Construction of a Compound Model to Enhance the Accuracy of Hepatic Fat Fraction Estimation with Quantitative Ultrasound

<b>Background:</b> we evaluated regression models based on quantitative ultrasound (QUS) parameters and compared them with a vendor-provided method for calculating the ultrasound fat fraction (USFF) in metabolic dysfunction-associated steatotic liver disease (MASLD). <b>Methods:<...

Full description

Saved in:
Bibliographic Details
Main Authors: Zsély Boglárka, Zita Zsombor, Aladár D. Rónaszéki, Anna Egresi, Róbert Stollmayer, Marco Himsel, Viktor Bérczi, Ildikó Kalina, Klára Werling, Gabriella Győri, Pál Maurovich-Horvat, Anikó Folhoffer, Krisztina Hagymási, Pál Novák Kaposi
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/2/203
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832588720838017024
author Zsély Boglárka
Zita Zsombor
Aladár D. Rónaszéki
Anna Egresi
Róbert Stollmayer
Marco Himsel
Viktor Bérczi
Ildikó Kalina
Klára Werling
Gabriella Győri
Pál Maurovich-Horvat
Anikó Folhoffer
Krisztina Hagymási
Pál Novák Kaposi
author_facet Zsély Boglárka
Zita Zsombor
Aladár D. Rónaszéki
Anna Egresi
Róbert Stollmayer
Marco Himsel
Viktor Bérczi
Ildikó Kalina
Klára Werling
Gabriella Győri
Pál Maurovich-Horvat
Anikó Folhoffer
Krisztina Hagymási
Pál Novák Kaposi
author_sort Zsély Boglárka
collection DOAJ
description <b>Background:</b> we evaluated regression models based on quantitative ultrasound (QUS) parameters and compared them with a vendor-provided method for calculating the ultrasound fat fraction (USFF) in metabolic dysfunction-associated steatotic liver disease (MASLD). <b>Methods:</b> We measured the attenuation coefficient (AC) and the backscatter-distribution coefficient (BSC-D) and determined the USFF during a liver ultrasound and calculated the magnetic resonance imaging proton-density fat fraction (MRI-PDFF) and steatosis grade (S0–S4) in a combined retrospective–prospective cohort. We trained multiple models using single or various QUS parameters as independent variables to forecast MRI-PDFF. Linear and nonlinear models were trained during five-time repeated three-fold cross-validation in a retrospectively collected dataset of 60 MASLD cases. We calculated the models’ Pearson correlation (r) and the intraclass correlation coefficient (ICC) in a prospectively collected test set of 57 MASLD cases. <b>Results:</b> The linear multivariable model (r = 0.602, ICC = 0.529) and USFF (r = 0.576, ICC = 0.54) were more reliable in S0- and S1-grade steatosis than the nonlinear multivariable model (r = 0.492, ICC = 0.461). In S2 and S3 grades, the nonlinear multivariable (r = 0.377, ICC = 0.32) and AC-only (r = 0.375, ICC = 0.313) models’ approximated correlation and agreement surpassed that of the multivariable linear model (r = 0.394, ICC = 0.265). We searched a QUS parameter grid to find the optimal thresholds (AC ≥ 0.84 dB/cm/MHz, BSC-D ≥ 105), above which switching from a linear (r = 0.752, ICC = 0.715) to a nonlinear multivariable (r = 0.719, ICC = 0.641) model could improve the overall fit (r = 0.775, ICC = 0.718). <b>Conclusions:</b> The USFF and linear multivariable models are robust in diagnosing low-grade steatosis. Switching to a nonlinear model could enhance the fit to MRI-PDFF in advanced steatosis.
format Article
id doaj-art-baf3178be33340659308fb54fc4b925b
institution Kabale University
issn 2075-4418
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-baf3178be33340659308fb54fc4b925b2025-01-24T13:29:06ZengMDPI AGDiagnostics2075-44182025-01-0115220310.3390/diagnostics15020203Construction of a Compound Model to Enhance the Accuracy of Hepatic Fat Fraction Estimation with Quantitative UltrasoundZsély Boglárka0Zita Zsombor1Aladár D. Rónaszéki2Anna Egresi3Róbert Stollmayer4Marco Himsel5Viktor Bérczi6Ildikó Kalina7Klára Werling8Gabriella Győri9Pál Maurovich-Horvat10Anikó Folhoffer11Krisztina Hagymási12Pál Novák Kaposi13Department of Radiology, Medical Imaging Centre, Semmelweis University, 1082 Budapest, HungaryDepartment of Radiology, Medical Imaging Centre, Semmelweis University, 1082 Budapest, HungaryDepartment of Radiology, Medical Imaging Centre, Semmelweis University, 1082 Budapest, HungaryDepartment of Surgery, Transplantation, and Gastroenterology, Semmelweis University, 1082 Budapest, HungaryDepartment of Radiology, Medical Imaging Centre, Semmelweis University, 1082 Budapest, HungaryDepartment of Radiology, Medical Imaging Centre, Semmelweis University, 1082 Budapest, HungaryDepartment of Radiology, Medical Imaging Centre, Semmelweis University, 1082 Budapest, HungaryDepartment of Radiology, Medical Imaging Centre, Semmelweis University, 1082 Budapest, HungaryDepartment of Surgery, Transplantation, and Gastroenterology, Semmelweis University, 1082 Budapest, HungaryDepartment of Radiology, Medical Imaging Centre, Semmelweis University, 1082 Budapest, HungaryDepartment of Radiology, Medical Imaging Centre, Semmelweis University, 1082 Budapest, HungaryDepartment of Internal Medicine and Oncology, Semmelweis University, 