AUTHOR=Gong Xiuru , Guo Yaxin , Zhu Tingting , Peng Xiaolin , Xing Dongwei , Zhang Minguang 

TITLE=Diagnostic performance of radiomics in predicting axillary lymph node metastasis in breast cancer: A systematic review and meta-analysis

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.1046005

DOI=10.3389/fonc.2022.1046005

ISSN=2234-943X

ABSTRACT=Background
The aim of this study was to perform a meta‐analysis to evaluate the diagnostic performance of radiomics in predicting axillary lymph node metastasis (ALNM) and sentinel lymph node metastasis (SLNM) in breast cancer.
Materials and Methods
PubMed, Embase, Web of Science, Cochrane Library databases and two Chinese databases were systematically searched to identify relevant studies published up until April 29, 2022. The quality of the included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) scale. The overall diagnostic odds ratio (DOR), sensitivity, specificity and area under the curve (AUC) were calculated to evaluate the diagnostic performance of radiomic features in patients with lymph node metastasis (LNM) of breast cancer. Spearman's correlation coefficient was calculated and meta-regression and subgroup analysis were performed to explore the causes of heterogeneity.
Results
Thirty studies with 5611 patients were included in this meta-analysis. The pooled DOR, sensitivity, specificity, and AUC with 95% confidence intervals of radiomics in detecting LNM were 23(16,33), 0.86(0.82,0.88), 0.79(0.73,0.84) and 0.90(0.87,0.92), respectively. The meta-analysis showed significant heterogeneity between sensitivity and specificity among the included studies. There was no threshold effect in the test. Meta-regression and subgroup analyses showed that combine clinical factors, modeling methods, region, MRI, US, CT and MMG contributed to the heterogeneity in the sensitivity analysis (P < 0.05). Modeling methods, MR and MMG contributed to the heterogeneity in the specificity analysis (P < 0.05).
Conclusion
Our meta-analysis shows that radiomic has good diagnostic performance in predicting ALNM and SLNM in breast cancer and is expected to be a clinical method for preoperative identification of LNM.