Machine learning-based predictive analysis of energy efficiency factors necessary for the HIFU treatment of adenomyosis

PurposeThis study aimed to develop a joint model combining T2-weighted imaging (T2WI) suppressed fat radiomics, and clinical parameters to predict the energy efficiency factor (EEF) required for high-intensity focused ultrasound (HIFU) ablation in patients with adenomyosis.Materials and methodsThis...

Full description

Saved in:
Bibliographic Details
Main Authors: Ziyan Liu, Ziyi Liu, Yuan Wang, Xiyao Wan, Xiaohua Huang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Physiology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fphys.2025.1602866/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762364800368640
author Ziyan Liu
Ziyi Liu
Yuan Wang
Xiyao Wan
Xiaohua Huang
author_facet Ziyan Liu
Ziyi Liu
Yuan Wang
Xiyao Wan
Xiaohua Huang
author_sort Ziyan Liu
collection DOAJ
description PurposeThis study aimed to develop a joint model combining T2-weighted imaging (T2WI) suppressed fat radiomics, and clinical parameters to predict the energy efficiency factor (EEF) required for high-intensity focused ultrasound (HIFU) ablation in patients with adenomyosis.Materials and methodsThis retrospective study included 169 adenomyosis patients who underwent HIFU ablation between September 2021 and May 2024. EEF values were calculated based on T2WI fat suppression (T2WI-FS) sequences, and radiomics features were extracted. Predictive features were selected using minimum redundancy maximum relevance (MRMR) and least absolute shrinkage and selection operator (LASSO) methods, and two joint—based on decision tree and random forest algorithms—models were developed for EEF prediction.ResultsThe decision tree model achieved a mean absolute error (MAE) of 8.095 on the test set, while the random forest model exhibited an MAE of 8.231. The Wilcoxon rank-sum test for the test set revealed that the discrepancy in predictive performance between the two models was statistically significant (p < 0.05). The correlation coefficients were 0.768 and 0.777, and the R2 coefficients of the two models in the test set were 0.559 and 0.549, respectively.ConclusionThe joint model integrating T2WI radiomics and clinical data effectively predicted EEF values for HIFU ablation in adenomyosis. This approach provides a foundation for optimizing HIFU dosing strategies and enhancing treatment safety and efficacy.
format Article
id doaj-art-f2835c71ef8a4bcba2b0b6a00bd081fa
institution DOAJ
issn 1664-042X
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Physiology
spelling doaj-art-f2835c71ef8a4bcba2b0b6a00bd081fa2025-08-20T03:05:45ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2025-08-011610.3389/fphys.2025.16028661602866Machine learning-based predictive analysis of energy efficiency factors necessary for the HIFU treatment of adenomyosisZiyan LiuZiyi LiuYuan WangXiyao WanXiaohua HuangPurposeThis study aimed to develop a joint model combining T2-weighted imaging (T2WI) suppressed fat radiomics, and clinical parameters to predict the energy efficiency factor (EEF) required for high-intensity focused ultrasound (HIFU) ablation in patients with adenomyosis.Materials and methodsThis retrospective study included 169 adenomyosis patients who underwent HIFU ablation between September 2021 and May 2024. EEF values were calculated based on T2WI fat suppression (T2WI-FS) sequences, and radiomics features were extracted. Predictive features were selected using minimum redundancy maximum relevance (MRMR) and least absolute shrinkage and selection operator (LASSO) methods, and two joint—based on decision tree and random forest algorithms—models were developed for EEF prediction.ResultsThe decision tree model achieved a mean absolute error (MAE) of 8.095 on the test set, while the random forest model exhibited an MAE of 8.231. The Wilcoxon rank-sum test for the test set revealed that the discrepancy in predictive performance between the two models was statistically significant (p < 0.05). The correlation coefficients were 0.768 and 0.777, and the R2 coefficients of the two models in the test set were 0.559 and 0.549, respectively.ConclusionThe joint model integrating T2WI radiomics and clinical data effectively predicted EEF values for HIFU ablation in adenomyosis. This approach provides a foundation for optimizing HIFU dosing strategies and enhancing treatment safety and efficacy.https://www.frontiersin.org/articles/10.3389/fphys.2025.1602866/fulladenomyosismagnetic resonance imaginghigh-intensity focused ultrasoundenergy efficiency factorprediction
spellingShingle Ziyan Liu
Ziyi Liu
Yuan Wang
Xiyao Wan
Xiaohua Huang
Machine learning-based predictive analysis of energy efficiency factors necessary for the HIFU treatment of adenomyosis
Frontiers in Physiology
adenomyosis
magnetic resonance imaging
high-intensity focused ultrasound
energy efficiency factor
prediction
title Machine learning-based predictive analysis of energy efficiency factors necessary for the HIFU treatment of adenomyosis
title_full Machine learning-based predictive analysis of energy efficiency factors necessary for the HIFU treatment of adenomyosis
title_fullStr Machine learning-based predictive analysis of energy efficiency factors necessary for the HIFU treatment of adenomyosis
title_full_unstemmed Machine learning-based predictive analysis of energy efficiency factors necessary for the HIFU treatment of adenomyosis
title_short Machine learning-based predictive analysis of energy efficiency factors necessary for the HIFU treatment of adenomyosis
title_sort machine learning based predictive analysis of energy efficiency factors necessary for the hifu treatment of adenomyosis
topic adenomyosis
magnetic resonance imaging
high-intensity focused ultrasound
energy efficiency factor
prediction
url https://www.frontiersin.org/articles/10.3389/fphys.2025.1602866/full
work_keys_str_mv AT ziyanliu machinelearningbasedpredictiveanalysisofenergyefficiencyfactorsnecessaryforthehifutreatmentofadenomyosis
AT ziyiliu machinelearningbasedpredictiveanalysisofenergyefficiencyfactorsnecessaryforthehifutreatmentofadenomyosis
AT yuanwang machinelearningbasedpredictiveanalysisofenergyefficiencyfactorsnecessaryforthehifutreatmentofadenomyosis
AT xiyaowan machinelearningbasedpredictiveanalysisofenergyefficiencyfactorsnecessaryforthehifutreatmentofadenomyosis
AT xiaohuahuang machinelearningbasedpredictiveanalysisofenergyefficiencyfactorsnecessaryforthehifutreatmentofadenomyosis