Gradient-enhanced neural network and extreme gradient boosting modeling for the prediction of the 3D bone mineral density distribution from 2D-DXA scans
This study aims to predict the volumetric bone mineral density (BMD) distribution from a dual-energy X-ray absorptiometry (DXA) scan. By employing machine learning, this study bridges the gap between DXA and computed tomography (CT) in terms of volumetric bone assessment, suggesting an approach for...
Saved in:
| Published in: | Osteoporosis and Sarcopenia Vol. 11; no. 3; pp. 98 - 106 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Netherlands
Elsevier B.V
01.09.2025
Elsevier 대한골다공증학회 |
| Subjects: | |
| ISSN: | 2405-5255, 2405-5263, 2405-5263 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | This study aims to predict the volumetric bone mineral density (BMD) distribution from a dual-energy X-ray absorptiometry (DXA) scan. By employing machine learning, this study bridges the gap between DXA and computed tomography (CT) in terms of volumetric bone assessment, suggesting an approach for a cost-effective and low-radiation alternative for bone health evaluation in a three-dimensional (3D) fashion from a two-dimensional (2D) scan.
Data from 34 participants included aligned DXA and CT scans for the proximal femur. Intensity values were extracted in Hounsfield units, with 3D information mapped as target variables and 2D information as features. Two machine learning models, Extreme Gradient Boosting (XGB) and Gradient-Enhanced Neural Network (GENN), were trained using 5-fold cross-validation strategy and show an average registration accuracy of 0.89 ± 0.04, assessed thorough structural similarity index measure.
Both models were built to predict the statistics of the 3D structure of the bone from a 2D image. The GENN model outperformed XGB, achieving mean absolute percentage errors (MAPE) of 12.98 ± 1.70%, 13.28 ± 2.01%, and 9.63 ± 1.66% for minimum, maximum, and the number of nonzero pixel intensities, respectively. In contrast, XGB's errors exceeded 16% across these metrics. The loss stabilized within 100 epochs, indicating model robustness and reliability across diverse test sets.
The proposed GENN framework offers a method for predicting 3D BMD distributions from a 2D-DXA scan, rivaling CT-based assessments. This approach reduces costs and radiation exposure, presenting a viable solution for personalized bone health evaluation and early osteoporosis diagnosis. |
|---|---|
| AbstractList | Objectives: This study aims to predict the volumetric bone mineral density (BMD) distribution from a dual-energy X-ray absorptiometry (DXA) scan. By employing machine learning, this study bridges the gap between DXA and computed tomography (CT) in terms of volumetric bone assessment, suggesting an approach for a cost-effective and low-radiation alternative for bone health evaluation in a three-dimensional (3D) fashion from a twodimensional (2D) scan.
Methods: Data from 34 participants included aligned DXA and CT scans for the proximal femur. Intensity values were extracted in Hounsfield units, with 3D information mapped as target variables and 2D information as features. Two machine learning models, Extreme Gradient Boosting (XGB) and Gradient-Enhanced Neural Network (GENN), were trained using 5-fold cross-validation strategy and show an average registration accuracy of 0.89 ± 0.04, assessed thorough structural similarity index measure.
Results: Both models were built to predict the statistics of the 3D structure of the bone from a 2D image. The GENN model outperformed XGB, achieving mean absolute percentage errors (MAPE) of 12.98 ± 1.70%, 13.28 ± 2.01%, and 9.63 ± 1.66% for minimum, maximum, and the number of nonzero pixel intensities, respectively. In contrast, XGB’s errors exceeded 16% across these metrics. The loss stabilized within 100 epochs, indicating model robustness and reliability across diverse test sets.
Conclusions: The proposed GENN framework offers a method for predicting 3D BMD distributions from a 2D-DXA scan, rivaling CT-based assessments. This approach reduces costs and radiation exposure, presenting a viable solution for personalized bone health evaluation and early osteoporosis diagnosis. KCI Citation Count: 0 Objectives: This study aims to predict the volumetric bone mineral density (BMD) distribution from a dual-energy X-ray absorptiometry (DXA) scan. By employing machine learning, this study bridges the gap between DXA and computed tomography (CT) in terms of volumetric bone assessment, suggesting an approach for a cost-effective and low-radiation alternative for bone health evaluation in a three-dimensional (3D) fashion from a two-dimensional (2D) scan. Methods: Data from 34 participants included aligned DXA and CT scans for the proximal femur. Intensity values were extracted in Hounsfield units, with 3D information mapped as target variables and 2D information as features. Two machine learning models, Extreme Gradient Boosting (XGB) and Gradient-Enhanced Neural Network (GENN), were trained using 5-fold cross-validation strategy and show an average registration accuracy of 0.89 ± 0.04, assessed thorough structural similarity index measure. Results: Both models were built to predict the statistics of the 3D structure of the bone from a 2D image. The GENN model outperformed XGB, achieving mean absolute percentage errors (MAPE) of 12.98 ± 1.70%, 13.28 ± 2.01%, and 9.63 ± 1.66% for minimum, maximum, and the number of nonzero pixel intensities, respectively. In contrast, XGB's errors exceeded 16% across these metrics. The loss stabilized within 100 