An Ultrasound-based Machine Learning Model for Predicting Tumor-Infiltrating Lymphocytes in Breast Cancer

Introduction Tumor-infiltrating lymphocytes (TILs) are key indicators of immune response and prognosis in breast cancer (BC). Accurate prediction of TIL levels is essential for guiding personalized treatment strategies. This study aimed to develop and evaluate machine learning models using ultrasoun...

Full description

Saved in:
Bibliographic Details
Main Authors: Boya Liu MM, Xiangrong Gu MM, Danling Xie MM, Bing Zhao BM, Dong Han MD, Yuli Zhang BM, Tao Li PhD, Jingqin Fang MD, PhD
Format: Article
Language:English
Published: SAGE Publishing 2025-04-01
Series:Technology in Cancer Research & Treatment
Online Access:https://doi.org/10.1177/15330338251334453
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850281208827609088
author Boya Liu MM
Xiangrong Gu MM
Danling Xie MM
Bing Zhao BM
Dong Han MD
Yuli Zhang BM
Tao Li PhD
Jingqin Fang MD, PhD
author_facet Boya Liu MM
Xiangrong Gu MM
Danling Xie MM
Bing Zhao BM
Dong Han MD
Yuli Zhang BM
Tao Li PhD
Jingqin Fang MD, PhD
author_sort Boya Liu MM
collection DOAJ
description Introduction Tumor-infiltrating lymphocytes (TILs) are key indicators of immune response and prognosis in breast cancer (BC). Accurate prediction of TIL levels is essential for guiding personalized treatment strategies. This study aimed to develop and evaluate machine learning models using ultrasound-derived radiomics and clinical features to predict TIL levels in BC. Methods This retrospective study included 256 BC patients between January 2019 and August 2023, who were randomly divided into training (n = 179) and test (n = 77) cohorts. Radiomics features were extracted from the intratumor and peritumor regions in ultrasound images. Feature selection was performed using the “Boruta” package in R to iteratively remove non-significant features. Extra Trees Classifier was used to construct radiomics and clinical models. A combined radiomics-clinical (R-C) model was also developed. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and decision curve analysis (DCA) to assess clinical utility. A nomogram was created based on the best-performing model. Results A total of 1712 radiomics features were extracted from the intratumor and peritumor regions. The Boruta method selected five key features (four from the peritumor and one from the intratumor) for model construction. Clinical features, including immunohistochemistry, tumor size, shape, and echo characteristics, showed significant differences between high (≥10%) and low (<10%) TIL groups. Both the R-C and radiomics models outperformed the clinical model in the test cohort (area under the curve values of 0.869/0.838 vs 0.627, P  < .05). Calibration curves and Brier scores demonstrated superior accuracy and calibration for the R-C and radiomics models. DCA revealed the highest net benefit of the R-C model at intermediate threshold probabilities. Conclusion Ultrasound-derived radiomics effectively predicts TIL levels in BC, providing valuable insights for personalized treatment and surveillance strategies.
format Article
id doaj-art-3a8e62d02cc741b89e4308d67015e88d
institution OA Journals
issn 1533-0338
language English
publishDate 2025-04-01
publisher SAGE Publishing
record_format Article
series Technology in Cancer Research & Treatment
spelling doaj-art-3a8e62d02cc741b89e4308d67015e88d2025-08-20T01:48:25ZengSAGE PublishingTechnology in Cancer Research & Treatment1533-03382025-04-012410.1177/15330338251334453An Ultrasound-based Machine Learning Model for Predicting Tumor-Infiltrating Lymphocytes in Breast CancerBoya Liu MM0Xiangrong Gu MM1Danling Xie MM2Bing Zhao BM3Dong Han MD4Yuli Zhang BM5Tao Li PhD6Jingqin Fang MD, PhD7 Department of Ultrasound Diagnosis, Wanzhou District First People's Hospital, Chongqing, China Department of Radiology, Daping Hospital, Army Medical University, Chongqing, China Department of Ultrasound Diagnosis, The Second Affiliated Hospital of the Army Medical University, Chongqing, China Department of Ultrasound, Daping Hospital, Army Medical University, Chongqing, China Department of Ultrasound, Daping Hospital, Army Medical University, Chongqing, China Department of Ultrasound, Daping Hospital, Army Medical University, Chongqing, China Department of Ultrasound, Daping Hospital, Army Medical