Non-invasive prediction of axillary lymph node dissection exemption in breast cancer patients post-neoadjuvant therapy: A radiomics and deep learning analysis on longitudinal DCE-MRI data

• Published in: Breast (Edinburgh) Vol. 77; p. 103786
• Main Authors: Yu, Yushuai, Chen, Ruiliang, Yi, Jialu, Huang, Kaiyan, Yu, Xin, Zhang, Jie, Song, Chuangui
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier Ltd 01.10.2024; Elsevier
• Subjects: Adult; Aged; Axilla; Axillary lymph node dissection exemption; Breast cancer; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - pathology; Breast Neoplasms - therapy; Contrast Media; Deep Learning; Female; Humans; Longitudinal data; Lymph Node Excision - methods; Lymph Nodes - diagnostic imaging; Lymph Nodes - pathology; Lymphatic Metastasis - diagnostic imaging; Magnetic Resonance Imaging - methods; Middle Aged; Neoadjuvant therapy; Neoadjuvant Therapy - methods; Original; Predictive Value of Tests; Radiomics; Retrospective Studies; Support Vector Machine; Deep learning; Neoadjuvant therapy; Breast cancer; Longitudinal data; Axillary lymph node dissection exemption; Radiomics
• ISSN: 0960-9776; 1532-3080; 1532-3080
• DOI: 10.1016/j.breast.2024.103786

In breast cancer (BC) patients with clinical axillary lymph node metastasis (cN+) undergoing neoadjuvant therapy (NAT), precise axillary lymph node (ALN) assessment dictates therapeutic strategy. There is a critical demand for a precise method to assess the axillary lymph node (ALN) status in these patients. A retrospective analysis was conducted on 160 BC patients undergoing NAT at Fujian Medical University Union Hospital. We analyzed baseline and two-cycle reassessment dynamic contrast-enhanced MRI (DCE-MRI) images, extracting 3668 radiomic and 4096 deep learning features, and computing 1834 delta-radiomic and 2048 delta-deep learning features. Light Gradient Boosting Machine (LightGBM), Support Vector Machine (SVM), RandomForest, and Multilayer Perceptron (MLP) algorithms were employed to develop risk models and were evaluated using 10-fold cross-validation. Of the patients, 61 (38.13 %) achieved ypN0 status post-NAT. Univariate and multivariable logistic regression analyses revealed molecular subtypes and Ki67 as pivotal predictors of achieving ypN0 post-NAT. The SVM-based “Data Amalgamation” model that integrates radiomic, deep learning features, and clinical data, exhibited an outstanding AUC of 0.986 (95 % CI: 0.954–1.000), surpassing other models. Our study illuminates the challenges and opportunities inherent in breast cancer management post-NAT. By introducing a sophisticated, SVM-based “Data Amalgamation” model, we propose a way towards accurate, dynamic ALN assessments, offering potential for personalized therapeutic strategies in BC. •Feasible exemption of axillary lymph node dissection post-NAT.•Developed a precise method for assessing axillary lymph node status post-NAT.•Model using longitudinal DCE-MRI data improves surgical risk stratification.