Average glandular dose prediction for breast model with patient-specific fibroglandular distribution in mammography and digital breast tomosynthesis: a machine-learning algorithms comparison.
Saved in:
| Title: | Average glandular dose prediction for breast model with patient-specific fibroglandular distribution in mammography and digital breast tomosynthesis: a machine-learning algorithms comparison. |
|---|---|
| Authors: | Alice, Barcella1 (AUTHOR), Massera, Rodrigo T2 (AUTHOR), Ivan, Veronese1 (AUTHOR), Cristina, Lenardi1 (AUTHOR), Antonio, Sarno1 (AUTHOR) antonio.sarno@unimi.it |
| Source: | Physics in Medicine & Biology. 2026, Vol. 71 Issue 7, p1-14. 14p. |
| Subjects: | Machine learning, Radiation doses, Tomosynthesis, Mammograms, Diagnostic imaging |
| Abstract: | Objective. To investigate machine learning (ML) methodologies for predicting glandular dose conversion coefficients for breast models with patient-specific fibroglandular distribution (Γpatient) in digital mammography (DM) and digital breast tomosynthesis (DBT). Approach. We investigated four ML algorithms for predicting Γpatient, namely generalized additive model (GAM), extreme gradient boosting (XGBoost), support vector regression (SVR) and automatic relevance determination regression (ARDR). These were trained with Γpatient data generated with a Monte Carlo software and by adopting a dataset of 126 digital breast phantoms with patient-specific fibroglandular distribution. The ML input features were the compressed breast thickness (CBT), the glandular fraction by volume and the total breast volume. DM was simulated at 28 kV (Anode/Filter: W/Rh) and at 36 kV (Anode/Filter: W/Al); DBT at 28 kV (Anode/Filter: W/Rh) and 50°scanning angle. Results. The four investigated algorithms predicted the Γpatient coefficients with an average difference from the ground truth between −2% (SVR) and +7% (XGBoost). The best model from the GAM fine tuning required the sole CBT as input feature. This algorithm presented the smallest model uncertainty, and the lowest cases of dose underestimate. Conclusions. The GAM algorithm predicted Γpatient with an average difference from the expected value of 4%, in line with the other investigated algorithms. This algorithm showed the best performance in terms of model uncertainty, with average total estimated uncertainty of 12%, including the model accuracy, for DM at 28 kV. No relevant differences were observed in the case of DBT; bias and uncertainty of the prediction reduced for higher tube voltages. [ABSTRACT FROM AUTHOR] |
| © 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 192724408 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Average glandular dose prediction for breast model with patient-specific fibroglandular distribution in mammography and digital breast tomosynthesis: a machine-learning algorithms comparison. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Alice%2C+Barcella%22">Alice, Barcella</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Massera%2C+Rodrigo+T%22">Massera, Rodrigo T</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ivan%2C+Veronese%22">Ivan, Veronese</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Cristina%2C+Lenardi%22">Cristina, Lenardi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Antonio%2C+Sarno%22">Antonio, Sarno</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> antonio.sarno@unimi.it</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Physics+in+Medicine+%26+Biology%22">Physics in Medicine & Biology</searchLink>. 2026, Vol. 71 Issue 7, p1-14. 14p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Radiation+doses%22">Radiation doses</searchLink><br /><searchLink fieldCode="DE" term="%22Tomosynthesis%22">Tomosynthesis</searchLink><br /><searchLink fieldCode="DE" term="%22Mammograms%22">Mammograms</searchLink><br /><searchLink fieldCode="DE" term="%22Diagnostic+imaging%22">Diagnostic imaging</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Objective. To investigate machine learning (ML) methodologies for predicting glandular dose conversion coefficients for breast models with patient-specific fibroglandular distribution (Γpatient) in digital mammography (DM) and digital breast tomosynthesis (DBT). Approach. We investigated four ML algorithms for predicting Γpatient, namely generalized additive model (GAM), extreme gradient boosting (XGBoost), support vector regression (SVR) and automatic relevance determination regression (ARDR). These were trained with Γpatient data generated with a Monte Carlo software and by adopting a dataset of 126 digital breast phantoms with patient-specific fibroglandular distribution. The ML input features were the compressed breast thickness (CBT), the glandular fraction by volume and the total breast volume. DM was simulated at 28 kV (Anode/Filter: W/Rh) and at 36 kV (Anode/Filter: W/Al); DBT at 28 kV (Anode/Filter: W/Rh) and 50°scanning angle. Results. The four investigated algorithms predicted the Γpatient coefficients with an average difference from the ground truth between −2% (SVR) and +7% (XGBoost). The best model from the GAM fine tuning required the sole CBT as input feature. This algorithm presented the smallest model uncertainty, and the lowest cases of dose underestimate. Conclusions. The GAM algorithm predicted Γpatient with an average difference from the expected value of 4%, in line with the other investigated algorithms. This algorithm showed the best performance in terms of model uncertainty, with average total estimated uncertainty of 12%, including the model accuracy, for DM at 28 kV. No relevant differences were observed in the case of DBT; bias and uncertainty of the prediction reduced for higher tube voltages. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>© 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=192724408 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1088/1361-6560/ae556c Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 14 StartPage: 1 Subjects: – SubjectFull: Machine learning Type: general – SubjectFull: Radiation doses Type: general – SubjectFull: Tomosynthesis Type: general – SubjectFull: Mammograms Type: general – SubjectFull: Diagnostic imaging Type: general Titles: – TitleFull: Average glandular dose prediction for breast model with patient-specific fibroglandular distribution in mammography and digital breast tomosynthesis: a machine-learning algorithms comparison. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Alice, Barcella – PersonEntity: Name: NameFull: Massera, Rodrigo T – PersonEntity: Name: NameFull: Ivan, Veronese – PersonEntity: Name: NameFull: Cristina, Lenardi – PersonEntity: Name: NameFull: Antonio, Sarno IsPartOfRelationships: – BibEntity: Dates: – D: 14 M: 04 Text: 2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 00319155 Numbering: – Type: volume Value: 71 – Type: issue Value: 7 Titles: – TitleFull: Physics in Medicine & Biology Type: main |
| ResultId | 1 |
