Super‐resolution reconstruction algorithm for medical images by fusion of wavelet transform and multi‐scale adaptive feature selection
Abstract Conventional computed tomography (CT) images often suffer from blurred edges and unclear details. Image super‐resolution methods can significantly enhance CT image quality, thereby improving diagnostic accuracy. To better extract detailed features and enhance the cascading effects of differ...
Saved in:
Published in | IET image processing |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
01.10.2024
|
Online Access | Get full text |
Cover
Loading…
Abstract | Abstract Conventional computed tomography (CT) images often suffer from blurred edges and unclear details. Image super‐resolution methods can significantly enhance CT image quality, thereby improving diagnostic accuracy. To better extract detailed features and enhance the cascading effects of different feature levels, we propose a novel medical image super‐resolution algorithm that integrates discrete wavelet transform and multi‐scale adaptive feature selection. Our approach uses both the low‐resolution image and its high‐frequency component from the frequency domain as network inputs, with the high‐frequency component providing learning supervision, which enhances detail fidelity in reconstruction. Additionally, we introduce a multi‐scale adaptive feature selection module to learn from different layers of CT images and their inter‐layer correlations. Finally, the pixel information is efficiently integrated by a coordinate attention mechanism incorporating the concept of squeeze excitation. Experimental results show that our method outperforms state‐of‐the‐art methods, achieving superior reconstruction at scale factors of 2, 4, and 8, especially at scale factor 8, where it surpasses others by 1.12 in PSNR, 0.0145 in SSIM, and 0.0038 in LPIPS. Visually, our method also delivers more accurate details and better perceptual quality. |
---|---|
AbstractList | Abstract Conventional computed tomography (CT) images often suffer from blurred edges and unclear details. Image super‐resolution methods can significantly enhance CT image quality, thereby improving diagnostic accuracy. To better extract detailed features and enhance the cascading effects of different feature levels, we propose a novel medical image super‐resolution algorithm that integrates discrete wavelet transform and multi‐scale adaptive feature selection. Our approach uses both the low‐resolution image and its high‐frequency component from the frequency domain as network inputs, with the high‐frequency component providing learning supervision, which enhances detail fidelity in reconstruction. Additionally, we introduce a multi‐scale adaptive feature selection module to learn from different layers of CT images and their inter‐layer correlations. Finally, the pixel information is efficiently integrated by a coordinate attention mechanism incorporating the concept of squeeze excitation. Experimental results show that our method outperforms state‐of‐the‐art methods, achieving superior reconstruction at scale factors of 2, 4, and 8, especially at scale factor 8, where it surpasses others by 1.12 in PSNR, 0.0145 in SSIM, and 0.0038 in LPIPS. Visually, our method also delivers more accurate details and better perceptual quality. |
