Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set

Abstract

Purpose To determine whether a multivariate machine learning-based model using computer-extracted features of pre-treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict pathologic complete response (pCR) to neoadjuvant therapy (NAT) in breast cancer patients. Methods Institutional review board approval was obtained for this retrospective study of 288 breast cancer patients at our institution who received NAT and had a pre-treatment breast MRI. A comprehensive set of 529 radiomic features was extracted from each patient’s pretreatment MRI. The patients were divided into equal groups to form a training set and an independent test set. Two multivariate machine learning models (logistic regression and a support vector machine) based on imaging features were trained to predict pCR in (a) all patients with NAT, (b) patients with neoadjuvant chemotherapy (NACT), and (c) triple negative or human epidermal growth factor receptor 2-positive (TN/HER2+) patients who had NAT. The multivariate models were tested using the independent test set, and the area under the receiver operating characteristics (ROC) curve (AUC) was calculated. Results Out of the 288 patients, 64 achieved pCR. The AUC values for predicting pCR in TN/HER+ patients who received NAT were significant (.707, 95%CI: 0.582–0.833, p < 0.002). Conclusions The multivariate models based on pre-treatment MRI features were able to predict pCR in TN/HER2+ patients.

Value of Machine Learning with CE-MRI Radiomics for Early Prediction of Pathological Complete Response to Neoadjuvant Therapy in HER2-positive Invasive Breast Cancer

“…The optical model was able to perform robustly. Speci cally, the AUC of the nal model was 0.84, which was signi cantly higher than that of previous reports [12,25] based on the 1st phase. The result revealed that sequential texture features captured more detailed information of tumor complexity and heterogeneity that indistinguishable to the 1st phase.…”

“…Whereas in uni-focal and unilateral multi-focal cases, the accuracy were 79% and 75% respectively. While in many studies [12,14,24,25], non-mass enhancement and unilateral multifocal cases were excluded, our model performed well without regarding to tumor morphology and number. Several studies suggested that non-mass enhancement and multifocal or multicentric [28][29][30] tumors were more frequently present in HER2positive subtype.…”

“…A possible explanation is that the treatment reagions for training set and validation are not uniform. Another study [25] combining the HER2 positive and TN breast cancers as one subgroup concluded that the AUCs of model of predicting pCR to NAC were less than 0.80 not only in the training sets but also in the validation sets. Nevertheless, analysis suggested that there was a difference in pCR rates after NAC for HER2-positive and triple-negative breast cancers.…”

“…To date, previous studies have indicated that radimics model can detect the pCR to NAT in breast cancer [13,14,21,25]. However, there are no studies published that speci cally assess the performance of MRI radiomics in detecting pCR to NAT in HRE2 positive subtype.…”

Radiomics predicts response of individual HER2‐amplified colorectal cancer liver metastases in patients treated with HER2‐targeted therapy

“…11 Radiomics is the study of these quantitative features and their correlation with tumor phenotypes, 10 and it has been shown to be useful in predicting response to medical therapy in different tumor models. [12][13][14][15][16][17] In CRC correlation has been found between entropy and skewness, computed on CT scans, and tumor grade, KRAS mutational status and risk of recurrence in posttreatment future liver remnant. 18,19 However, prediction of the behavior of single lmCRC under treatment has not been explored and only one published study describes a machine learning method to predict treatment response of individual liver metastases from esophagogastric cancer, achieving an AUC of 0.87.…”