A new generative adversarial network for medical images super resolution

<div><p>For medical image analysis, there is always an immense need for rich details in an image. Typically, the diagnosis will be served best if the fine details in the image are retained and the image is available in high resolution. In medical imaging, acquiring high-resolution images...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Waqar Ahmad (1953211) (author)
مؤلفون آخرون: Hazrat Ali (421019) (author), Zubair Shah (231886) (author), Shoaib Azmat (18418572) (author)
منشور في: 2022
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513519099052032
author Waqar Ahmad (1953211)
author2 Hazrat Ali (421019)
Zubair Shah (231886)
Shoaib Azmat (18418572)
author2_role author
author
author
author_facet Waqar Ahmad (1953211)
Hazrat Ali (421019)
Zubair Shah (231886)
Shoaib Azmat (18418572)
author_role author
dc.creator.none.fl_str_mv Waqar Ahmad (1953211)
Hazrat Ali (421019)
Zubair Shah (231886)
Shoaib Azmat (18418572)
dc.date.none.fl_str_mv 2022-06-09T03:00:00Z
dc.identifier.none.fl_str_mv 10.1038/s41598-022-13658-4
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_new_generative_adversarial_network_for_medical_images_super_resolution/25658907
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Mathematical sciences
Numerical and computational mathematics
Medical image analysis
High-resolution imaging
Deep learning
Super resolution
Generative Adversarial Network (GAN)
dc.title.none.fl_str_mv A new generative adversarial network for medical images super resolution
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <div><p>For medical image analysis, there is always an immense need for rich details in an image. Typically, the diagnosis will be served best if the fine details in the image are retained and the image is available in high resolution. In medical imaging, acquiring high-resolution images is challenging and costly as it requires sophisticated and expensive instruments, trained human resources, and often causes operation delays. Deep learning based super resolution techniques can help us to extract rich details from a low-resolution image acquired using the existing devices. In this paper, we propose a new Generative Adversarial Network (GAN) based architecture for medical images, which maps low-resolution medical images to high-resolution images. The proposed architecture is divided into three steps. In the first step, we use a multi-path architecture to extract shallow features on multiple scales instead of single scale. In the second step, we use a ResNet34 architecture to extract deep features and upscale the features map by a factor of two. In the third step, we extract features of the upscaled version of the image using a residual connection-based mini-CNN and again upscale the feature map by a factor of two. The progressive upscaling overcomes the limitation for previous methods in generating true colors. Finally, we use a reconstruction convolutional layer to map back the upscaled features to a high-resolution image. Our addition of an extra loss term helps in overcoming large errors, thus, generating more realistic and smooth images. We evaluate the proposed architecture on four different medical image modalities: (1) the DRIVE and STARE datasets of retinal fundoscopy images, (2) the BraTS dataset of brain MRI, (3) the ISIC skin cancer dataset of dermoscopy images, and (4) the CAMUS dataset of cardiac ultrasound images. The proposed architecture achieves superior accuracy compared to other state-of-the-art super-resolution architectures.</p><p> </p></div><h2>Other Information</h2> <p> Published in: Scientific Reports<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1038/s41598-022-13658-4" target="_blank">https://dx.doi.org/10.1038/s41598-022-13658-4</a></p>
eu_rights_str_mv openAccess
id Manara2_64b63f0add6ad992c7d03c34b9b2e7fa
identifier_str_mv 10.1038/s41598-022-13658-4
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25658907
publishDate 2022
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A new generative adversarial network for medical images super resolutionWaqar Ahmad (1953211)Hazrat Ali (421019)Zubair Shah (231886)Shoaib Azmat (18418572)Mathematical sciencesNumerical and computational mathematicsMedical image analysisHigh-resolution imagingDeep learningSuper resolutionGenerative Adversarial Network (GAN)<div><p>For medical image analysis, there is always an immense need for rich details in an image. Typically, the diagnosis will be served best if the fine details in the image are retained and the image is available in high resolution. In medical imaging, acquiring high-resolution images is challenging and costly as it requires sophisticated and expensive instruments, trained human resources, and often causes operation delays. Deep learning based super resolution techniques can help us to extract rich details from a low-resolution image acquired using the existing devices. In this paper, we propose a new Generative Adversarial Network (GAN) based architecture for medical images, which maps low-resolution medical images to high-resolution images. The proposed architecture is divided into three steps. In the first step, we use a multi-path architecture to extract shallow features on multiple scales instead of single scale. In the second step, we use a ResNet34 architecture to extract deep features and upscale the features map by a factor of two. In the third step, we extract features of the upscaled version of the image using a residual connection-based mini-CNN and again upscale the feature map by a factor of two. The progressive upscaling overcomes the limitation for previous methods in generating true colors. Finally, we use a reconstruction convolutional layer to map back the upscaled features to a high-resolution image. Our addition of an extra loss term helps in overcoming large errors, thus, generating more realistic and smooth images. We evaluate the proposed architecture on four different medical image modalities: (1) the DRIVE and STARE datasets of retinal fundoscopy images, (2) the BraTS dataset of brain MRI, (3) the ISIC skin cancer dataset of dermoscopy images, and (4) the CAMUS dataset of cardiac ultrasound images. The proposed architecture achieves superior accuracy compared to other state-of-the-art super-resolution architectures.</p><p> </p></div><h2>Other Information</h2> <p> Published in: Scientific Reports<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1038/s41598-022-13658-4" target="_blank">https://dx.doi.org/10.1038/s41598-022-13658-4</a></p>2022-06-09T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1038/s41598-022-13658-4https://figshare.com/articles/journal_contribution/A_new_generative_adversarial_network_for_medical_images_super_resolution/25658907CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/256589072022-06-09T03:00:00Z
spellingShingle A new generative adversarial network for medical images super resolution
Waqar Ahmad (1953211)
Mathematical sciences
Numerical and computational mathematics
Medical image analysis
High-resolution imaging
Deep learning
Super resolution
Generative Adversarial Network (GAN)
status_str publishedVersion
title A new generative adversarial network for medical images super resolution
title_full A new generative adversarial network for medical images super resolution
title_fullStr A new generative adversarial network for medical images super resolution
title_full_unstemmed A new generative adversarial network for medical images super resolution
title_short A new generative adversarial network for medical images super resolution
title_sort A new generative adversarial network for medical images super resolution
topic Mathematical sciences
Numerical and computational mathematics
Medical image analysis
High-resolution imaging
Deep learning
Super resolution
Generative Adversarial Network (GAN)