epochs, indicating model robustness and reliability across diverse test sets. Conclusions: The proposed GENN framework offers a method for predicting 3D BMD distributions from a 2D-DXA scan, rivaling CT-based assessments. This approach reduces costs and radiation exposure, presenting a viable solution for personalized bone health evaluation and early osteoporosis diagnosis. AbstractObjectivesThis study aims to predict the volumetric bone mineral density (BMD) distribution from a dual-energy X-ray absorptiometry (DXA) scan. By employing machine learning, this study bridges the gap between DXA and computed tomography (CT) in terms of volumetric bone assessment, suggesting an approach for a cost-effective and low-radiation alternative for bone health evaluation in a three-dimensional (3D) fashion from a two-dimensional (2D) scan. MethodsData from 34 participants included aligned DXA and CT scans for the proximal femur. Intensity values were extracted in Hounsfield units, with 3D information mapped as target variables and 2D information as features. Two machine learning models, Extreme Gradient Boosting (XGB) and Gradient-Enhanced Neural Network (GENN), were trained using 5-fold cross-validation strategy and show an average registration accuracy of 0.89 ± 0.04, assessed thorough structural similarity index measure. ResultsBoth models were built to predict the statistics of the 3D structure of the bone from a 2D image. The GENN model outperformed XGB, achieving mean absolute percentage errors (MAPE) of 12.98 ± 1.70%, 13.28 ± 2.01%, and 9.63 ± 1.66% for minimum, maximum, and the number of nonzero pixel intensities, respectively. In contrast, XGB's errors exceeded 16% across these metrics. The loss stabilized within 100 epochs, indicating model robustness and reliability across diverse test sets. ConclusionsThe proposed GENN framework offers a method for predicting 3D BMD distributions from a 2D-DXA scan, rivaling CT-based assessments. This approach reduces costs and radiation exposure, presenting a viable solution for personalized bone health evaluation and early osteoporosis diagnosis. This study aims to predict the volumetric bone mineral density (BMD) distribution from a dual-energy X-ray absorptiometry (DXA) scan. By employing machine learning, this study bridges the gap between DXA and computed tomography (CT) in terms of volumetric bone assessment, suggesting an approach for a cost-effective and low-radiation alternative for bone health evaluation in a three-dimensional (3D) fashion from a two-dimensional (2D) scan. Data from 34 participants included aligned DXA and CT scans for the proximal femur. Intensity values were extracted in Hounsfield units, with 3D information mapped as target variables and 2D information as features. Two machine learning models, Extreme Gradient Boosting (XGB) and Gradient-Enhanced Neural Network (GENN), were trained using 5-fold cross-validation strategy and show an average registration accuracy of 0.89 ± 0.04, assessed thorough structural similarity index measure. Both models were built to predict the statistics of the 3D structure of the bone from a 2D image. The GENN model outperformed XGB, achieving mean absolute percentage errors (MAPE) of 12.98 ± 1.70%, 13.28 ± 2.01%, and 9.63 ± 1.66% for minimum, maximum, and the number of nonzero pixel intensities, respectively. In contrast, XGB's errors exceeded 16% across these metrics. The loss stabilized within 100 epochs, indicating model robustness and reliability across diverse test sets. The proposed GENN framework offers a method for predicting 3D BMD distributions from a 2D-DXA scan, rivaling CT-based assessments. This approach reduces costs and radiation exposure, presenting a viable solution for personalized bone health evaluation and early osteoporosis diagnosis. This study aims to predict the volumetric bone mineral density (BMD) distribution from a dual-energy X-ray absorptiometry (DXA) scan. By employing machine learning, this study bridges the gap between DXA and computed tomography (CT) in terms of volumetric bone assessment, suggesting an approach for a cost-effective and low-radiation alternative for bone health evaluation in a three-dimensional (3D) fashion from a two-dimensional (2D) scan.ObjectivesThis study aims to predict the volumetric bone mineral density (BMD) distribution from a dual-energy X-ray absorptiometry (DXA) scan. By employing machine learning, this study bridges the gap between DXA and computed tomography (CT) in terms of volumetric bone assessment, suggesting an approach for a cost-effective and low-radiation alternative for bone health evaluation in a three-dimensional (3D) fashion from a two-dimensional (2D) scan.Data from 34 participants included aligned DXA and CT scans for the proximal femur. Intensity values were extracted in Hounsfield units, with 3D information mapped as target variables and 2D information as features. Two machine learning models, Extreme Gradient Boosting (XGB) and Gradient-Enhanced Neural Network (GENN), were trained using 5-fold cross-validation strategy and show an average registration accuracy of 0.89 ± 0.04, assessed thorough structural similarity index measure.MethodsData from 34 participants included aligned DXA and CT scans for the proximal femur. Intensity values were extracted in Hounsfield units, with 3D information mapped as target variables and 2D information as features. Two machine learning models, Extreme Gradient Boosting (XGB) and Gradient-Enhanced Neural Network (GENN), were trained using 5-fold cross-validation strategy and show an average registration accuracy of 