1082 Budapest, HungaryDepartment of Surgery, Transplantation, and Gastroenterology, Semmelweis University, 1082 Budapest, HungaryDepartment of Radiology, Medical Imaging Centre, Semmelweis University, 1082 Budapest, Hungary<b>Background:</b> we evaluated regression models based on quantitative ultrasound (QUS) parameters and compared them with a vendor-provided method for calculating the ultrasound fat fraction (USFF) in metabolic dysfunction-associated steatotic liver disease (MASLD). <b>Methods:</b> We measured the attenuation coefficient (AC) and the backscatter-distribution coefficient (BSC-D) and determined the USFF during a liver ultrasound and calculated the magnetic resonance imaging proton-density fat fraction (MRI-PDFF) and steatosis grade (S0–S4) in a combined retrospective–prospective cohort. We trained multiple models using single or various QUS parameters as independent variables to forecast MRI-PDFF. Linear and nonlinear models were trained during five-time repeated three-fold cross-validation in a retrospectively collected dataset of 60 MASLD cases. We calculated the models’ Pearson correlation (r) and the intraclass correlation coefficient (ICC) in a prospectively collected test set of 57 MASLD cases. <b>Results:</b> The linear multivariable model (r = 0.602, ICC = 0.529) and USFF (r = 0.576, ICC = 0.54) were more reliable in S0- and S1-grade steatosis than the nonlinear multivariable model (r = 0.492, ICC = 0.461). In S2 and S3 grades, the nonlinear multivariable (r = 0.377, ICC = 0.32) and AC-only (r = 0.375, ICC = 0.313) models’ approximated correlation and agreement surpassed that of the multivariable linear model (r = 0.394, ICC = 0.265). We searched a QUS parameter grid to find the optimal thresholds (AC ≥ 0.84 dB/cm/MHz, BSC-D ≥ 105), above which switching from a linear (r = 0.752, ICC = 0.715) to a nonlinear multivariable (r = 0.719, ICC = 0.641) model could improve the overall fit (r = 0.775, ICC = 0.718). <b>Conclusions:</b> The USFF and linear multivariable models are robust in diagnosing low-grade steatosis. Switching to a nonlinear model could enhance the fit to MRI-PDFF in advanced steatosis.https://www.mdpi.com/2075-4418/15/2/203fatty livermetabolic dysfunction-associated steatotic liver diseaseultrasound fat fraction (USFF)magnetic resonance imaging proton-density fat fractionregression analysis
spellingShingle Zsély Boglárka
Zita Zsombor
Aladár D. Rónaszéki
Anna Egresi
Róbert Stollmayer
Marco Himsel
Viktor Bérczi
Ildikó Kalina
Klára Werling
Gabriella Győri
Pál Maurovich-Horvat
Anikó Folhoffer
Krisztina Hagymási
Pál Novák Kaposi
Construction of a Compound Model to Enhance the Accuracy of Hepatic Fat Fraction Estimation with Quantitative Ultrasound
Diagnostics
fatty liver
metabolic dysfunction-associated steatotic liver disease
ultrasound fat fraction (USFF)
magnetic resonance imaging proton-density fat fraction
regression analysis
title Construction of a Compound Model to Enhance the Accuracy of Hepatic Fat Fraction Estimation with Quantitative Ultrasound
title_full Construction of a Compound Model to Enhance the Accuracy of Hepatic Fat Fraction Estimation with Quantitative Ultrasound
title_fullStr Construction of a Compound Model to Enhance the Accuracy of Hepatic Fat Fraction Estimation with Quantitative Ultrasound
title_full_unstemmed Construction of a Compound Model to Enhance the Accuracy of Hepatic Fat Fraction Estimation with Quantitative Ultrasound
title_short Construction of a Compound Model to Enhance the Accuracy of Hepatic Fat Fraction Estimation with Quantitative Ultrasound
title_sort construction of a compound model to enhance the accuracy of hepatic fat fraction estimation with quantitative ultrasound
topic fatty liver
metabolic dysfunction-associated steatotic liver disease
ultrasound fat fraction (USFF)
magnetic resonance imaging proton-density fat fraction
regression analysis
url https://www.mdpi.com/2075-4418/15/2/203
work_keys_str_mv AT zselyboglarka constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT zitazsombor constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT aladardronaszeki constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT annaegresi constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT robertstollmayer constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT marcohimsel constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT viktorberczi constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT ildikokalina constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT klarawerling constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT gabriellagyori constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT palmaurovichhorvat constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT anikofolhoffer constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT krisztinahagymasi constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound
AT palnovakkaposi constructionofacompoundmodeltoenhancetheaccuracyofhepaticfatfractionestimationwithquantitativeultrasound