Author | Wang, QiaoSu Ma, Qiaomei |
Author_xml | – sequence: 1 givenname: QiaoSu surname: Wang fullname: Wang, QiaoSu organization: School of Software North University of China Taiyuan Shanxi China – sequence: 2 givenname: Qiaomei orcidid: 0009-0002-7123-0754 surname: Ma fullname: Ma, Qiaomei organization: School of Software North University of China Taiyuan Shanxi China, Shanxi Engineering and Technology Research Centre for Artificial Intelligence in Medical Imaging Taiyuan Shanxi China |
BookMark | eNo9kL9OwzAQxi1UJNrCwhN4RkqxEzuOR1TxT0JioHt0cc4lKIkj2ynqxszEM_IkpAUx3Z3u--7T_RZk1rseCbnkbMWZ0NfN4NMVz1KZnpA5V5InOs_V7L-X-owsQnhjTGpWyDn5fBkH9N8fXx6Da8fYuJ56NK4P0Y_mOEK7db6Jrx21ztMO68ZAS5sOthhotad2DAeZs_QddthipNFDHyZxR6GvaTe2sZkSwmRDCjUMsdkhtQhx9EjDZDkGnZNTC23Ai7-6JJu72836IXl6vn9c3zwlRvE0SRXHIquwMsqASHOtWCVELoVUCKKotQAuMo26qCSvJa-gtkKZFGxt82paLcnV71njXQgebTn46Rm_LzkrDxDLA8TyCDH7AeKEbYI |
Cites_doi | 10.1175/1520-0450(1979)018<1016:LFIOAT>2.0.CO;2 10.1109/CVPRW59228.2023.00135 10.1109/CVPR.2016.182 10.1109/CVPRW.2017.151 10.1016/j.bspc.2021.103412 10.1109/CVPR.2017.19 10.1016/j.irbm.2020.08.004 10.1007/11744085_23 10.1109/CVPR.2018.00262 10.1109/CVPR.2015.7298594 10.1109/TCBB.2022.3191387 10.1109/TPAMI.2015.2439281 10.1109/CVPR.2016.90 10.1109/ICCVW54120.2021.00210 10.1080/22221751.2020.1750307 10.1109/TPAMI.2020.2982166 10.1109/CVPR46437.2021.01350 10.1109/CVPR46437.2021.00352 10.3390/cancers12061672 |
ContentType | Journal Article |
DBID | AAYXX CITATION |
DOI | 10.1049/ipr2.13252 |
DatabaseName | CrossRef |
DatabaseTitle | CrossRef |
DatabaseTitleList | CrossRef |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Applied Sciences |
EISSN | 1751-9667 |
ExternalDocumentID | 10_1049_ipr2_13252 |
GroupedDBID | .DC 0R~ 1OC 24P 29I 4.4 5GY 6IK 8FE 8FG 8VB AAHHS AAHJG AAJGR AAYXX ABJCF ABQXS ACCFJ ACESK ACGFS ACIWK ACXQS ADZOD AEEZP AENEX AEQDE AFKRA AIWBW AJBDE ALMA_UNASSIGNED_HOLDINGS ALUQN ARAPS AVUZU BENPR BGLVJ CCPQU CITATION CS3 DU5 EBS EJD ESX GROUPED_DOAJ HCIFZ HZ~ IAO IFIPE IPLJI ITC JAVBF K1G L6V LAI M43 M7S MCNEO MS~ O9- OCL OK1 P2P P62 PTHSS QWB RIE RNS ROL RUI S0W ZL0 |
ID | FETCH-LOGICAL-c712-271e83bebc7ca426970b4465457ea48d94a1439e98b51d51badf47c2afdf6b143 |
ISSN | 1751-9659 |
IngestDate | Wed Oct 02 14:37:25 EDT 2024 |
IsDoiOpenAccess | false |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-c712-271e83bebc7ca426970b4465457ea48d94a1439e98b51d51badf47c2afdf6b143 |
ORCID | 0009-0002-7123-0754 |
OpenAccessLink | https://doi.org/10.1049/ipr2.13252 |
ParticipantIDs | crossref_primary_10_1049_ipr2_13252 |
PublicationCentury | 2000 |
PublicationDate | 2024-10-00 |
PublicationDateYYYYMMDD | 2024-10-01 |
PublicationDate_xml | – month: 10 year: 2024 text: 2024-10-00 |
PublicationDecade | 2020 |
PublicationTitle | IET image processing |
PublicationYear | 2024 |
References | e_1_2_11_10_1 e_1_2_11_21_1 e_1_2_11_14_1 Zhou S. (e_1_2_11_16_1) 2020; 33 e_1_2_11_13_1 e_1_2_11_9_1 e_1_2_11_12_1 e_1_2_11_23_1 e_1_2_11_8_1 e_1_2_11_11_1 e_1_2_11_22_1 e_1_2_11_7_1 e_1_2_11_18_1 e_1_2_11_6_1 e_1_2_11_17_1 e_1_2_11_5_1 e_1_2_11_4_1 e_1_2_11_15_1 e_1_2_11_3_1 e_1_2_11_2_1 e_1_2_11_19_1 Lin Y. (e_1_2_11_20_1) 2023; 50 |
