Radiomics of Tumor Heterogeneity in Longitudinal Dynamic Contrast-Enhanced Magnetic Resonance Imaging for Predicting Response to Neoadjuvant Chemotherapy in Breast Cancer

Abstract

Breast tumor morphological and vascular characteristics can be changed during neoadjuvant chemotherapy (NACT). The early changes in tumor heterogeneity can be quantitatively modeled by longitudinal dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), which is useful in predicting responses to NACT in breast cancer. In this retrospective analysis, 114 female patients with unilateral unifocal primary breast cancer who received NACT were included in a development (n = 61) dataset and a testing dataset (n = 53). DCE-MRI was performed for each patient before and after treatment (two cycles of NACT) to generate baseline and early follow-up images, respectively. Feature-level changes (delta) of the entire tumor were evaluated by calculating the relative net feature change (deltaRAD) between baseline and follow-up images. The voxel-level change inside the tumor was evaluated, which yielded a Jacobian map by registering the follow-up image to the baseline image. Clinical information and the radiomic features were fused to enhance the predictive performance. The area under the curve (AUC) values were assessed to evaluate the prediction performance. Predictive models using radiomics based on pre- and post-treatment images, Jacobian maps and deltaRAD showed AUC values of 0.568, 0.767, 0.630 and 0.726, respectively. When features from these images were fused, the predictive model generated an AUC value of 0.771. After adding the molecular subtype information in the fused model, the performance was increased to an AUC of 0.809 (sensitivity of 0.826 and specificity of 0.800), which is significantly higher than that of the baseline imaging- and Jacobian map-based predictive models (p = 0.028 and 0.019, respectively). The level of tumor heterogeneity reduction (evaluated by texture feature) is higher in the NACT responders than in the nonresponders. The results suggested that changes in DCE-MRI features that reflect a reduction in tumor heterogeneity following NACT could provide early prediction of breast tumor response. The prediction was improved when the molecular subtype information was combined into the model.

Radiomics Analysis of Multi-Phase DCE-MRI in Predicting Tumor Response to Neoadjuvant Therapy in Breast Cancer

“…Most of the previous research on breast cancer radiomics only focused on the features extracted from one single phase after enhancement [25,26]. The prediction performance of other phases of DCE-MRI was still relatively unexplored.…”

Pretreatment DCE-MRI-Based Deep Learning Outperforms Radiomics Analysis in Predicting Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer

“…Our results showed that the molecular-only LDA and MLP model achieved an AUROC of 0.744 and 0.752 in the breast cancer patients, higher than kinetic-only and image-only predictive models. However, the molecular information is acquired via invasive needle biopsy, which cannot reflect certain pathophysiological characteristics of tumors, such as microvascular density and permeability, and tumor heterogeneity, which is known to be relevant to the sensitivity of pCR NAC in breast cancer ( 15 , 30 ).…”

“…RA relies on a pipeline including extraction of numerous handcrafted imaging features, followed by feature selection and then machine learning-based classification ( 11 ). However, the performance of radiomics models derived from pretreatment DCE-MRI is limited in predicting pCR with an AUROC ranging from 0.568 to 0.79 ( 12 , 15 , 16 ). DL can automatically learn discriminative features directly from images without the necessity of feature predefinition ( 17 ).…”

Prediction Breast Molecular Typing of Invasive Ductal Carcinoma Based on Dynamic Contrast Enhancement Magnetic Resonance Imaging Radiomics Characteristics: A Feasibility Study

“…Radiomics is a rapid developing field of medical study that quantitates the microstructure and biological information of tumor tissue for exploring the intra-tumoral heterogeneity and tumor characterization in a convenient and non-invasive way ( 22 ). To date, some studies have already investigated the discrimination between benign and malignant breast tumors ( 23 , 24 ), lymph node metastasis ( 25 – 27 ), tumor response prediction of neoadjuvant chemotherapy ( 28 , 29 ), and survival analysis ( 30 , 31 ). Our study found that radiomics showed favorable predictive performance on molecular subtype based on the DCE-MRI images.…”