Adaptive k-sparse constrained dictionary learning strategy for bioluminescence tomography reconstruction
. Bioluminescence tomography (BLT) is a significant molecular imaging modality with promising potential in biomedical research. However, the reconstruction results of BLT are frequently sensitive and imprecise due to the light scattering effect and ill-posed inverse problem. . We propose an accelera...
Saved in:
| Published in: | Physics in medicine & biology Vol. 70; no. 20 |
|---|---|
| Main Authors: | , , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
England
19.10.2025
|
| Subjects: | |
| ISSN: | 1361-6560, 1361-6560 |
| Online Access: | Get more information |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | . Bioluminescence tomography (BLT) is a significant molecular imaging modality with promising potential in biomedical research. However, the reconstruction results of BLT are frequently sensitive and imprecise due to the light scattering effect and ill-posed inverse problem.
. We propose an accelerated forward-backward splitting and the difference of convex functions algorithm (AFBS-DCA) based on a dictionary learning framework. In the sparse coding phase, a k-sparsity strategy enables adaptive adjustment of the regularization parameter, improving the overall efficiency. The non-convex generalized minimax-concave regularization is employed to enhance sparsity, while Nesterov's acceleration strategy improves convergence speed. During dictionary updating, DCA is utilized to efficiently solve a non-convex optimization problem modelled as a difference of two convex functions, effectively reducing computational complexity.
. The effectiveness of the AFBS-DCA method was evaluated through numerical simulations and light source implantation experiments. It achieved the highest reconstruction accuracy with an average localization error of 0.391 mm, an average Dice coefficient (DICE) of 0.774, and a contrast-to-noise ratio of 0.872. Compared with three baseline methods, the AFBS-DCA reduced reconstruction errors by 62.8%, 52.5%, and 37.8%, respectively.
. The proposed AFBS-DCA method demonstrates superior performance in terms of localization accuracy, morphological recovery, and robustness, indicating its potential to advance the practical application of BLT in biomedical research and molecular imaging. |
|---|---|
| AbstractList | . Bioluminescence tomography (BLT) is a significant molecular imaging modality with promising potential in biomedical research. However, the reconstruction results of BLT are frequently sensitive and imprecise due to the light scattering effect and ill-posed inverse problem.
. We propose an accelerated forward-backward splitting and the difference of convex functions algorithm (AFBS-DCA) based on a dictionary learning framework. In the sparse coding phase, a k-sparsity strategy enables adaptive adjustment of the regularization parameter, improving the overall efficiency. The non-convex generalized minimax-concave regularization is employed to enhance sparsity, while Nesterov's acceleration strategy improves convergence speed. During dictionary updating, DCA is utilized to efficiently solve a non-convex optimization problem modelled as a difference of two convex functions, effectively reducing computational complexity.
. The effectiveness of the AFBS-DCA method was evaluated through numerical simulations and light source implantation experiments. It achieved the highest reconstruction accuracy with an average localization error of 0.391 mm, an average Dice coefficient (DICE) of 0.774, and a contrast-to-noise ratio of 0.872. Compared with three baseline methods, the AFBS-DCA reduced reconstruction errors by 62.8%, 52.5%, and 37.8%, respectively.
. The proposed AFBS-DCA method demonstrates superior performance in terms of localization accuracy, morphological recovery, and robustness, indicating its potential to advance the practical application of BLT in biomedical research and molecular imaging. Bioluminescence tomography (BLT) is a significant molecular imaging modality with promising potential in biomedical research. However, the reconstruction results of BLT are frequently sensitive and imprecise due to the light scattering effect and ill-posed inverse problem.OBJECTIVEBioluminescence tomography (BLT) is a significant molecular imaging modality with promising potential in biomedical research. However, the reconstruction results of BLT are frequently sensitive and imprecise due to the light scattering effect and ill-posed inverse problem.We propose an accelerated forward-backward splitting