References_xml | – ident: e_1_2_11_6_1 doi: 10.1175/1520-0450(1979)018<1016:LFIOAT>2.0.CO;2 – ident: e_1_2_11_21_1 doi: 10.1109/CVPRW59228.2023.00135 – ident: e_1_2_11_10_1 doi: 10.1109/CVPR.2016.182 – ident: e_1_2_11_15_1 doi: 10.1109/CVPRW.2017.151 – ident: e_1_2_11_18_1 doi: 10.1016/j.bspc.2021.103412 – ident: e_1_2_11_11_1 doi: 10.1109/CVPR.2017.19 – volume: 50 start-page: 1017 issue: 2 year: 2023 ident: e_1_2_11_20_1 article-title: A semantic attention‐based approach to medical image super‐resolution publication-title: Comput. Sci. contributor: fullname: Lin Y. – ident: e_1_2_11_5_1 doi: 10.1016/j.irbm.2020.08.004 – ident: e_1_2_11_7_1 doi: 10.1007/11744085_23 – ident: e_1_2_11_12_1 doi: 10.1109/CVPR.2018.00262 – ident: e_1_2_11_23_1 doi: 10.1109/CVPR.2015.7298594 – ident: e_1_2_11_19_1 doi: 10.1109/TCBB.2022.3191387 – ident: e_1_2_11_8_1 doi: 10.1109/TPAMI.2015.2439281 – ident: e_1_2_11_9_1 doi: 10.1109/CVPR.2016.90 – ident: e_1_2_11_14_1 doi: 10.1109/ICCVW54120.2021.00210 – volume: 33 start-page: 3499 year: 2020 ident: e_1_2_11_16_1 article-title: Cross‐scale internal graph neural network for image super‐resolution publication-title: Adv. Neural Inf. Process. Syst. contributor: fullname: Zhou S. – ident: e_1_2_11_2_1 doi: 10.1080/22221751.2020.1750307 – ident: e_1_2_11_4_1 doi: 10.1109/TPAMI.2020.2982166 – ident: e_1_2_11_13_1 doi: 10.1109/CVPR46437.2021.01350 – ident: e_1_2_11_17_1 doi: 10.1109/CVPR46437.2021.00352 – ident: e_1_2_11_3_1 doi: 10.3390/cancers12061672 – ident: e_1_2_11_22_1 |
SSID | ssj0059085 |
Score | 2.3802257 |
Snippet | Abstract Conventional computed tomography (CT) images often suffer from blurred edges and unclear details. Image super‐resolution methods can significantly... |
SourceID | crossref |
SourceType | Aggregation Database |
Title | Super‐resolution reconstruction algorithm for medical images by fusion of wavelet transform and multi‐scale adaptive feature selection |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnZ1Lb9NAEIBXoVy4QHmJR6lGgpvlEju7XvtYoValAiTUIPUW7ctgiSRWk6gqp5576m_sL-nsy3FbDoWLZW28mWi_eHdmdx6EfChLZoZcsTQfSYMGCsNXSmqRKmmGtRzlqhY2dvjrt-LgBz08ZseDwZee19JqKXfUn7_GlfwPVWxDrjZK9h_Idl-KDXiPfPGKhPF6L8ZHqxZHPLoroOEcpCXOzO1Swybi98_5SbP8NXVOhdNwNtNMhU3wgPpnvVoEvfFU2EIUS1s5wuuz7nDBeR12chbY2SRCi9bnDDcuN2iycBV1Iuag737eG3s5SesjEuJK6fbw_TzzvRHzo9V6azy2TU3T35PIaefdFqdRzrLUpir0q0y_zRffuDNxo6GCo920J_kO2sc-qe3N7Ni3Vq3Ol9CdotNqYvtOXN8H5GHOK8aige3XZVvcnbnw2PDbYrJaWn1cy-2pJz09Y7xJHgcDAXY97adkYGbPyJNgLECYihfPyYWDf3V-ucYON7FDhx2QJATs4LGDPAOPHeY1BOzQYQfEDg47SnDAIQKHABw64C_IeH9v_OkgDYU1UsUzG42VmRJfTam4EjaUmQ-ly6vHuBG01BUVqEVXpiolyzTLpNA15SoXta4LiR-9JBuz-cy8IoAdRiovFC0NpUJSgfYCY5LXemh0oYvX5H0czknr06dM7gJ7c6-n3pJH6__aFtnA0TTvUCNcym0H-hryWmsP |
link.rule.ids | 315,786,790,870,27955,27956 |
linkProvider | Directory of Open Access Journals |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Super%E2%80%90resolution+reconstruction+algorithm+for+medical+images+by+fusion+of+wavelet+transform+and+multi%E2%80%90scale+adaptive+feature+selection&rft.jtitle=IET+image+processing&rft.au=Wang%2C+QiaoSu&rft.au=Ma%2C+Qiaomei&rft.date=2024-10-01&rft.issn=1751-9659&rft.eissn=1751-9667&rft_id=info:doi/10.1049%2Fipr2.13252&rft.externalDBID=n%2Fa&rft.externalDocID=10_1049_ipr2_13252 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1751-9659&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1751-9659&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1751-9659&client=summon |