0.89 ± 0.04, assessed thorough structural similarity index measure.Both models were built to predict the statistics of the 3D structure of the bone from a 2D image. The GENN model outperformed XGB, achieving mean absolute percentage errors (MAPE) of 12.98 ± 1.70%, 13.28 ± 2.01%, and 9.63 ± 1.66% for minimum, maximum, and the number of nonzero pixel intensities, respectively. In contrast, XGB's errors exceeded 16% across these metrics. The loss stabilized within 100 epochs, indicating model robustness and reliability across diverse test sets.ResultsBoth models were built to predict the statistics of the 3D structure of the bone from a 2D image. The GENN model outperformed XGB, achieving mean absolute percentage errors (MAPE) of 12.98 ± 1.70%, 13.28 ± 2.01%, and 9.63 ± 1.66% for minimum, maximum, and the number of nonzero pixel intensities, respectively. In contrast, XGB's errors exceeded 16% across these metrics. The loss stabilized within 100 epochs, indicating model robustness and reliability across diverse test sets.The proposed GENN framework offers a method for predicting 3D BMD distributions from a 2D-DXA scan, rivaling CT-based assessments. This approach reduces costs and radiation exposure, presenting a viable solution for personalized bone health evaluation and early osteoporosis diagnosis.ConclusionsThe proposed GENN framework offers a method for predicting 3D BMD distributions from a 2D-DXA scan, rivaling CT-based assessments. This approach reduces costs and radiation exposure, presenting a viable solution for personalized bone health evaluation and early osteoporosis diagnosis. |
| Author | Seo, Jiin Quagliato, Luca Lee, Taeyong Chung, Yoon-Sok |
| Author_xml | – sequence: 1 givenname: Jiin orcidid: 0009-0008-8647-6427 surname: Seo fullname: Seo, Jiin organization: Department of Mechanical and Biomedical Engineering, Ewha Womans University, Seoul, South Korea – sequence: 2 givenname: Luca orcidid: 0000-0002-5379-8306 surname: Quagliato fullname: Quagliato, Luca organization: Department of Mechanical and Biomedical Engineering, Ewha Womans University, Seoul, South Korea – sequence: 3 givenname: Yoon-Sok orcidid: 0000-0003-0179-4386 surname: Chung fullname: Chung, Yoon-Sok organization: Department of Endocrinology and Metabolism, Ajou University School of Medicine, Suwon, South Korea – sequence: 4 givenname: Taeyong orcidid: 0000-0002-0176-0525 surname: Lee fullname: Lee, Taeyong email: tlee@ewha.ac.kr organization: Department of Mechanical and Biomedical Engineering, Ewha Womans University, Seoul, South Korea |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/41127348$$D View this record in MEDLINE/PubMed https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART003246206$$DAccess content in National Research Foundation of Korea (NRF) |
| BookMark | eNqFklGL1DAQx4uceOd5X8AHyaMIXZM0absiwnKr58KBoCf4FtJkspfdNlmTVt1v4sc17a77IKgQmDD8_pPMzP9xdua8gyx7SvCMYFK-3Myk8XFGMeUzPJ9hTB9kF5RhnnNaFmenO-fn2VWMtsGMVZzTqnyUnTNCaFWw-iL7eROktuD6HNy9dAo0cjAE2abQf_dhi6TTCH70ATpA6yOMGu9jb90adV5DO16MD6i_B7QLoK3qrXfImylTLBPuAHXWwVhYg4u23yNtYx9sM0ysCb5DdJkvvyxQVNLFJ9lDI9sIV8d4mX1-9_bu-n1---Fmdb24zRWr6z6XynBeU6WhkLosmWkazlTqLh1OC9pUdQmMMGAyjY2Veo5TnhBFdV1Vcl5cZi8OdV0wYqus8NJOce3FNojFx7uVIElTp0kneHWAtZcbsQu2k2E_KaaED2shQ29VCwKrgjNQhVRQM1XruqZzzg0HXZjSmCLVen6otQv-6wCxF52NCtpWOvBDFAUtWZE6oHVCnx3RoelAnx7-vcYE0AOggo8xgDkhBIvRLmIjRruI0S4CzwWemnl9EEEa7zcLQUSVlpssYAOoPrVk_y1_84dcJSNYJdst7CFu_BBcWpwgIlKBxafRj6MdKceY0HL89Ku_F_jf678ACGXwKQ |
| Cites_doi | 10.1002/mp.14835 10.1016/j.afos.2018.11.082 10.1016/j.wneu.2023.07.146 10.3389/fbioe.2023.1111020 10.1109/TIP.2005.854501 10.1016/j.bone.2016.12.016 10.1007/s00198-004-1782-3 10.1016/j.afos.2019.06.003 10.1080/10255842.2012.670855 10.3340/jkns.2013.54.5.384 10.1016/j.ijmecsci.2023.108898 10.1109/83.887976 10.2147/CIA.S150067 10.1016/j.jocd.2022.01.004 10.1007/s10994-016-5585-5 10.1016/j.gsf.2020.03.007 10.5312/wjo.v5.i4.402 10.1016/j.heliyon.2023.e19253 10.1016/j.bone.2017.05.020 10.1118/1.4944501 10.1109/TIP.2003.819861 10.1097/BOT.0000000000001078 10.2106/JBJS.J.00160 10.1016/j.afos.2020.05.004 10.1007/s00198-020-05319-x 10.3928/01477447-20150701-56 10.1016/bs.adcom.2020.11.005 10.1007/s00256-021-03801-z 10.1111/joim.12586 10.1109/MM.2010.41 10.1002/mp.13627 10.1016/j.afos.2021.05.004 10.1109/TMI.2016.2593346 10.1007/s40846-018-0394-x 10.1016/j.matdes.2023.111625 |
| ContentType | Journal Article |
| Copyright | 2025 The Korean Society of Osteoporosis The Korean Society of Osteoporosis 2025 The Korean Society of Osteoporosis. Publishing services by Elsevier B.V. |
| Copyright_xml | – notice: 2025 The Korean Society of Osteoporosis – notice: The Korean Society of Osteoporosis – notice: 2025 The Korean Society of Osteoporosis. Publishing services by Elsevier B.V. |
| DBID | 6I. AAFTH AAYXX CITATION NPM 7X8 DOA ACYCR |
| DOI | 10.1016/j.afos.2025.09.002 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef PubMed MEDLINE - Academic DOAJ Directory of Open Access Journals Korean Citation Index |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 2405-5263 |
| EndPage | 106 |
| ExternalDocumentID | oai_kci_go_kr_ARTI_10758202 oai_doaj_org_article_0c354ec3ace84c8d882955f5ed3f6ff3 41127348 10_1016_j_afos_2025_09_002 S2405525525001268 1_s2_0_S2405525525001268 |
| Genre | Journal Article |
| GroupedDBID | ALMA_UNASSIGNED_HOLDINGS M~E 6I. AAFTH AAYXX CITATION .1- .FO 0R~ 457 5VS AAEDW AALRI AAXUO AAYWO ABMAC ACGFS ACVFH ADBBV ADCNI ADEZE ADVLN AEUPX AEXQZ AFPUW AFRHN AFTJW AGHFR AIGII AITUG AJUYK AKBMS AKRWK AKYEP AMRAJ AOIJS BCNDV EBS EJD FDB GROUPED_DOAJ HYE IPNFZ KQ8 NPM O9- OK1 RIG ROL RPM SSZ Z5R 7X8 ACYCR |