University, Chongqing, China Department of Ultrasound, Daping Hospital, Army Medical University, Chongqing, ChinaIntroduction Tumor-infiltrating lymphocytes (TILs) are key indicators of immune response and prognosis in breast cancer (BC). Accurate prediction of TIL levels is essential for guiding personalized treatment strategies. This study aimed to develop and evaluate machine learning models using ultrasound-derived radiomics and clinical features to predict TIL levels in BC. Methods This retrospective study included 256 BC patients between January 2019 and August 2023, who were randomly divided into training (n = 179) and test (n = 77) cohorts. Radiomics features were extracted from the intratumor and peritumor regions in ultrasound images. Feature selection was performed using the “Boruta” package in R to iteratively remove non-significant features. Extra Trees Classifier was used to construct radiomics and clinical models. A combined radiomics-clinical (R-C) model was also developed. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and decision curve analysis (DCA) to assess clinical utility. A nomogram was created based on the best-performing model. Results A total of 1712 radiomics features were extracted from the intratumor and peritumor regions. The Boruta method selected five key features (four from the peritumor and one from the intratumor) for model construction. Clinical features, including immunohistochemistry, tumor size, shape, and echo characteristics, showed significant differences between high (≥10%) and low (<10%) TIL groups. Both the R-C and radiomics models outperformed the clinical model in the test cohort (area under the curve values of 0.869/0.838 vs 0.627, P  < .05). Calibration curves and Brier scores demonstrated superior accuracy and calibration for the R-C and radiomics models. DCA revealed the highest net benefit of the R-C model at intermediate threshold probabilities. Conclusion Ultrasound-derived radiomics effectively predicts TIL levels in BC, providing valuable insights for personalized treatment and surveillance strategies.https://doi.org/10.1177/15330338251334453
spellingShingle Boya Liu MM
Xiangrong Gu MM
Danling Xie MM
Bing Zhao BM
Dong Han MD
Yuli Zhang BM
Tao Li PhD
Jingqin Fang MD, PhD
An Ultrasound-based Machine Learning Model for Predicting Tumor-Infiltrating Lymphocytes in Breast Cancer
Technology in Cancer Research & Treatment
title An Ultrasound-based Machine Learning Model for Predicting Tumor-Infiltrating Lymphocytes in Breast Cancer
title_full An Ultrasound-based Machine Learning Model for Predicting Tumor-Infiltrating Lymphocytes in Breast Cancer
title_fullStr An Ultrasound-based Machine Learning Model for Predicting Tumor-Infiltrating Lymphocytes in Breast Cancer
title_full_unstemmed An Ultrasound-based Machine Learning Model for Predicting Tumor-Infiltrating Lymphocytes in Breast Cancer
title_short An Ultrasound-based Machine Learning Model for Predicting Tumor-Infiltrating Lymphocytes in Breast Cancer
title_sort ultrasound based machine learning model for predicting tumor infiltrating lymphocytes in breast cancer
url https://doi.org/10.1177/15330338251334453
work_keys_str_mv AT boyaliumm anultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT xiangronggumm anultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT danlingxiemm anultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT bingzhaobm anultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT donghanmd anultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT yulizhangbm anultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT taoliphd anultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT jingqinfangmdphd anultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT boyaliumm ultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT xiangronggumm ultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT danlingxiemm ultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT bingzhaobm ultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT donghanmd ultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT yulizhangbm ultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT taoliphd ultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer
AT jingqinfangmdphd ultrasoundbasedmachinelearningmodelforpredictingtumorinfiltratinglymphocytesinbreastcancer