Contrast-enhanced ultrasound radiomics model for predicting axillary lymph node metastasis and prognosis in breast cancer: a multicenter study
Abstract Objective To construct a multimodal ultrasound (US) radiomics model for predicting axillary lymph node metastasis (ALNM) in breast cancer and evaluated its application value in predicting ALNM and patient prognosis. Methods From March 2014 to December 2022, data from 682 breast cancer patie...
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-08-01
|
| Series: | BMC Cancer |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12885-025-14632-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849342258923438080 |
|---|---|
| author | Shi Yu Li Yue Ming Li Yong Qi Fang Zhi Ying Jin Jun Kang Li Xiao Meng Zou Si Si Huang Rui Lan Niu Nai Qing Fu Yu Hong Shao Xuan Tong Gong Mao Ran Li Wei Wang Zhi Li Wang |
| author_facet | Shi Yu Li Yue Ming Li Yong Qi Fang Zhi Ying Jin Jun Kang Li Xiao Meng Zou Si Si Huang Rui Lan Niu Nai Qing Fu Yu Hong Shao Xuan Tong Gong Mao Ran Li Wei Wang Zhi Li Wang |
| author_sort | Shi Yu Li |
| collection | DOAJ |
| description | Abstract Objective To construct a multimodal ultrasound (US) radiomics model for predicting axillary lymph node metastasis (ALNM) in breast cancer and evaluated its application value in predicting ALNM and patient prognosis. Methods From March 2014 to December 2022, data from 682 breast cancer patients from four hospitals were collected, including preoperative grayscale US, color Doppler flow imaging (CDFI), contrast-enhanced ultrasound (CEUS) imaging data, and clinical information. Data from the First Medical Center of PLA General Hospital were used as the training and internal validation sets, while data from Peking University First Hospital, the Cancer Hospital of the Chinese Academy of Medical Sciences, and the Fourth Medical Center of PLA General Hospital were used as the external validation set. LASSO regression was employed to select radiomic features (RFs), while eight machine learning algorithms were utilized to construct radiomic models based on US, CDFI, and CEUS. The prediction efficiency of ALNM was assessed to identify the optimal model. In the meantime, Radscore was computed and integrated with immunoinflammatory markers to forecast Disease-Free Survival (DFS) in breast cancer patients. Follow-up methods included telephone outreach and in-person hospital visits. The analysis employed Cox regression to pinpoint prognostic factors, while clinical-imaging models were developed accordingly. The performance of the model was evaluated using the C-index, Receiver Operating Characteristic (ROC) curves, calibration curves, and Decision Curve Analysis (DCA). Results In the training cohort (n = 400), 40% of patients had ALNM, with a mean age of 55 ± 10 years. The US + CDFI + CEUS-based radiomics model achieved Area Under the Curves (AUCs) of 0.88, 0.81, and 0.77 for predicting N0 versus N+ (≥ 1) in the training, internal, and external validation sets, respectively, outperforming the US-only model (P < 0.05). For distinguishing N+ (1–2) from N+ (≥ 3), the model achieved AUCs of 0.89, 0.74, and 0.75. Combining radiomics scores with clinical immunoinflammatory markers (platelet count and neutrophil-to-lymphocyte ratio) yielded a clinical-radiomics model predicting disease-free survival (DFS), with C-indices of 0.80, 0.73, and 0.79 across the three cohorts. In the external validation cohort, the clinical-radiomics model achieved higher AUCs for predicting 2-, 3-, and 5-year DFS compared to the clinical model alone (2-year: 0.79 vs. 0.66; 3-year: 0.83 vs. 0.70; 5-year: 0.78 vs. 0.64; all P < 0.05). Calibration and decision curve analyses demonstrated good model agreement and clinical utility. Conclusion The multimodal ultrasound radiomics model based on US, CDFI, and CEUS could effectively predict ALNM in breast cancer. Furthermore, the combined application of radiomics and immune inflammation markers might predict the DFS of breast cancer patients to some extent. |
| format | Article |
| id | doaj-art-a09b825c2d474f4aa2c95e99f8e26bef |
| institution | Kabale University |
| issn | 1471-2407 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Cancer |
| spelling | doaj-art-a09b825c2d474f4aa2c95e99f8e26bef2025-08-20T03:43:27ZengBMCBMC Cancer1471-24072025-08-0125111610.1186/s12885-025-14632-9Contrast-enhanced ultrasound radiomics model for predicting axillary lymph node metastasis and prognosis in breast cancer: a multicenter studyShi Yu Li0Yue Ming Li1Yong Qi Fang2Zhi Ying Jin3Jun Kang Li4Xiao Meng Zou5Si Si Huang6Rui Lan Niu7Nai Qing Fu8Yu Hong Shao9Xuan Tong Gong10Mao Ran Li11Wei Wang12Zhi Li Wang13Medical School of Chinese PLAMedical School of Chinese PLADepartment of Ultrasound, The First Medical Center, Chinese PLA General HospitalMedical School of Chinese PLADepartment of Ultrasound, Chinese People’s Liberation Army 63820 HospitalMedical School of Chinese PLAMedical School of Chinese PLAMedical School of Chinese PLAMedical School of Chinese PLADepartment of Ultrasound, Peking University First HospitalDepartment of Ultrasound, the Cancer Hospital of the Chinese Academy of Medical SciencesDepartment of Ultrasound, the Cancer Hospital of the Chinese Academy of Medical SciencesDepartment of Ultrasound, the Fourth Medical Center of the PLA General HospitalDepartment of Ultrasound, The First Medical Center, Chinese PLA General HospitalAbstract Objective To construct a multimodal ultrasound (US) radiomics model for predicting axillary lymph