3D Deformable Convolutions for MRI classification

11/05/2019
by   Marina Pominova, et al.
117

Deep learning convolutional neural networks have proved to be a powerful tool for MRI analysis. In current work, we explore the potential of the deformable convolutional deep neural network layers for MRI data classification. We propose new 3D deformable convolutions(d-convolutions), implement them in VoxResNet architecture and apply for structural MRI data classification. We show that 3D d-convolutions outperform standard ones and are effective for unprocessed 3D MR images being robust to particular geometrical properties of the data. Firstly proposed dVoxResNet architecture exhibits high potential for the use in MRI data classification.

READ FULL TEXT

page 3

page 4

research
09/13/2018

Linear and Deformable Image Registration with 3D Convolutional Neural Networks

Image registration and in particular deformable registration methods are...
research
12/07/2020

Deformable Gabor Feature Networks for Biomedical Image Classification

In recent years, deep learning has dominated progress in the field of me...
research
01/26/2023

Convolutional Learning on Simplicial Complexes

We propose a simplicial complex convolutional neural network (SCCNN) to ...
research
11/06/2021

Convolutional Gated MLP: Combining Convolutions gMLP

To the best of our knowledge, this is the first paper to introduce Convo...
research
06/29/2017

Tensor-based approach to accelerate deformable part models

This article provides next step towards solving speed bottleneck of any ...
research
02/19/2021

Adaptable Deformable Convolutions for Semantic Segmentation of Fisheye Images in Autonomous Driving Systems

Advanced Driver-Assistance Systems rely heavily on perception tasks such...
research
01/05/2021

Density Compensated Unrolled Networks for Non-Cartesian MRI Reconstruction

Deep neural networks have recently been thoroughly investigated as a pow...

Please sign up or login with your details

Forgot password? Click here to reset