| ID | FETCH-LOGICAL-c488t-acf5582cde3ad664fbb54c1271275232b786e414e4a10146d9075211c2d877a93 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001589019500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2405-5255 2405-5263 |
| IngestDate | Wed Oct 01 06:59:02 EDT 2025 Tue Oct 07 09:29:18 EDT 2025 Sat Oct 25 07:05:05 EDT 2025 Sun Oct 26 04:17:34 EDT 2025 Thu Nov 13 04:22:13 EST 2025 Sat Nov 01 17:05:16 EDT 2025 Sat Oct 25 09:08:13 EDT 2025 Sat Nov 08 08:05:07 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Keywords | 2D-3D mapping Bone mineral density (BMD) prediction Extreme gradient boosting (XGB) Gradient-enhanced neural network (GENN) Dual-energy X-Ray absorptiometry (DXA) |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. 2025 The Korean Society of Osteoporosis. Publishing services by Elsevier B.V. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c488t-acf5582cde3ad664fbb54c1271275232b786e414e4a10146d9075211c2d877a93 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0009-0008-8647-6427 0000-0002-0176-0525 0000-0002-5379-8306 0000-0003-0179-4386 |
| OpenAccessLink | https://doaj.org/article/0c354ec3ace84c8d882955f5ed3f6ff3 |
| PMID | 41127348 |
| PQID | 3264323228 |
| PQPubID | 23479 |
| PageCount | 9 |
| ParticipantIDs | nrf_kci_oai_kci_go_kr_ARTI_10758202 doaj_primary_oai_doaj_org_article_0c354ec3ace84c8d882955f5ed3f6ff3 proquest_miscellaneous_3264323228 pubmed_primary_41127348 crossref_primary_10_1016_j_afos_2025_09_002 elsevier_sciencedirect_doi_10_1016_j_afos_2025_09_002 elsevier_clinicalkeyesjournals_1_s2_0_S2405525525001268 elsevier_clinicalkey_doi_10_1016_j_afos_2025_09_002 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-09-01 |
| PublicationDateYYYYMMDD | 2025-09-01 |
| PublicationDate_xml | – month: 09 year: 2025 text: 2025-09-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Netherlands |
| PublicationPlace_xml | – name: Netherlands |
| PublicationTitle | Osteoporosis and Sarcopenia |
| PublicationTitleAlternate | Osteoporos Sarcopenia |
| PublicationYear | 2025 |
| Publisher | Elsevier B.V Elsevier 대한골다공증학회 |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier – name: 대한골다공증학회 |
| References | Ruiz-Adame, Correa (bib7) 2020; 31 Dimai (bib11) 2017; 104 Inci, Isgenc, Marculescu (bib21) 2023 Lee, Lim, Galdos, Lee, Quagliato (bib26) 2024; 265 Tang, Jing, Jiang, Yang, Huang, Wu (bib28) 2023; 9 Schreiber, Anderson, Rosas, Buchholz, Au (bib39) 2011; 93 Lee, Chung, Oh, Park (bib42) 2013; 54 Glüer (bib12) 2017; 104 Lee, Park, Kim, Lee, Quagliato (bib25) 2023; 226 Humbert, Martelli, Fonolla, Steghöfer, Di Gregorio, Malouf (bib19) 2016; 36 Hong, Han (bib4) 2019; 5 Ho, Wong (bib6) 2020; 6 Humbert, Hazrati Marangalou, del Río Barquero, van Lenthe, van Rietbergen (bib17) 2016; 43 Almeida, Astudillo, Vandermeulen (bib18) 2021; 48 Kurkure, Sivaraman, Vu (bib23) 2017 Jun Nickolls, Dally (bib24) 2010; 30 Cortez, Lai, Tabu (bib8) 2021; 7 Zhang, Wu, Zhong, Li, Wang (bib34) 2021; 12 Ibrahim, Pal, Pesant (bib37) 2017; 106 Amphansap, Sujarekul (bib10) 2018; 4 Park, Kim (bib20) 2021; 122 Thévenaz, Unser (bib30) 2000; 9 Cano (bib22) 2018; vol. 8 Whitmarsh, Fritscher, Humbert, Del Rio Barquero, Roth, Kammerlander (bib15) 2011 Wu, Kim, Li (bib27) 2019; 46 Alexiou, Roushias, Varitimidis, Malizos (bib1) 2018 Borchardt, Nickel, Andersen (bib14) 2022; 25 Oliveira, Tavares (bib29) 2014; 17 Luo (bib13) 2019; 39 Pu, Zhang, Zhu, Zhong, Shen, Zhang (bib40) 2023; 180 Lane, Nahm, Vallier (bib3) 2015; 38 Rathore, Dadich, Jha, Pradhan (bib35) 2018; 6 Kolta, Le Bras, Mitton, Bousson, de Guise, Fechtenbaum (bib16) 2005; 16 Zokai, Wolberg (bib31) 2005; 14 Dudle, Gugler, Pretterklieber, Ferrari, Lippuner, Zysset (bib38) 2023; 11 Katsoulis, Benetou, Karapetyan (bib2) 2017; 281 Wang, Bovik, Sheikh, Simoncelli (bib32) 2004; 13 Chen, Guestrin (bib33) 2016 Aug Carpintero, Caeiro, Carpintero, Morales, Silva, Mesa (bib9) 2014; 5 Myers, Laboe, Johnson, Fredericks, Crichlow, Maar (bib5) 2018; 32 Dechter (bib36) 2022 Amin, Zakaria, Yahya (bib41) 2021; 50 Amphansap (10.1016/j.afos.2025.09.002_bib10) 2018; 4 Lee (10.1016/j.afos.2025.09.002_bib26) 2024; 265 Kolta (10.1016/j.afos.2025.09.002_bib16) 2005; 16 Rathore (10.1016/j.afos.2025.09.002_bib35) 2018; 6 Dudle (10.1016/j.afos.2025.09.002_bib38) 2023; 11 Amin (10.1016/j.afos.2025.09.002_bib41) 2021; 50 Zokai (10.1016/j.afos.2025.09.002_bib31) 2005; 14 Lane (10.1016/j.afos.2025.09.002_bib3) 2015; 38 Wang (10.1016/j.afos.2025.09.002_bib32) 2004; 13 Wu (10.1016/j.afos.2025.09.002_bib27) 2019; 46 Pu (10.1016/j.afos.2025.09.002_bib40) 2023; 180 Lee (10.1016/j.afos.2025.09.002_bib42) 2013; 54 Humbert (10.1016/j.afos.2025.09.002_bib19) 2016; 36 Oliveira (10.1016/j.afos.2025.09.002_bib29) 2014; 17 Carpintero (10.1016/j.afos.2025.09.002_bib9) 2014; 5 Cano (10.1016/j.afos.2025.09.002_bib22) 2018; vol. 8 Dechter (10.1016/j.afos.2025.09.002_bib36) 2022 Ruiz-Adame (10.1016/j.afos.2025.09.002_bib7) 2020; 31 Chen (10.1016/j.afos.2025.09.002_bib33) 2016 Glüer (10.1016/j.afos.2025.09.002_bib12) 2017; 104 Borchardt (10.1016/j.afos.2025.09.002_bib14) 2022; 25 Inci (10.1016/j.afos.2025.09.002_bib21) 2023 Ho (10.1016/j.afos.2025.09.002_bib6) 2020; 6 Luo (10.1016/j.afos.2025.09.002_bib13) 2019; 39 Zhang (10.1016/j.afos.2025.09.002_bib34) 2021; 12 Alexiou (10.1016/j.afos.2025.09.002_bib1) 2018 Whitmarsh (10.1016/j.afos.2025.09.002_bib15) 2011 Hong (10.1016/j.afos.2025.09.002_bib4) 2019; 5 Tang (10.1016/j.afos.2025.09.002_bib28) 2023; 9 Ibrahim (10.1016/j.afos.2025.09.002_bib37) 2017; 106 Myers (10.1016/j.afos.2025.09.002_bib5) 2018; 32 Schreiber (10.1016/j.afos.2025.09.002_bib39) 2011; 93 Cortez (10.1016/j.afos.2025.09.002_bib8) 2021; 7 Park (10.1016/j.afos.2025.09.002_bib20) 2021; 122 Dimai (10.1016/j.afos.2025.09.002_bib11) 2017; 104 Almeida (10.1016/j.afos.2025.09.002_bib18) 2021; 48 Lee (10.1016/j.afos.2025.09.002_bib25) 2023; 226 Humbert (10.1016/j.afos.2025.09.002_bib17) 2016; 43 Thévenaz (10.1016/j.afos.2025.09.002_bib30) 2000; 9 Katsoulis (10.1016/j.afos.2025.09.002_bib2) 2017; 281 Kurkure (10.1016/j.afos.2025.09.002_bib23) 2017 Nickolls (10.1016/j.afos.2025.09.002_bib24) 2010; 30 |