node metastasis (ALNM) in breast cancer and evaluated its application value in predicting ALNM and patient prognosis. Methods From March 2014 to December 2022, data from 682 breast cancer patients from four hospitals were collected, including preoperative grayscale US, color Doppler flow imaging (CDFI), contrast-enhanced ultrasound (CEUS) imaging data, and clinical information. Data from the First Medical Center of PLA General Hospital were used as the training and internal validation sets, while data from Peking University First Hospital, the Cancer Hospital of the Chinese Academy of Medical Sciences, and the Fourth Medical Center of PLA General Hospital were used as the external validation set. LASSO regression was employed to select radiomic features (RFs), while eight machine learning algorithms were utilized to construct radiomic models based on US, CDFI, and CEUS. The prediction efficiency of ALNM was assessed to identify the optimal model. In the meantime, Radscore was computed and integrated with immunoinflammatory markers to forecast Disease-Free Survival (DFS) in breast cancer patients. Follow-up methods included telephone outreach and in-person hospital visits. The analysis employed Cox regression to pinpoint prognostic factors, while clinical-imaging models were developed accordingly. The performance of the model was evaluated using the C-index, Receiver Operating Characteristic (ROC) curves, calibration curves, and Decision Curve Analysis (DCA). Results In the training cohort (n = 400), 40% of patients had ALNM, with a mean age of 55 ± 10 years. The US + CDFI + CEUS-based radiomics model achieved Area Under the Curves (AUCs) of 0.88, 0.81, and 0.77 for predicting N0 versus N+ (≥ 1) in the training, internal, and external validation sets, respectively, outperforming the US-only model (P < 0.05). For distinguishing N+ (1–2) from N+ (≥ 3), the model achieved AUCs of 0.89, 0.74, and 0.75. Combining radiomics scores with clinical immunoinflammatory markers (platelet count and neutrophil-to-lymphocyte ratio) yielded a clinical-radiomics model predicting disease-free survival (DFS), with C-indices of 0.80, 0.73, and 0.79 across the three cohorts. In the external validation cohort, the clinical-radiomics model achieved higher AUCs for predicting 2-, 3-, and 5-year DFS compared to the clinical model alone (2-year: 0.79 vs. 0.66; 3-year: 0.83 vs. 0.70; 5-year: 0.78 vs. 0.64; all P < 0.05). Calibration and decision curve analyses demonstrated good model agreement and clinical utility. Conclusion The multimodal ultrasound radiomics model based on US, CDFI, and CEUS could effectively predict ALNM in breast cancer. Furthermore, the combined application of radiomics and immune inflammation markers might predict the DFS of breast cancer patients to some extent.https://doi.org/10.1186/s12885-025-14632-9Contrast-enhanced ultrasoundBreast cancerRadiomicsLymph node metastasisPrognosis |
| spellingShingle | Shi Yu Li Yue Ming Li Yong Qi Fang Zhi Ying Jin Jun Kang Li Xiao Meng Zou Si Si Huang Rui Lan Niu Nai Qing Fu Yu Hong Shao Xuan Tong Gong Mao Ran Li Wei Wang Zhi Li Wang Contrast-enhanced ultrasound radiomics model for predicting axillary lymph node metastasis and prognosis in breast cancer: a multicenter study BMC Cancer Contrast-enhanced ultrasound Breast cancer Radiomics Lymph node metastasis Prognosis |
| title | Contrast-enhanced ultrasound radiomics model for predicting axillary lymph node metastasis and prognosis in breast cancer: a multicenter study |
| title_full | Contrast-enhanced ultrasound radiomics model for predicting axillary lymph node metastasis and prognosis in breast cancer: a multicenter study |
| title_fullStr | Contrast-enhanced ultrasound radiomics model for predicting axillary lymph node metastasis and prognosis in breast cancer: a multicenter study |
| title_full_unstemmed | Contrast-enhanced ultrasound radiomics model for predicting axillary lymph node metastasis and prognosis in breast cancer: a multicenter study |
| title_short | Contrast-enhanced ultrasound radiomics model for predicting axillary lymph node metastasis and prognosis in breast cancer: a multicenter study |
| title_sort | contrast enhanced ultrasound radiomics model for predicting axillary lymph node metastasis and prognosis in breast cancer a multicenter study |
| topic | Contrast-enhanced ultrasound Breast cancer Radiomics Lymph node metastasis Prognosis |
| url | https://doi.org/10.1186/s12885-025-14632-9 |
| work_keys_str_mv | AT shiyuli contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT yuemingli contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT yongqifang contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT zhiyingjin contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT junkangli contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT xiaomengzou contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT sisihuang contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT ruilanniu contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT naiqingfu contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT yuhongshao contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT xuantonggong contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT maoranli contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT weiwang contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy AT zhiliwang contrastenhancedultrasoundradiomicsmodelforpredictingaxillarylymphnodemetastasisandprognosisinbreastcanceramulticenterstudy |