and the difference of convex functions algorithm (AFBS-DCA) based on a dictionary learning framework. In the sparse coding phase, a k-sparsity strategy enables adaptive adjustment of the regularization parameter, improving the overall efficiency. The non-convex generalized minimax-concave (GMC) regularization is employed to enhance sparsity, while Nesterov's acceleration strategy improves convergence speed. During dictionary updating, DCA is utilized to efficiently solve a non-convex optimization problem modelled as a difference of two convex functions, effectively reducing computational complexity.APPROACHWe propose an accelerated forward-backward splitting and the difference of convex functions algorithm (AFBS-DCA) based on a dictionary learning framework. In the sparse coding phase, a k-sparsity strategy enables adaptive adjustment of the regularization parameter, improving the overall efficiency. The non-convex generalized minimax-concave (GMC) regularization is employed to enhance sparsity, while Nesterov's acceleration strategy improves convergence speed. During dictionary updating, DCA is utilized to efficiently solve a non-convex optimization problem modelled as a difference of two convex functions, effectively reducing computational complexity.The effectiveness of the AFBS-DCA method was evaluated through numerical simulations and light source implantation experiments. It achieved the highest reconstruction accuracy with an average localization error (LE) of 0.391 mm, an average Dice coefficient (DICE) of 0.774, and a contrast-to-noise ratio (CNR) of 0.872. Compared with three baseline methods, the AFBS-DCA reduced reconstruction errors by 62.8%, 52.5%, and 37.8%, respectively.MAIN RESULTSThe effectiveness of the AFBS-DCA method was evaluated through numerical simulations and light source implantation experiments. It achieved the highest reconstruction accuracy with an average localization error (LE) of 0.391 mm, an average Dice coefficient (DICE) of 0.774, and a contrast-to-noise ratio (CNR) of 0.872. Compared with three baseline methods, the AFBS-DCA reduced reconstruction errors by 62.8%, 52.5%, and 37.8%, respectively.The proposed AFBS-DCA method demonstrates superior performance in terms of localization accuracy, morphological recovery, and robustness, indicating its potential to advance the practical application of BLT in biomedical research and molecular imaging.SIGNIFICANCEThe proposed AFBS-DCA method demonstrates superior performance in terms of localization accuracy, morphological recovery, and robustness, indicating its potential to advance the practical application of BLT in biomedical research and molecular imaging. |
| Author | Cai, Nannan Chen, Yi Hao, Xingxing Yang, Bianbian Gao, Chengyi Cao, Xin Yi, Huangjian He, Yiting |
| Author_xml | – sequence: 1 givenname: Bianbian surname: Yang fullname: Yang, Bianbian organization: School of Information Science and Technology, Northwest University, Xi'an, Shaanxi 710127, People's Republic of China – sequence: 2 givenname: Yiting surname: He fullname: He, Yiting organization: School of Information Science and Technology, Northwest University, Xi'an, Shaanxi 710127, People's Republic of China – sequence: 3 givenname: Nannan surname: Cai fullname: Cai, Nannan organization: School of Information Science and Technology, Northwest University, Xi'an, Shaanxi 710127, People's Republic of China – sequence: 4 givenname: Yi surname: Chen fullname: Chen, Yi organization: School of Electrical and Mechanical Engineering, The University of Adelaide, Adelaide, SA 5005, Australia – sequence: 5 givenname: Huangjian surname: Yi fullname: Yi, Huangjian organization: School of Information Science and Technology, Northwest University, Xi'an, Shaanxi 710127, People's Republic of China – sequence: 6 givenname: Xingxing surname: Hao fullname: Hao, Xingxing organization: School of Information Science and Technology, Northwest University, Xi'an, Shaanxi 710127, People's Republic of China – sequence: 7 givenname: Chengyi surname: Gao fullname: Gao, Chengyi organization: Department of Oncology, The First Affiliated Hospital, Xi'an Jiaotong University, Xi'an, Shaanxi 710061, People's Republic of China – sequence: 8 givenname: Xin orcidid: 0000-0003-3560-6523 surname: Cao fullname: Cao, Xin organization: School of Information Science and Technology, Northwest University, Xi'an, Shaanxi 710127, People's Republic of China |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/41005351$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkE1PwzAMhiM0xD7gzgnlyKUscdOuPU4TX9IkLnCu0sTdAm1Skhap_56ODcTJlv3o0WvPycQ6i4Rcc3bHWZYteZzyKE1StpTIVMLPyOxvNPnXT8k8hHfGOM9AXJCp4IwlccJnZL_Wsu3MF9KPKLTSB6TK2dB5aSxqqo3qjLPSD7RG6a2xO3pYdrgbaOU8LY2r-2Zkg0KrkHaucTsv2_1APR5N_Y_ikpxXsg54daoL8vZw_7p5irYvj8-b9TZSkPMu0mnJKjhk1pzlEsoYhUhliaXAFcdErHQOGmRSVirVCjPAqgIFMcZaixhgQW6P3ta7zx5DVzRmzFbX0qLrQxFDInLgAGxEb05oXzaoi9abZry0-P0OfAOphGxs |