| References_xml | – volume: 281 start-page: 300 year: 2017 end-page: 310 ident: bib2 article-title: Excess mortality after hip fracture in elderly persons from Europe and the USA: the CHANCES project publication-title: J Intern Med – volume: 5 start-page: 38 year: 2019 end-page: 43 ident: bib4 article-title: The incidence of hip fracture and mortality rate after hip fracture in Korea: a nationwide population-based cohort study publication-title: Osteoporos Sarcopenia – volume: 36 start-page: 27 year: 2016 end-page: 39 ident: bib19 article-title: 3D-DXA: assessing the femoral shape, the trabecular macrostructure and the cortex in 3D from DXA images publication-title: IEEE Trans Med Imaging – volume: 50 start-page: 2525 year: 2021 end-page: 2535 ident: bib41 article-title: Correlation between Hounsfield unit derived from head, thorax, abdomen, spine and pelvis CT and T-scores from DXA publication-title: Skelet Radiol – volume: 6 start-page: 71 year: 2020 end-page: 74 ident: bib6 article-title: Second hip fracture in Hong Kong–Incidence, demographics, and mortality publication-title: Osteoporos Sarcopenia – volume: 48 start-page: 2448 year: 2021 end-page: 2457 ident: bib18 article-title: Three-dimensional image volumes from two-dimensional digitally reconstructed radiographs: a deep learning approach in lower limb CT scans publication-title: Med Phys – volume: 6 start-page: 1 year: 2018 end-page: 8 ident: bib35 article-title: Effect of learning rate on neural network and convolutional neural network publication-title: Int J Eng Res Technol – start-page: 225 year: 2023 end-page: 252 ident: bib21 article-title: Efficient deep learning using non-volatile memory technology in GPU architectures publication-title: Embedded machine Learning for Cyber-Physical, IoT, and Edge Computing: Hardware Architectures – volume: 32 start-page: 111 year: 2018 end-page: 115 ident: bib5 article-title: Patient mortality in geriatric distal femur fractures publication-title: J Orthop Trauma – start-page: 393 year: 2011 end-page: 400 ident: bib15 article-title: A statistical model of shape and bone mineral density distribution of the proximal femur for fracture risk assessment publication-title: Medical image computing and Computer-Assisted intervention – MICCAI 2011 – volume: vol. 8 year: 2018 ident: bib22 publication-title: A survey on graphic processing unit computing for large‐scale data mining – start-page: 785 year: 2016 Aug end-page: 794 ident: bib33 article-title: XGBoost: a scalable tree boosting system publication-title: Proceedings of the 22nd ACM SIGKDD International Conference on knowledge Discovery and Data Mining – volume: 180 start-page: e56 year: 2023 end-page: e68 ident: bib40 article-title: Hounsfield unit for evaluating bone mineral density and strength: variations in measurement methods publication-title: World Neurosurg – volume: 39 start-page: 287 year: 2019 end-page: 293 ident: bib13 article-title: Empirical functions for conversion of femur areal and volumetric bone mineral density publication-title: J Med Biol Eng – volume: 9 year: 2023 ident: bib28 article-title: The effect of image resolution on convolutional neural networks in breast ultrasound publication-title: Heliyon – volume: 17 start-page: 73 year: 2014 end-page: 93 ident: bib29 article-title: Medical image registration: a review publication-title: Comput Methods Biomech Biomed Engin – volume: 93 start-page: 1057 year: 2011 end-page: 1063 ident: bib39 article-title: Hounsfield units for assessing bone mineral density and strength: a tool for osteoporosis management publication-title: JBJS – volume: 31 start-page: 1205 year: 2020 end-page: 1216 ident: bib7 article-title: A systematic review of the indirect and social costs studies in fragility fractures publication-title: Osteoporos Int – start-page: 591 year: 2017 Jun end-page: 604 ident: bib23 article-title: Machine learning using virtualized GPUs in cloud environments publication-title: International Conference on High Performance Computing – volume: 106 start-page: 1 year: 2017 end-page: 54 ident: bib37 article-title: Improving probabilistic inference in graphical models with determinism and cycles publication-title: Mach Learn – volume: 104 start-page: 7 year: 2017 end-page: 12 ident: bib12 article-title: 30 years of DXA technology innovations publication-title: Bone – volume: 265 year: 2024 ident: bib26 article-title: Gaussian process regression-driven deep drawing blank design method publication-title: Int J Mech Sci – volume: 11 year: 2023 ident: bib38 article-title: 2D-3D reconstruction of the proximal femur from DXA scans: Evaluation of the 3D-Shaper software publication-title: Front Bioeng Biotechnol – volume: 4 start-page: 140 year: 2018 end-page: 144 ident: bib10 article-title: Quality of life and factors that affect osteoporotic hip fracture patients in Thailand publication-title: Osteoporos Sarcopenia – volume: 104 start-page: 39 year: 2017 end-page: 43 ident: bib11 article-title: Use of dual-energy X-ray absorptiometry (DXA) for diagnosis and fracture risk