Machine learning with magnetic resonance imaging for prediction of response to neoadjuvant chemotherapy in breast cancer: A systematic review and meta-analysis

• Published in: European journal of radiology 2022-05, Vol.150, p.110247-110247, Article 110247
• Main Authors: Liang, Xueheng, Yu, Xingyan, Gao, Tianhu
• Format: Article
• Language: English
• Subjects: Breast neoplasms; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - drug therapy; Breast Neoplasms - pathology; Female; Humans; Machine Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Neoadjuvant therapy; Neoadjuvant Therapy - methods; Retrospective Studies; ROC Curve
• ISSN: 0720-048X; 1872-7727
• DOI: 10.1016/j.ejrad.2022.110247

•Machine learning has moderate accuracy (AUC = 0.87) in predicting breast cancer pCR.•Deep learning predicts NAC responses more accurately than ML + radiomics.•pCR prediction by radiomics is more precise with clinical information than without it. The aim of this meta-analysis was to determine the diagnostic accuracy of machine learning (ML) models with MRI in predicting pathological response to neoadjuvant chemotherapy in patients with breast cancer. Furthermore, we compared the pathologic complete response (pCR) prediction performance of ML + radiomics with that of a deep learning (DL) algorithm. A search for relevant studies published until December 20, 2021 was conducted in MEDLINE and EMBASE databases. The quality of the studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies −2 criteria. The I2 value assessed the heterogeneity of the included studies as well as the decision to adopt a random effects model. The area under the receiver operating characteristic curves (AUC) was pooled to quantify the predictive accuracy. Subgroup analysis, meta-regression analysis, and sensitivity analysis were performed to detect potential sources of study heterogeneity. A funnel plot was used to investigate publication bias. The PROSPERO ID of our study was CRD42022284071. Seventeen eligible studies encompassing 3392 patients were evaluated in the analysis. ML + MRI showed high accuracy (AUC = 0.87, 95% CI = 0.84–0.91) in predicting response to neoadjuvant therapy. In subgroup analysis, the AUC of the DL subgroup (AUC = 0.92, 95% CI = 0.88–0.97) was higher than that of the ML + radiomics subgroup (AUC = 0.85, 95% CI = 0.82–0.90) (P = 0.030). In the ML + radiomics subgroup, the studies using MRI combined with other parameters (clinical or histopathologic information; AUC = 0.90, 95% CI = 0.85–0.96) reported better performance than studies using only MRI parameters (AUC = 0.82, 95% CI = 0.78–0.86) (P = 0.009). ML applied to MRI enabled moderate accuracy in predicting pathological response to neoadjuvant therapy in patients with breast cancer. Furthermore, the meta-analysis showed that DL had higher predictive accuracy than ML + radiomics.