Comparison of Resampling Methods and Radiomic Machine Learning Classifiers for Predicting Bone Quality Using Dual-Energy X-Ray Absorptiometry.
| Title: | Comparison of Resampling Methods and Radiomic Machine Learning Classifiers for Predicting Bone Quality Using Dual-Energy X-Ray Absorptiometry. |
|---|---|
| Authors: | Gonzalez, Mailen1,2 (AUTHOR) jmassa@intia.exa.unicen.edu.ar, Fuertes García, José Manuel3 (AUTHOR) jmf@ujaen.es, Zanchetta, María Belén4 (AUTHOR), Abdala, Rubén4 (AUTHOR), Massa, José María1 (AUTHOR) |
| Source: | Diagnostics (2075-4418). Jan2025, Vol. 15 Issue 2, p175. 16p. |
| Subject Terms: | *DUAL-energy X-ray absorptiometry, *MACHINE learning, *FEATURE extraction, *CANCELLOUS bone, *SUPPORT vector machines |
| Abstract: | Background/Objectives: This study presents a novel approach, based on a combination of radiomic feature extraction, data resampling techniques, and machine learning algorithms, for the detection of degraded bone structures in Dual X-ray Absorptiometry (DXA) images. This comprehensive approach, which addresses the critical aspects of the problem, distinguishes this work from previous studies, improving the performance achieved by the most similar studies. The primary aim is to provide clinicians with an accessible tool for quality bone assessment, which is currently limited. Methods: A dataset of 1531 spine DXA images was automatically segmented and labelled based on Trabecular Bone Score (TBS) values. Radiomic features were extracted using Pyradiomics, and various resampling techniques were employed to address class imbalance. Three machine learning classifiers (Logistic Regression, Support Vector Machine (SVM), and XGBoost) were trained and evaluated using standard performance metrics. Results: The SVM classifier outperformed the other classifiers. The highest F-score of 97.5% was achieved using the Grey Level Dependence Matrix and Grey Level Run Length Matrix feature combination with SMOTEENN resampling, which proved to be the most effective resampling technique, while the undersampling method yielded the lowest performance. Conclusions: This research demonstrates the potential of radiomic texture features, resampling techniques, and machine learning methods for classifying DXA images into healthy or degraded bone structures, which potentially leads to improved clinical diagnosis and treatment. [ABSTRACT FROM AUTHOR] |
| Copyright of Diagnostics (2075-4418) is the property of MDPI and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Academic Search Complete |
| Full text is not displayed to guests. | Login for full access. |
| FullText | Links: – Type: pdflink Text: Availability: 1 CustomLinks: – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:a9h&genre=article&issn=20754418&ISBN=&volume=15&issue=2&date=20250115&spage=175&pages=175-190&title=Diagnostics (2075-4418)&atitle=Comparison%20of%20Resampling%20Methods%20and%20Radiomic%20Machine%20Learning%20Classifiers%20for%20Predicting%20Bone%20Quality%20Using%20Dual-Energy%20X-Ray%20Absorptiometry.&aulast=Gonzalez%2C%20Mailen&id=DOI:10.3390/diagnostics15020175 Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: a9h DbLabel: Academic Search Complete An: 182465510 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Comparison of Resampling Methods and Radiomic Machine Learning Classifiers for Predicting Bone Quality Using Dual-Energy X-Ray Absorptiometry. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Gonzalez%2C+Mailen%22">Gonzalez, Mailen</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> jmassa@intia.exa.unicen.edu.ar</i><br /><searchLink fieldCode="AR" term="%22Fuertes+García%2C+José+Manuel%22">Fuertes García, José Manuel</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> jmf@ujaen.es</i><br /><searchLink fieldCode="AR" term="%22Zanchetta%2C+María+Belén%22">Zanchetta, María Belén</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Abdala%2C+Rubén%22">Abdala, Rubén</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Massa%2C+José+María%22">Massa, José María</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Diagnostics+%282075-4418%29%22">Diagnostics (2075-4418)</searchLink>. Jan2025, Vol. 15 Issue 2, p175. 16p. – Name: Subject Label: Subject Terms Group: Su Data: *<searchLink fieldCode="DE" term="%22DUAL-energy+X-ray+absorptiometry%22">DUAL-energy X-ray absorptiometry</searchLink><br />*<searchLink fieldCode="DE" term="%22MACHINE+learning%22">MACHINE learning</searchLink><br />*<searchLink fieldCode="DE" term="%22FEATURE+extraction%22">FEATURE extraction</searchLink><br />*<searchLink fieldCode="DE" term="%22CANCELLOUS+bone%22">CANCELLOUS bone</searchLink><br />*<searchLink fieldCode="DE" term="%22SUPPORT+vector+machines%22">SUPPORT vector machines</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Background/Objectives: This study presents a novel approach, based on a combination of radiomic feature extraction, data resampling techniques, and machine learning algorithms, for the detection of degraded bone structures in Dual X-ray Absorptiometry (DXA) images. This comprehensive approach, which addresses the critical aspects of the problem, distinguishes this work from previous studies, improving the performance achieved by the most similar studies. The primary aim is to provide clinicians with an accessible tool for quality bone assessment, which is currently limited. Methods: A dataset of 1531 spine DXA images was automatically segmented and labelled based on Trabecular Bone Score (TBS) values. Radiomic features were extracted using Pyradiomics, and various resampling techniques were employed to address class imbalance. Three machine learning classifiers (Logistic Regression, Support Vector Machine (SVM), and XGBoost) were trained and evaluated using standard performance metrics. Results: The SVM classifier outperformed the other classifiers. The highest F-score of 97.5% was achieved using the Grey Level Dependence Matrix and Grey Level Run Length Matrix feature combination with SMOTEENN resampling, which proved to be the most effective resampling technique, while the undersampling method yielded the lowest performance. Conclusions: This research demonstrates the potential of radiomic texture features, resampling techniques, and machine learning methods for classifying DXA images into healthy or degraded bone structures, which potentially leads to improved clinical diagnosis and treatment. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Diagnostics (2075-4418) is the property of MDPI and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=a9h&AN=182465510 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/diagnostics15020175 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 16 StartPage: 175 Subjects: – SubjectFull: DUAL-energy X-ray absorptiometry Type: general – SubjectFull: MACHINE learning Type: general – SubjectFull: FEATURE extraction Type: general – SubjectFull: CANCELLOUS bone Type: general – SubjectFull: SUPPORT vector machines Type: general Titles: – TitleFull: Comparison of Resampling Methods and Radiomic Machine Learning Classifiers for Predicting Bone Quality Using Dual-Energy X-Ray Absorptiometry. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Gonzalez, Mailen – PersonEntity: Name: NameFull: Fuertes García, José Manuel – PersonEntity: Name: NameFull: Zanchetta, María Belén – PersonEntity: Name: NameFull: Abdala, Rubén – PersonEntity: Name: NameFull: Massa, José María IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 01 Text: Jan2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 20754418 Numbering: – Type: volume Value: 15 – Type: issue Value: 2 Titles: – TitleFull: Diagnostics (2075-4418) Type: main |
| ResultId | 1 |