Utilizing multiclassifier radiomics analysis of ultrasound to predict high axillary lymph node tumour burden in node-positive breast cancer patients: a multicentre study

被引:1
|
作者
Wu, Jiangfeng [1 ]
Ge, Lifang [1 ]
Guo, Yinghong [1 ]
Xu, Dong [2 ]
Wang, Zhengping [1 ]
机构
[1] Wenzhou Med Univ, Affiliated Dongyang Hosp, Dongyang Peoples Hosp, Dept Ultrasound, 60 Wuning West Rd, Dongyang 322100, Zhejiang, Peoples R China
[2] Chinese Acad Sci, Zhejiang Canc Hosp, Inst Basic Med & Canc, Dept Ultrasound,Canc Hosp,Univ Chinese Acad Sci, Hangzhou, Peoples R China
关键词
Axillary lymph node; tumour burden; ultrasound; radiomics; breast cancer; INTERNATIONAL EXPERT CONSENSUS; PRIMARY THERAPY; BIOPSY; MANAGEMENT; SELECTION; SURGERY; SYSTEM;
D O I
10.1080/07853890.2024.2395061
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
BackgroundThe tumor burden within the axillary lymph nodes (ALNs) constitutes a pivotal factor in breast cancer, serving as the primary determinant for treatment decisions and exhibiting a close correlation with prognosis.ObjectiveThis study aimed to investigate the potential of ultrasound-based radiomics and clinical characteristics in non-invasively distinguishing between low tumor burden (1-2 positive nodes) and high tumor burden (more than 2 positive nodes) in patients with node-positive breast cancer.MethodsA total of 215 patients with node-positive breast cancer, who underwent preoperative ultrasound examinations, were enrolled in this study. Among these patients, 144 cases were allocated to the training set, 37 cases to the validation set, and 34 cases to the testing set. Postoperative histopathology was used to determine the status of ALN tumor burden. The region of interest for breast cancer was delineated on the ultrasound image. Nine models were developed to predict high ALN tumor burden, employing a combination of three feature screening methods and three machine learning classifiers. Ultimately, the optimal model was selected and tested on both the validation and testing sets. In addition, clinical characteristics were screened to develop a clinical model. Furthermore, Shapley additive explanations (SHAP) values were utilized to provide explanations for the machine learning model.ResultsDuring the validation and testing sets, the models demonstrated area under the curve (AUC) values ranging from 0.577 to 0.733 and 0.583 to 0.719, and accuracies ranging from 64.9% to 75.7% and 64.7% to 70.6%, respectively. Ultimately, the Boruta_XGB model, comprising five radiomics features, was selected as the final model. The AUC values of this model for distinguishing low from high tumor burden were 0.828, 0.715, and 0.719 in the training, validation, and testing sets, respectively, demonstrating its superiority over the clinical model.ConclusionsThe developed radiomics models exhibited a significant level of predictive performance. The Boruta_XGB radiomics model outperformed other radiomics models in this study.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Is axillary lymph node clearance required in node-positive breast cancer?
    Bundred, Nigel J.
    Barnes, Nicola L. P.
    Rutgers, Emiel
    Donker, Mila
    NATURE REVIEWS CLINICAL ONCOLOGY, 2015, 12 (01) : 55 - 61
  • [2] A regression model to predict axillary high tumor burden in sentinel node-positive breast cancer patients
    Barco, Israel
    Garcia-Font, Marc
    Garcia-Fernandez, Antonio
    Gimenez, Nuria
    Fraile, Manuel
    Gonzalez, Sonia
    Vallejo, Elena
    Lain, Jose Maria
    Vidal, MCarmen
    Gonzalez, Clarisa
    Larranaga, Itziar
    Canales, Lidia
    Pessarrodona, Antoni
    Chabrera, Carolina
    BREAST JOURNAL, 2020, 26 (02): : 322 - 324
  • [3] Is axillary lymph node clearance required in node-positive breast cancer?
    Nigel J. Bundred
    Nicola L. P. Barnes
    Emiel Rutgers
    Mila Donker
    Nature Reviews Clinical Oncology, 2015, 12 : 55 - 61
  • [4] Avoidance of axillary lymph node dissection in selected patients with node-positive breast cancer
    Noguchi, M.
    EJSO, 2008, 34 (02): : 129 - 134
  • [5] Role of Completion Axillary Lymph Node Dissection for Sentinel Node-Positive Breast Cancer Patients
    Yi, Min
    Meric-Bernstam, Funda
    Mittendorf, Elizabeth A.
    Kuerer, Henry M.
    Hwang, Rosa F.
    Bedrosian, Isabelle
    Rourke, Loren
    Hunt, Kelly K.
    ANNALS OF SURGICAL ONCOLOGY, 2010, 17 (02) : S159 - S159
  • [6] Early experience of robotic axillary lymph node dissection in patients with node-positive breast cancer
    Ahn, Jee Hyun
    Park, Jung Min
    Choi, Soon Bo
    Go, Jieon
    Lee, Jeea
    Kim, Jee Ye
    Park, Hyung Seok
    BREAST CANCER RESEARCH AND TREATMENT, 2023, 198 (03) : 405 - 412
  • [7] Early experience of robotic axillary lymph node dissection in patients with node-positive breast cancer
    Jee Hyun Ahn
    Jung Min Park
    Soon Bo Choi
    Jieon Go
    Jeea Lee
    Jee Ye Kim
    Hyung Seok Park
    Breast Cancer Research and Treatment, 2023, 198 : 405 - 412
  • [8] Axillary Lymphadenectomy in Sentinel Lymph Node-Positive Breast Cancer
    Liling Zhu
    Kai Chen
    Lisa K. Jacobs
    Rebecca Aft
    Annals of Surgical Oncology, 2018, 25 : 28 - 31
  • [9] Axillary Lymphadenectomy in Sentinel Lymph Node-Positive Breast Cancer
    Zhu, Liling
    Chen, Kai
    Jacobs, Lisa K.
    Aft, Rebecca
    ANNALS OF SURGICAL ONCOLOGY, 2018, 25 (01) : 28 - 31
  • [10] A nomogram to predict the probability of axillary lymph node metastasis in early breast cancer patients with positive axillary ultrasound
    Si-Qi Qiu
    Huan-Cheng Zeng
    Fan Zhang
    Cong Chen
    Wen-He Huang
    Rick G. Pleijhuis
    Jun-Dong Wu
    Gooitzen M. van Dam
    Guo-Jun Zhang
    Scientific Reports, 6