assessment; WHO-criteria, T- and Z-score, and reference databases publication-title: Bone – volume: 43 start-page: 1945 year: 2016 end-page: 1954 ident: bib17 article-title: Cortical thickness and density estimation from clinical CT using a prior thickness‐density relationship publication-title: Med Phys – volume: 54 start-page: 384 year: 2013 end-page: 389 ident: bib42 article-title: Correlation between bone mineral density measured by dual-energy X-ray absorptiometry and Hounsfield units measured by diagnostic CT in lumbar spine publication-title: J Korean Neurosurg Soc – volume: 5 start-page: 402 year: 2014 end-page: 411 ident: bib9 article-title: Complications of hip fractures: a review publication-title: World J Orthop – volume: 122 start-page: 51 year: 2021 end-page: 95 ident: bib20 article-title: Hardware accelerator systems for artificial intelligence and machine learning publication-title: Adv Comput – volume: 7 start-page: 63 year: 2021 end-page: 68 ident: bib8 article-title: Economic burden and the effects of early versus delayed hospitalization on the treatment cost of patients with acute fragility hip fractures under the UPM-PGH Orthogeriatric Multidisciplinary Fracture Management Model and Fracture Liaison Service publication-title: Osteoporos Sarcopenia – volume: 25 start-page: 319 year: 2022 end-page: 327 ident: bib14 article-title: Femur and tibia BMD measurement in elective total knee arthroplasty candidates publication-title: J Clin Densitom – volume: 13 start-page: 600 year: 2004 end-page: 612 ident: bib32 article-title: Image quality assessment: from error visibility to structural similarity publication-title: IEEE Trans Image Process – volume: 30 start-page: 56 year: 2010 end-page: 69 ident: bib24 article-title: The GPU computing era publication-title: IEEE Micro – volume: 46 start-page: 4763 year: 2019 end-page: 4776 ident: bib27 article-title: Computationally efficient deep neural network for computed tomography image reconstruction publication-title: Med Phys – volume: 9 start-page: 2083 year: 2000 end-page: 2099 ident: bib30 article-title: Optimization of mutual information for multiresolution image registration publication-title: IEEE Trans Image Process – volume: 226 year: 2023 ident: bib25 article-title: Extreme gradient boosting-inspired process optimization algorithm for manufacturing engineering applications publication-title: Mater Des – volume: 14 start-page: 1422 year: 2005 end-page: 1434 ident: bib31 article-title: Image registration using log-polar mappings for recovery of large-scale similarity and projective transformations publication-title: IEEE Trans Image Process – year: 2022 ident: bib36 article-title: Reasoning with probabilistic and deterministic graphical models: Exact algorithms – volume: 38 start-page: e588 year: 2015 end-page: e592 ident: bib3 article-title: Morbidity and mortality of bilateral femur fractures publication-title: Orthopedics – start-page: 143 year: 2018 end-page: 150 ident: bib1 article-title: Quality of life and psychological consequences in elderly patients after a hip fracture: a review publication-title: Clin Interv Aging – volume: 12 start-page: 469 year: 2021 end-page: 477 ident: bib34 article-title: Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization publication-title: Geosci Front – volume: 16 start-page: 969 year: 2005 end-page: 976 ident: bib16 article-title: Three-dimensional X-ray absorptiometry (3D-XA): a method for reconstruction of human bones using a dual X-ray absorptiometry device publication-title: Osteoporos Int – volume: 48 start-page: 2448 year: 2021 ident: 10.1016/j.afos.2025.09.002_bib18 article-title: Three-dimensional image volumes from two-dimensional digitally reconstructed radiographs: a deep learning approach in lower limb CT scans publication-title: Med Phys doi: 10.1002/mp.14835 – volume: 4 start-page: 140 year: 2018 ident: 10.1016/j.afos.2025.09.002_bib10 article-title: Quality of life and factors that affect osteoporotic hip fracture patients in Thailand publication-title: Osteoporos Sarcopenia doi: 10.1016/j.afos.2018.11.082 – volume: 180 start-page: e56 year: 2023 ident: 10.1016/j.afos.2025.09.002_bib40 article-title: Hounsfield unit for evaluating bone mineral density and strength: variations in measurement methods publication-title: World Neurosurg doi: 10.1016/j.wneu.2023.07.146 – volume: 11 year: 2023 ident: 10.1016/j.afos.2025.09.002_bib38 article-title: 2D-3D reconstruction of the proximal femur from DXA scans: Evaluation of the 3D-Shaper software publication-title: Front Bioeng Biotechnol doi: 10.3389/fbioe.2023.1111020 – start-page: 393 year: 2011 ident: 10.1016/j.afos.2025.09.002_bib15 article-title: A statistical model of shape and bone mineral density distribution of the proximal femur for fracture risk assessment – volume: 14 start-page: 1422 year: 2005 ident: 10.1016/j.afos.2025.09.002_bib31 article-title: Image registration using log-polar mappings for recovery of large-scale similarity and projective transformations publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2005.854501 – volume: 6 start-page: 1 year: 2018 ident: 10.1016/j.afos.2025.09.002_bib35 article-title: Effect of learning rate on neural network and convolutional neural network publication-title: Int J Eng Res Technol – volume: 104 start-page: 39 year: 2017 ident: 10.1016/j.afos.2025.09.002_bib11 article-title: Use of dual-energy X-ray absorptiometry (DXA) for diagnosis and fracture risk assessment; WHO-criteria, T- and Z-score, and reference databases publication-title: Bone doi: 10.1016/j.bone.2016.12.016 – volume: 16 start-page: 969 