Cargando…

Arbitrary Scale Super-Resolution for Brain MRI Images

Recent attempts at Super-Resolution for medical images used deep learning techniques such as Generative Adversarial Networks (GANs) to achieve perceptually realistic single image Super-Resolution. Yet, they are constrained by their inability to generalise to different scale factors. This involves hi...

Descripción completa

Detalles Bibliográficos
Autores principales: Tan, Chuan, Zhu, Jin, Lio’, Pietro
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7256400/
http://dx.doi.org/10.1007/978-3-030-49161-1_15
_version_ 1783539900030648320
author Tan, Chuan
Zhu, Jin
Lio’, Pietro
author_facet Tan, Chuan
Zhu, Jin
Lio’, Pietro
author_sort Tan, Chuan
collection PubMed
description Recent attempts at Super-Resolution for medical images used deep learning techniques such as Generative Adversarial Networks (GANs) to achieve perceptually realistic single image Super-Resolution. Yet, they are constrained by their inability to generalise to different scale factors. This involves high storage and energy costs as every integer scale factor involves a separate neural network. A recent paper has proposed a novel meta-learning technique that uses a Weight Prediction Network to enable Super-Resolution on arbitrary scale factors using only a single neural network. In this paper, we propose a new network that combines that technique with SRGAN, a state-of-the-art GAN-based architecture, to achieve arbitrary scale, high fidelity Super-Resolution for medical images. By using this network to perform arbitrary scale magnifications on images from the Multimodal Brain Tumor Segmentation Challenge (BraTS) dataset, we demonstrate that it is able to outperform traditional interpolation methods by up to 20[Formula: see text] on SSIM scores whilst retaining generalisability on brain MRI images. We show that performance across scales is not compromised, and that it is able to achieve competitive results with other state-of-the-art methods such as EDSR whilst being fifty times smaller than them. Combining efficiency, performance, and generalisability, this can hopefully become a new foundation for tackling Super-Resolution on medical images.
format Online
Article
Text
id pubmed-7256400
institution National Center for Biotechnology Information
language English
publishDate 2020
record_format MEDLINE/PubMed
spelling pubmed-72564002020-05-29 Arbitrary Scale Super-Resolution for Brain MRI Images Tan, Chuan Zhu, Jin Lio’, Pietro Artificial Intelligence Applications and Innovations Article Recent attempts at Super-Resolution for medical images used deep learning techniques such as Generative Adversarial Networks (GANs) to achieve perceptually realistic single image Super-Resolution. Yet, they are constrained by their inability to generalise to different scale factors. This involves high storage and energy costs as every integer scale factor involves a separate neural network. A recent paper has proposed a novel meta-learning technique that uses a Weight Prediction Network to enable Super-Resolution on arbitrary scale factors using only a single neural network. In this paper, we propose a new network that combines that technique with SRGAN, a state-of-the-art GAN-based architecture, to achieve arbitrary scale, high fidelity Super-Resolution for medical images. By using this network to perform arbitrary scale magnifications on images from the Multimodal Brain Tumor Segmentation Challenge (BraTS) dataset, we demonstrate that it is able to outperform traditional interpolation methods by up to 20[Formula: see text] on SSIM scores whilst retaining generalisability on brain MRI images. We show that performance across scales is not compromised, and that it is able to achieve competitive results with other state-of-the-art methods such as EDSR whilst being fifty times smaller than them. Combining efficiency, performance, and generalisability, this can hopefully become a new foundation for tackling Super-Resolution on medical images. 2020-05-06 /pmc/articles/PMC7256400/ http://dx.doi.org/10.1007/978-3-030-49161-1_15 Text en © IFIP International Federation for Information Processing 2020 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Article
Tan, Chuan
Zhu, Jin
Lio’, Pietro
Arbitrary Scale Super-Resolution for Brain MRI Images
title Arbitrary Scale Super-Resolution for Brain MRI Images
title_full Arbitrary Scale Super-Resolution for Brain MRI Images
title_fullStr Arbitrary Scale Super-Resolution for Brain MRI Images
title_full_unstemmed Arbitrary Scale Super-Resolution for Brain MRI Images
title_short Arbitrary Scale Super-Resolution for Brain MRI Images
title_sort arbitrary scale super-resolution for brain mri images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7256400/
http://dx.doi.org/10.1007/978-3-030-49161-1_15
work_keys_str_mv AT tanchuan arbitraryscalesuperresolutionforbrainmriimages
AT zhujin arbitraryscalesuperresolutionforbrainmriimages
AT liopietro arbitraryscalesuperresolutionforbrainmriimages