Publication detail

Superresolution of MRI brain images using unbalanced 3D Dense-U-Net network

KOLAŘÍK, M. BURGET, R. UHER, V. POVODA, L.

Original Title

Superresolution of MRI brain images using unbalanced 3D Dense-U-Net network

Type

conference paper

Language

English

Original Abstract

This paper proposes an unbalanced end-to-end trained 3D Dense-U-Net network for brain MRI images superresolution. We evaluated capabilites of the proposed architecture on upsampling the MRI brain scans in the factor of 2, 4 and 8 and compared the results with resampled images using lanczos, spline and bilinear interpolation achieving best results. While the network does not exceed superresolution capabilites of state-of-the-art GAN networks, it does not require large dataset, is easy to train and capable of processing 3D images in resolution suitable for medical image processing.

Keywords

3D; brain; mri; neural networks; superresolution; u-net

Authors

KOLAŘÍK, M.; BURGET, R.; UHER, V.; POVODA, L.

Released

1. 7. 2019

ISBN

978-1-7281-1864-2

Book

2019 42nd International Conference on Telecommunications and Signal Processing (TSP)

Pages from

643

Pages to

646

Pages count

4

URL

BibTex

@inproceedings{BUT157997,
  author="Martin {Kolařík} and Radim {Burget} and Václav {Uher} and Lukáš {Povoda}",
  title="Superresolution of MRI brain images using unbalanced 3D Dense-U-Net network",
  booktitle="2019 42nd International Conference on Telecommunications and Signal Processing (TSP)",
  year="2019",
  pages="643--646",
  doi="10.1109/TSP.2019.8768829",
  isbn="978-1-7281-1864-2",
  url="https://ieeexplore.ieee.org/abstract/document/8768829"
}