaneously.
0
0
0
Fri Mar 08 2019
Computer Vision
Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
Classical deformable registration techniques achieve impressive results andoffer a rigorous theoretical treatment, but are computationally intensive. Recently, learning-based methods have facilitated fast registration by learning spatial deformation functions. We present a probabilistic generative model and derive an unsupervised learning-based inference algorithm.
0
0
0