year: 2005 ident: 10.1016/j.afos.2025.09.002_bib16 article-title: Three-dimensional X-ray absorptiometry (3D-XA): a method for reconstruction of human bones using a dual X-ray absorptiometry device publication-title: Osteoporos Int doi: 10.1007/s00198-004-1782-3 – volume: 5 start-page: 38 year: 2019 ident: 10.1016/j.afos.2025.09.002_bib4 article-title: The incidence of hip fracture and mortality rate after hip fracture in Korea: a nationwide population-based cohort study publication-title: Osteoporos Sarcopenia doi: 10.1016/j.afos.2019.06.003 – volume: 17 start-page: 73 year: 2014 ident: 10.1016/j.afos.2025.09.002_bib29 article-title: Medical image registration: a review publication-title: Comput Methods Biomech Biomed Engin doi: 10.1080/10255842.2012.670855 – volume: 54 start-page: 384 year: 2013 ident: 10.1016/j.afos.2025.09.002_bib42 article-title: Correlation between bone mineral density measured by dual-energy X-ray absorptiometry and Hounsfield units measured by diagnostic CT in lumbar spine publication-title: J Korean Neurosurg Soc doi: 10.3340/jkns.2013.54.5.384 – volume: vol. 8 year: 2018 ident: 10.1016/j.afos.2025.09.002_bib22 – volume: 265 year: 2024 ident: 10.1016/j.afos.2025.09.002_bib26 article-title: Gaussian process regression-driven deep drawing blank design method publication-title: Int J Mech Sci doi: 10.1016/j.ijmecsci.2023.108898 – volume: 9 start-page: 2083 year: 2000 ident: 10.1016/j.afos.2025.09.002_bib30 article-title: Optimization of mutual information for multiresolution image registration publication-title: IEEE Trans Image Process doi: 10.1109/83.887976 – start-page: 143 year: 2018 ident: 10.1016/j.afos.2025.09.002_bib1 article-title: Quality of life and psychological consequences in elderly patients after a hip fracture: a review publication-title: Clin Interv Aging doi: 10.2147/CIA.S150067 – volume: 25 start-page: 319 year: 2022 ident: 10.1016/j.afos.2025.09.002_bib14 article-title: Femur and tibia BMD measurement in elective total knee arthroplasty candidates publication-title: J Clin Densitom doi: 10.1016/j.jocd.2022.01.004 – volume: 106 start-page: 1 year: 2017 ident: 10.1016/j.afos.2025.09.002_bib37 article-title: Improving probabilistic inference in graphical models with determinism and cycles publication-title: Mach Learn doi: 10.1007/s10994-016-5585-5 – volume: 12 start-page: 469 year: 2021 ident: 10.1016/j.afos.2025.09.002_bib34 article-title: Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization publication-title: Geosci Front doi: 10.1016/j.gsf.2020.03.007 – volume: 5 start-page: 402 year: 2014 ident: 10.1016/j.afos.2025.09.002_bib9 article-title: Complications of hip fractures: a review publication-title: World J Orthop doi: 10.5312/wjo.v5.i4.402 – volume: 9 year: 2023 ident: 10.1016/j.afos.2025.09.002_bib28 article-title: The effect of image resolution on convolutional neural networks in breast ultrasound publication-title: Heliyon doi: 10.1016/j.heliyon.2023.e19253 – volume: 104 start-page: 7 year: 2017 ident: 10.1016/j.afos.2025.09.002_bib12 article-title: 30 years of DXA technology innovations publication-title: Bone doi: 10.1016/j.bone.2017.05.020 – volume: 43 start-page: 1945 year: 2016 ident: 10.1016/j.afos.2025.09.002_bib17 article-title: Cortical thickness and density estimation from clinical CT using a prior thickness‐density relationship publication-title: Med Phys doi: 10.1118/1.4944501 – volume: 13 start-page: 600 year: 2004 ident: 10.1016/j.afos.2025.09.002_bib32 article-title: Image quality assessment: from error visibility to structural similarity publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2003.819861 – year: 2022 ident: 10.1016/j.afos.2025.09.002_bib36 – volume: 32 start-page: 111 year: 2018 ident: 10.1016/j.afos.2025.09.002_bib5 article-title: Patient mortality in geriatric distal femur fractures publication-title: J Orthop Trauma doi: 10.1097/BOT.0000000000001078 – volume: 93 start-page: 1057 year: 2011 ident: 10.1016/j.afos.2025.09.002_bib39 article-title: Hounsfield units for assessing bone mineral density and strength: a tool for osteoporosis management publication-title: JBJS doi: 10.2106/JBJS.J.00160 – start-page: 225 year: 2023 ident: 10.1016/j.afos.2025.09.002_bib21 article-title: Efficient deep learning using non-volatile memory technology in GPU architectures – volume: 6 start-page: 71 year: 2020 ident: 10.1016/j.afos.2025.09.002_bib6 article-title: Second hip fracture in Hong Kong–Incidence, demographics, and mortality publication-title: Osteoporos Sarcopenia doi: 10.1016/j.afos.2020.05.004 – volume: 31 start-page: 1205 year: 2020 ident: 10.1016/j.afos.2025.09.002_bib7 article-title: A systematic review of the indirect and social costs studies in fragility fractures publication-title: Osteoporos Int doi: 10.1007/s00198-020-05319-x – volume: 38 start-page: e588 year: 2015 ident: 10.1016/j.afos.2025.09.002_bib3 article-title: Morbidity and mortality of bilateral femur fractures publication-title: Orthopedics doi: 10.3928/01477447-20150701-56 – volume: 122 start-page: 51 year: 2021 ident: 10.1016/j.afos.2025.09.002_bib20 article-title: Hardware accelerator systems for artificial intelligence and machine learning publication-title: Adv Comput doi: 10.1016/bs.adcom.2020.11.005 – start-page: 591 year: 2017 ident: 10.1016/j.afos.2025.09.002_bib23 article-title: Machine learning using virtualized GPUs in cloud environments – volume: 50 start-page: 2525 year: 2021 ident: 10.1016/j.afos.2025.09.002_bib41 article-title: Correlation between Hounsfield unit derived from head, thorax, abdomen, spine and pelvis CT and T-scores from DXA