Going deeper with brain morphometry using neural networks

09/07/2020

∙

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 intraclass correlation coefficient (agreement measure) to FreeSurfer silver-standards while maintaining a competitive run-time.

READ FULL TEXT

Going deeper with brain morphometry using neural networks

Predicting brain-age from raw T 1 -weighted Magnetic Resonance Imaging data using 3D Convolutional Neural Networks

A Convolutional-based Model for Early Prediction of Alzheimer's based on the Dementia Stage in the MRI Brain Images

Brain Tumor Detection using Convolutional Neural Networks with Skip Connections

Comparison of atlas-based and neural-network-based semantic segmentation for DENSE MRI images

Multi-task Deep Learning for Cerebrovascular Disease Classification and MRI-to-PET Translation

Large-Scale Unsupervised Deep Representation Learning for Brain Structure

Knee Osteoarthritis Severity Prediction using an Attentive Multi-Scale Deep Convolutional Neural Network

Going deeper with brain morphometry using neural networks

Related Research

Predicting brain-age from raw T 1 -weighted Magnetic Resonance Imaging data using 3D Convolutional Neural Networks

A Convolutional-based Model for Early Prediction of Alzheimer's based on the Dementia Stage in the MRI Brain Images

Brain Tumor Detection using Convolutional Neural Networks with Skip Connections

Comparison of atlas-based and neural-network-based semantic segmentation for DENSE MRI images

Multi-task Deep Learning for Cerebrovascular Disease Classification and MRI-to-PET Translation

Large-Scale Unsupervised Deep Representation Learning for Brain Structure

Knee Osteoarthritis Severity Prediction using an Attentive Multi-Scale Deep Convolutional Neural Network