Machine learning-driven ultrasound radiomics for assessing axillary lymph node burden in breast cancer

ObjectiveThis study explores the value of combining intratumoral and peritumoral radiomics features from ultrasound imaging with clinical characteristics to assess axillary lymph node burden in breast cancer patients.MethodsA total of 131 breast cancer patients with axillary lymph node metastasis (A...

Full description

Saved in:
Bibliographic Details
Main Authors: Si-Rui Wang, Feng Tian, Tong Zhu, Chun-Li Cao, Jin-Li Wang, Wen-Xiao Li, Jun Li, Ji-Xue Hou
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-02-01
Series:Frontiers in Endocrinology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fendo.2025.1548888/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850230558457593856
author Si-Rui Wang
Feng Tian
Tong Zhu
Chun-Li Cao
Jin-Li Wang
Wen-Xiao Li
Jun Li
Ji-Xue Hou
author_facet Si-Rui Wang
Feng Tian
Tong Zhu
Chun-Li Cao
Jin-Li Wang
Wen-Xiao Li
Jun Li
Ji-Xue Hou
author_sort Si-Rui Wang
collection DOAJ
description ObjectiveThis study explores the value of combining intratumoral and peritumoral radiomics features from ultrasound imaging with clinical characteristics to assess axillary lymph node burden in breast cancer patients.MethodsA total of 131 breast cancer patients with axillary lymph node metastasis (ALNM) were enrolled between June 2019 and September 2024. Patients were divided into low (n=79) and high (n=52) axillary lymph node burden (ALNB) groups. They were further split into training (n=92) and validation (n=39) cohorts. Intratumoral and peritumoral features were analyzed using the maximum relevance minimum redundancy (MRMR) and least absolute shrinkage and selection operator (LASSO) methods. Six machine learning models were evaluated, and a combined clinical-radiomics model was built.ResultsThe combined logistic regression model exhibited superior diagnostic performance for high axillary lymph node burden, with areas under the ROC curve (AUC) of 0.857 in the training cohort and 0.820 in the validation cohort, outperforming individual models. The model balanced sensitivity and specificity well at a 52% cutoff value. A nomogram provided a practical risk assessment tool for clinicians.ConclusionThe combined clinical-radiomics model showed excellent predictive ability and may aid in optimizing management and treatment decisions for breast cancer patients.
format Article
id doaj-art-3446927f12d44ffe8f2546d7cd9249f8
institution OA Journals
issn 1664-2392
language English
publishDate 2025-02-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Endocrinology
spelling doaj-art-3446927f12d44ffe8f2546d7cd9249f82025-08-20T02:03:51ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922025-02-011610.3389/fendo.2025.15488881548888Machine learning-driven ultrasound radiomics for assessing axillary lymph node burden in breast cancerSi-Rui Wang0Feng Tian1Tong Zhu2Chun-Li Cao3Jin-Li Wang4Wen-Xiao Li5Jun Li6Ji-Xue Hou7The Ultrasound Diagnosis Department of the First Affiliated Hospital of Shihezi University, Shihezi, Xinjiang, ChinaThe Neurology Department of the First Affiliated Hospital of Shihezi University, Shihezi, Xinjiang, ChinaThe Ultrasound Diagnosis Department of the First Affiliated Hospital of Shihezi University, Shihezi, Xinjiang, ChinaThe Ultrasound Diagnosis Department of the First Affiliated Hospital of Shihezi University, Shihezi, Xinjiang, ChinaThe Ultrasound Diagnosis Department of the First Affiliated Hospital of Shihezi University, Shihezi, Xinjiang, ChinaThe Ultrasound Diagnosis Department of the First Affiliated Hospital of Shihezi University, Shihezi, Xinjiang, ChinaThe Ultrasound Diagnosis Department of the First Affiliated Hospital of Shihezi University, Shihezi, Xinjiang, ChinaThe Thyroid and Breast Surgery Department of the First Affiliated Hospital of Shihezi University, Shihezi, Xinjiang, ChinaObjectiveThis study explores the value of combining intratumoral and peritumoral radiomics features from ultrasound imaging with clinical characteristics to assess axillary lymph node burden in breast cancer patients.MethodsA total of 131 breast cancer patients with axillary lymph node metastasis (ALNM) were enrolled between June 2019 and September 2024. Patients were divided into low (n=79) and high (n=52) axillary lymph node burden (ALNB) groups. They were further split into training (n=92) and validation (n=39) cohorts. Intratumoral and peritumoral features were analyzed using the maximum relevance minimum redundancy (MRMR) and least absolute shrinkage and selection operator (LASSO) methods. Six machine learning models were evaluated, and a combined clinical-radiomics model was built.ResultsThe combined logistic regression model exhibited superior diagnostic performance for high axillary lymph node burden, with areas under the ROC curve (AUC) of 0.857 in the training cohort and 0.820 in the validation cohort, outperforming individual models. The model balanced sensitivity and specificity well at a 52% cutoff value. A nomogram provided a practical risk assessment tool for clinicians.ConclusionThe combined clinical-radiomics model showed excellent predictive ability and may aid in optimizing management and treatment decisions for breast cancer patients.https://www.frontiersin.org/articles/10.3389/fendo.2025.1548888/fullbreast cancerultrasoundaxillary lymph nodes burdenradiomicsmachine learning
spellingShingle Si-Rui Wang
Feng Tian
Tong Zhu
Chun-Li Cao
Jin-Li Wang
Wen-Xiao Li
Jun Li
Ji-Xue Hou
Machine learning-driven ultrasound radiomics for assessing axillary lymph node burden in breast cancer
Frontiers in Endocrinology
breast cancer
ultrasound
axillary lymph nodes burden
radiomics
machine learning
title Machine learning-driven ultrasound radiomics for assessing axillary lymph node burden in breast cancer
title_full Machine learning-driven ultrasound radiomics for assessing axillary lymph node burden in breast cancer
title_fullStr Machine learning-driven ultrasound radiomics for assessing axillary lymph node burden in breast cancer
title_full_unstemmed Machine learning-driven ultrasound radiomics for assessing axillary lymph node burden in breast cancer
title_short Machine learning-driven ultrasound radiomics for assessing axillary lymph node burden in breast cancer
title_sort machine learning driven ultrasound radiomics for assessing axillary lymph node burden in breast cancer
topic breast cancer
ultrasound
axillary lymph nodes burden
radiomics
machine learning
url https://www.frontiersin.org/articles/10.3389/fendo.2025.1548888/full
work_keys_str_mv AT siruiwang machinelearningdrivenultrasoundradiomicsforassessingaxillarylymphnodeburdeninbreastcancer
AT fengtian machinelearningdrivenultrasoundradiomicsforassessingaxillarylymphnodeburdeninbreastcancer
AT tongzhu machinelearningdrivenultrasoundradiomicsforassessingaxillarylymphnodeburdeninbreastcancer
AT chunlicao machinelearningdrivenultrasoundradiomicsforassessingaxillarylymphnodeburdeninbreastcancer
AT jinliwang machinelearningdrivenultrasoundradiomicsforassessingaxillarylymphnodeburdeninbreastcancer
AT wenxiaoli machinelearningdrivenultrasoundradiomicsforassessingaxillarylymphnodeburdeninbreastcancer
AT junli machinelearningdrivenultrasoundradiomicsforassessingaxillarylymphnodeburdeninbreastcancer
AT jixuehou machinelearningdrivenultrasoundradiomicsforassessingaxillarylymphnodeburdeninbreastcancer