摘要
Rationale and Objectives: Lymphovascular invasion (LVI) plays an important role in the prediction of metastasis and prognosis in breast cancer (BC) patients. The present study assessed correlations between preoperative breast MRI, clinical features, and LVI in patients with invasive ductal carcinoma (IDC) and identified risk factors based on these correlation factors.Materials and Methods: Patients confirmed with IDC between 01/2012 and 12/2021 were retrospectively reviewed at our hospital. A total of 5 clinical and 14 MRI features to characterize tumours were extracted. LVI evaluated in hematoxylin and eosin sections. T-test and chi-square tests were used to compare the differences in clinical and MRI features between the LVI positive and negative groups. The associ-ations between individual features and LVI were analysed by univariable logistic regression analysis, and risk factors for LVI were identified by multivariable logistic regression analysis based on these correlation factors.Results: This study included 353 patients with IDC, including 130 with positive LVI. Age, CEA, CA-153, amount of fibroglandular tissue (FGT), background parenchymal enhancement, tumour size, shape, skin thickening, nipple retraction, adjacent vessel sign, and axillary lymph node (ALN) size in the LVI positive group were significantly different from the LVI negative group (all p<0.05). Multivariate logistic regression analysis revealed that age (odds ratio OR = 1.030), CA-153 (OR = 1.018), heterogeneous FGT (OR = 2.484), shape (OR = 2.157), and ALN size (OR =1.051) were risk factors for LVI (all p<0.05). Conclusion: Preoperative breast MRI and clinical features correlated with LVI, age, CA-153, heterogeneous FGT, shape, and ALN size are risk factors for LVI in patients with IDC.
学科与关键词
- Using Machine Learning Methods to Assess Lymphovascular Invasion and Survival in Breast Cancer: Performance of Combining Preoperative Clinical and MRI CharacteristicsXu, Zeyan; Xie, Yu; Wu, Lei; Chen, Minglei; Shi, Zhenwei; Cui, Yanfen; Han, Chu; Lin, Huan; Liu, Yu; Li, Pinxiong; Chen, Xin; Ding, Yingying*; Liu, Zaiyi*Journal of Magnetic Resonance Imaging, 2023, 58(5): 1580-1589.
- Predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: Transfer learning vs. radiomicsFeng, Bao; Liu, Zhuangsheng; Liu, Yu; Chen, Yehang; Zhou, Haoyang; Cui, Enming; Li, Xiaoping; Chen, Xiangmeng; Li, Ronggang; Yu, Tianyou; Zhang, Ling*; Long, Wansheng*Frontiers in Oncology, 2022, 12: 890659.被引 3
- Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: A machine learning, multicenter studyYu, Yunfang; He, Zifan; Ouyang, Jie; Tan, Yujie; Chen, Yongjian; Gu, Yang; Mao, Luhui; Ren, Wei; Wang, Jue; Lin, Lili; Wu, Zhuo; Liu, Jingwen; Ou, Qiyun; Hu, Qiugen; Li, Anlin; Chen, Kai; Li, Chenchen; Lu, Nian; Li, Xiaohong; Su, Fengxi; Liu, Qiang; Xie, Chuanmiao*; Yao, Herui*EBioMedicine, 2021, 69: 103460.被引 84
