Machine Learning-Based Radiomics Nomogram Using Magnetic Resonance Images for Prediction of Neoadjuvant Chemotherapy Efficacy in Breast Cancer Patients

Abstract

The construction and validation of a radiomics nomogram based on machine learning using magnetic resonance image (MRI) for predicting the efficacy of neoadjuvant chemotherapy (NACT) in patients with breast cancer (BCa). Methods: This retrospective investigation consisted of 158 patients who were diagnosed with BCa and underwent MRI before NACT, of which 33 patients experienced pathological complete response (pCR) by the postoperative pathological examination. The patients with BCa were divided into the training set (n = 110) and test set (n = 48) randomly. The features were selected by the maximum relevance minimum redundancy (mRMR) and absolute shrinkage and selection operator (LASSO) algorithm in the training set. In return, the radiomics signature was established using machine learning. The predictive score of each patient was calculated using the radiomics signature formula. Finally, the predictive scores and clinical factors were used to perform the multivariate logistic regression and construct the nomogram. Receiver operating characteristics (ROC) analyses were used to assess and validate the diagnostic accuracy of the nomogram in the test set. Lastly, the usefulness of the nomogram was confirmed via decision curve analysis (DCA). Results: The radiomics signature was well-discriminated in the training set [AUC 0.835, specificity 71.32%, and sensitivity 82.61%], and test set (AUC 0.834, specificity 73.21%, and sensitivity 80%). Containing the radiomics signature and hormone status, the radiomics nomogram showed good calibration and discrimination in the training set [AUC 0.888, specificity 79.31%, and sensitivity 86.96%] and test set (AUC 0.879, Chen et al. Radiomics Predicted Efficancy of NACT specificity 82.19%, and sensitivity 83.57%). The decision curve indicated the clinical usefulness of our nomogram. Conclusion: Our radiomics nomogram showed good discrimination in patients with BCa who experience pCR after NACT. The model may aid physicians in predicting how specific patients may respond to BCa treatments in the future.

Multi-Parametric MRI-Based Radiomics Models for Predicting Molecular Subtype and Androgen Receptor Expression in Breast Cancer

“…DWI and its derived apparent diffusion coefficient (ADC) map also served as a non-contrast MR screening method in lesion detection and distinguishing malignancy from benign tumor (31). Several studies applied radiomics based on breast MRI for the evaluation of malignancy, differentiation of molecular subtype, prediction of receptor expression, and evaluation of response to neoadjuvant therapy in breast cancer (27,(32)(33)(34)(35). Some studies have reported that quantitative parameters of functional MRI, deep learning analysis, and MRI-based radiomics analysis had the potential in predicting molecular subtype and Ki-67 expression in breast cancer (36)(37)(38)(39)(40)(41)(42)(43)(44)(45).…”

Radiomics Nomogram Based on Radiomics Score from Multiregional Diffusion-Weighted MRI and Clinical Factors for Evaluating HER-2 2+ Status of Breast Cancer

“…Therefore, improving the diagnostic performance of the model is necessary for the identification of HER-2 2+ status in BC patients. Recent studies showed that a radiomics model constructed by incorporating clinical factors and radiomics score (rad-score) based on radiomic features could improve the predictive ability [23,24]. However, the diagnostic performance of clinical factors and the rad-score based on multiregional DWI and ADC images for evaluating HER-2 2+ status in BC patients has not been thoroughly investigated.…”

Construction and Validation of a Serum Albumin-to-Alkaline Phosphatase Ratio-Based Nomogram for Predicting Pathological Complete Response in Breast Cancer

“…Previous studies demonstrated that various methods could be applied to predict pCR with NAC in breast cancer patients, including analysis of gene signatures, histomorphological factors and imaging features (6)(7)(8). Compared with these methods, serum samples are easy to obtain and reflect the comprehensive state of cancer patients.…”