3D Deformable Convolutions for MRI classification
This work addresses MRI data classification for medical imaging applications, presenting an incremental improvement with a novel method for a known bottleneck.
The authors tackled MRI classification by proposing 3D deformable convolutions integrated into a VoxResNet architecture, showing they outperform standard convolutions and are robust to geometric variations in unprocessed 3D MR images.
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.