| ContentType | Journal Article |
| Copyright | 2025 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved. |
| Copyright_xml | – notice: 2025 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved. |
| DBID | CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1088/1361-6560/ae0c51 |
| DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Medicine Biology Physics |
| EISSN | 1361-6560 |
| ExternalDocumentID | 41005351 |
| Genre | Journal Article |
| GroupedDBID | --- -DZ -~X 123 1JI 4.4 5B3 5RE 5VS 5ZH 7.M 7.Q AAGCD AAJIO AAJKP AATNI ABCXL ABHWH ABJNI ABLJU ABQJV ABUFD ABVAM ACAFW ACGFS ACHIP ADEQX AEFHF AEINN AENEX AFYNE AKPSB ALMA_UNASSIGNED_HOLDINGS AOAED ASPBG ATQHT AVWKF AZFZN CBCFC CEBXE CGR CJUJL CRLBU CS3 CUY CVF DU5 EBS ECM EDWGO EIF EJD EMSAF EPQRW EQZZN F5P IHE IJHAN IOP IZVLO KOT LAP N5L N9A NPM P2P PJBAE R4D RIN RNS RO9 ROL RPA SY9 TN5 W28 XPP 7X8 |
| ID | FETCH-LOGICAL-c291t-d6b0f26560d109a2b3e446abeb4e71e547d92d2a5bfc6dce82eff2c23e3dd4322 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001590332300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1361-6560 |
| IngestDate | Sat Sep 27 17:45:38 EDT 2025 Fri Oct 10 01:53:17 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 20 |
| Keywords | dictionary learning framework k-sparsity strategy inverse problem bioluminescence tomography |
| Language | English |
| License | 2025 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c291t-d6b0f26560d109a2b3e446abeb4e71e547d92d2a5bfc6dce82eff2c23e3dd4322 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0003-3560-6523 |
| PMID | 41005351 |
| PQID | 3254921220 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_3254921220 pubmed_primary_41005351 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-10-19 |
| PublicationDateYYYYMMDD | 2025-10-19 |
| PublicationDate_xml | – month: 10 year: 2025 text: 2025-10-19 day: 19 |
| PublicationDecade | 2020 |
| PublicationPlace | England |
| PublicationPlace_xml | – name: England |
| PublicationTitle | Physics in medicine & biology |
| PublicationTitleAlternate | Phys Med Biol |
| PublicationYear | 2025 |
| SSID | ssj0011824 |
| Score | 2.4831822 |
| Snippet | . Bioluminescence tomography (BLT) is a significant molecular imaging modality with promising potential in biomedical research. However, the reconstruction... Bioluminescence tomography (BLT) is a significant molecular imaging modality with promising potential in biomedical research. However, the reconstruction... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| SubjectTerms | Algorithms Image Processing, Computer-Assisted - methods Luminescent Measurements - methods Machine Learning Tomography - methods |
| Title | Adaptive k-sparse constrained dictionary learning strategy for bioluminescence tomography reconstruction |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/41005351 https://www.proquest.com/docview/3254921220 |
| Volume | 70 |
| WOSCitedRecordID | wos001590332300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEA5qVbz4qK_6IoLX0E2y3cdJili8tPSg0FvJZhIt0m3ttkL_vZndtD0Jgpc9hF1YsjPffslMvo-QhzQSNkxjYKm1GQtDpVkSuXyEOLKOy4U80ElpNhH3eslgkPb9hlvh2ypXmFgCNUw07pE3Ja5kHM6K4HH6xdA1Cqur3kJjm9SkozLY0hUPNlUEx50rU9uIMxSZ8WVKl1jN9VhTmUC3-O8Es_zRdI7--4rH5NBTTNquYuKEbJm8TvYq08llnex3fTndDZb9n7o4JR9tUFNEPvrJHMbMCkM1Mkc0kDBAYVQef1CzJfU2E--0qHRtl9TRXopaTosxttBrhAo6n4y9FjYtl9xrmdoz8tZ5fn16Yd6EgWmR8jmDKAuswJkCHqRKZNK4FaTKTBaamJtWGEMqQKhWZnUE2iTCWCu0kEYChA4uzslOPsnNJaGBuzUOAIS0MgQJGedWJzzIIhkrwaFB7lfzOnRBjpULlZvJohhuZrZBLqqPM5xWahxDF06oUcOv_vD0NTkQ6N-LHSnpDalZl-Lmluzq7_momN2V0eOuvX73B7kV0Rk |
| linkProvider | ProQuest |
| 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=Adaptive+k-sparse+constrained+dictionary+learning+strategy+for+bioluminescence+tomography+reconstruction&rft.jtitle=Physics+in+medicine+%26+biology&rft.au=Yang%2C+Bianbian&rft.au=He%2C+Yiting&rft.au=Cai%2C+Nannan&rft.au=Chen%2C+Yi&rft.date=2025-10-19&rft.eissn=1361-6560&rft.volume=70&rft.issue=20&rft_id=info:doi/10.1088%2F1361-6560%2Fae0c51&rft_id=info%3Apmid%2F41005351&rft_id=info%3Apmid%2F41005351&rft.externalDocID=41005351 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1361-6560&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1361-6560&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1361-6560&client=summon |