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% 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.

Arbitrary scale super-resolution for brain MRI images / Tan, C.; Zhu, J.; Lio, P.. - 583:(2020), pp. 165-176. (Intervento presentato al convegno 16th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2020 tenutosi a Neos Marmaras; grc) [10.1007/978-3-030-49161-1_15].

Arbitrary scale super-resolution for brain MRI images

Lio P.
2020

Abstract

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% 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
16th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2020
Image processing; Medical image analysis; Meta-Learning; Super-Resolution
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Arbitrary scale super-resolution for brain MRI images / Tan, C.; Zhu, J.; Lio, P.. - 583:(2020), pp. 165-176. (Intervento presentato al convegno 16th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2020 tenutosi a Neos Marmaras; grc) [10.1007/978-3-030-49161-1_15].
File allegati a questo prodotto
File Dimensione Formato  
Tan_Arbitrary_2020.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.77 MB
Formato Adobe PDF
1.77 MB Adobe PDF   Contatta l'autore
tan_preprint_Arbitrary_2020.pdf

accesso aperto

Note: https://link.springer.com/chapter/10.1007/978-3-030-49161-1_15
Tipologia: Documento in Pre-print (manoscritto inviato all'editore, precedente alla peer review)
Licenza: Creative commons
Dimensione 472.22 kB
Formato Adobe PDF
472.22 kB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1720036
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 14
social impact