publication-title: Skelet Radiol doi: 10.1007/s00256-021-03801-z – volume: 281 start-page: 300 year: 2017 ident: 10.1016/j.afos.2025.09.002_bib2 article-title: Excess mortality after hip fracture in elderly persons from Europe and the USA: the CHANCES project publication-title: J Intern Med doi: 10.1111/joim.12586 – volume: 30 start-page: 56 year: 2010 ident: 10.1016/j.afos.2025.09.002_bib24 article-title: The GPU computing era publication-title: IEEE Micro doi: 10.1109/MM.2010.41 – volume: 46 start-page: 4763 year: 2019 ident: 10.1016/j.afos.2025.09.002_bib27 article-title: Computationally efficient deep neural network for computed tomography image reconstruction publication-title: Med Phys doi: 10.1002/mp.13627 – volume: 7 start-page: 63 year: 2021 ident: 10.1016/j.afos.2025.09.002_bib8 article-title: Economic burden and the effects of early versus delayed hospitalization on the treatment cost of patients with acute fragility hip fractures under the UPM-PGH Orthogeriatric Multidisciplinary Fracture Management Model and Fracture Liaison Service publication-title: Osteoporos Sarcopenia doi: 10.1016/j.afos.2021.05.004 – volume: 36 start-page: 27 year: 2016 ident: 10.1016/j.afos.2025.09.002_bib19 article-title: 3D-DXA: assessing the femoral shape, the trabecular macrostructure and the cortex in 3D from DXA images publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2016.2593346 – volume: 39 start-page: 287 year: 2019 ident: 10.1016/j.afos.2025.09.002_bib13 article-title: Empirical functions for conversion of femur areal and volumetric bone mineral density publication-title: J Med Biol Eng doi: 10.1007/s40846-018-0394-x – volume: 226 year: 2023 ident: 10.1016/j.afos.2025.09.002_bib25 article-title: Extreme gradient boosting-inspired process optimization algorithm for manufacturing engineering applications publication-title: Mater Des doi: 10.1016/j.matdes.2023.111625 – start-page: 785 year: 2016 ident: 10.1016/j.afos.2025.09.002_bib33 article-title: XGBoost: a scalable tree boosting system |
| SSID | ssib044755276 ssj0001562622 |
| Score | 2.301933 |
| Snippet | This study aims to predict the volumetric bone mineral density (BMD) distribution from a dual-energy X-ray absorptiometry (DXA) scan. By employing machine... AbstractObjectivesThis study aims to predict the volumetric bone mineral density (BMD) distribution from a dual-energy X-ray absorptiometry (DXA) scan. By... Objectives: This study aims to predict the volumetric bone mineral density (BMD) distribution from a dual-energy X-ray absorptiometry (DXA) scan. By employing... |
| SourceID | nrf doaj proquest pubmed crossref elsevier |
| SourceType | Open Website Aggregation Database Index Database Publisher |
| StartPage | 98 |
| SubjectTerms | 2D-3D mapping Bone mineral density (BMD) prediction Dual-energy X-Ray absorptiometry (DXA) Endocrinology and Metabolism Extreme gradient boosting (XGB) Gradient-enhanced neural network (GENN) 정형외과학 |
| Title | Gradient-enhanced neural network and extreme gradient boosting modeling for the prediction of the 3D bone mineral density distribution from 2D-DXA scans |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S2405525525001268 https://www.clinicalkey.es/playcontent/1-s2.0-S2405525525001268 https://dx.doi.org/10.1016/j.afos.2025.09.002 https://www.ncbi.nlm.nih.gov/pubmed/41127348 https://www.proquest.com/docview/3264323228 https://doaj.org/article/0c354ec3ace84c8d882955f5ed3f6ff3 https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART003246206 |
| Volume | 11 |
| WOSCitedRecordID | wos001589019500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| ispartofPNX | Osteoporosis and Sarcopenia, 2025, 11(3), , pp.98-106 |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2405-5263 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001562622 issn: 2405-5255 databaseCode: DOA dateStart: 20150101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2405-5263 dateEnd: 99991231 omitProxy: false ssIdentifier: ssib044755276 issn: 2405-5255 databaseCode: M~E dateStart: 20160101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELZoxYELAvFaHpUR3FBE4kfsHAvbAgcqJEDam-X4UbYV2SpJK_XC7-DnMmMnqyIBvXBJomicOJ6x_U08_oaQl3XA3ZQsFL6M4KAI7gqrrS2Y1coCgA5KxZRsQh0d6dWq-XQl1RfGhGV64Nxwr0vHpQiOWxe0cNoDImykjDJ4HusYE89nqZorzhRYErLYSZYzywEiAW9LymnHTA7usnGDXN1MJpLT6Z_KPCsl8v7fJqedro9_h6BpKjq8Q25PGJLu57rfJTdCd4_8fNen6K2xCN23tKxPkasS5Loc6U1t5ykMxfhDkB5PwhRA9oCRzzSlxMELQLEUUCE963ENB_VGNzHd4UsQ7wL9vk5U1dRj8Pt4ST2S7055syjuV6FsWSxX-3QAvQ33ydfDgy9v3xdT2oXCQW8eC-uilJo5H7j1dS1i20rhKqaQCx4AWKt0HUQlgrCY6Lf24F8DCKgc81op2_AHZLeD2jwitBVSgUvGgiitsEG1rS9txSxDmj-Algvyam52c5bZNcwcdnZiUEkGlWTKxoCSFuQNamYriczY6QbYi5nsxVxnLwvCZ72aefMpDJfwoPU_X63-VCoMU48fTGUGZkrzGe0NzQ2gJcz9tV4QuS05gZoMVq594wswOnPq1uk78Xy8Mae9AT_nAxQCP4-h1PPZKA2MC7jYY7uwOR8MwHLBQVsMavAwW-u24QSAbGQ1evw_GvQJuYXVznF3T8nu2J-HZ-SmuxjXQ79HdtRK76XOCcePPw5-ARR1PMs |
| 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=Gradient-enhanced+neural+network+and+extreme+gradient+boosting+modeling+for+the+prediction+of+the+3D+bone+mineral+density+distribution+from+2D-DXA+scans&rft.jtitle=Osteoporosis+and+Sarcopenia&rft.au=Seo%2C+Jiin&rft.au=Quagliato%2C+Luca&rft.au=Chung%2C+Yoon-Sok&rft.au=Lee%2C+Taeyong&rft.date=2025-09-01&rft.issn=2405-5255&rft.volume=11&rft.issue=3&rft.spage=98&rft.epage=106&rft_id=info:doi/10.1016%2Fj.afos.2025.09.002&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_afos_2025_09_002 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2405-5255&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2405-5255&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2405-5255&client=summon |