Prediction of Treatment Response to Neoadjuvant Chemotherapy for Breast Cancer via Early Changes in Tumor Heterogeneity Captured by DCE-MRI Registration

Abstract

We analyzed DCE-MR images from 132 women with locally advanced breast cancer from the I-SPY1 trial to evaluate changes of intra-tumor heterogeneity for augmenting early prediction of pathologic complete response (pCR) and recurrence-free survival (RFS) after neoadjuvant chemotherapy (NAC). Utilizing image registration, voxel-wise changes including tumor deformations and changes in DCE-MRI kinetic features were computed to characterize heterogeneous changes within the tumor. Using five-fold cross-validation, logistic regression and Cox regression were performed to model pCR and RFS, respectively. The extracted imaging features were evaluated in augmenting established predictors, including functional tumor volume (FTV) and histopathologic and demographic factors, using the area under the curve ( AUC ) and the C-statistic as performance measures. The extracted voxel-wise features were also compared to analogous conventional aggregated features to evaluate the potential advantage of voxel-wise analysis. Voxel-wise features improved prediction of pCR ( AUC = 0.78 (±0.03) vs 0.71 (±0.04), p < 0.05 and RFS ( C-statistic = 0.76 ( ± 0.05), vs 0.63 ( ± 0.01)), p < 0.05, while models based on analogous aggregate imaging features did not show appreciable performance changes ( p > 0 . 05 ). Furthermore, all selected voxel-wise features demonstrated significant association with outcome ( p < 0.05). Thus, precise measures of voxel-wise changes in tumor heterogeneity extracted from registered DCE-MRI scans can improve early prediction of neoadjuvant treatment outcomes in locally advanced breast cancer.

Comparative Study of Amide Proton Transfer‐Weighted Imaging and Intravoxel Incoherent Motion Imaging in Breast Cancer Diagnosis and Evaluation

“…GLOBALLY, BREAST CANCER is the most common malignant tumor in women 1 . As a noninvasive, radiation‐free examination with high soft‐tissue contrast, magnetic resonance imaging (MRI) plays an important role in the diagnosis, 2 treatment, 3 and prognostic evaluation 4 of breast cancer. However, breast cancer is a highly heterogeneous lesion characterized by variant biological features, and its diagnosis, treatment, and prognosis are affected by multiple factors, including breast cancer lesion size, pathological grade, receptor expression (estrogen receptor [ER], progesterone receptor [PR], and human epidermal growth factor receptor‐2 [HER‐2]), the status of axillary lymph node metastasis, and the antigen KI‐67 (Ki‐67) index 5 .…”

Current Landscape of Breast Cancer Imaging and Potential Quantitative Imaging Markers of Response in ER-Positive Breast Cancers Treated with Neoadjuvant Therapy

“…Recent advances in the radiomics-based analysis have demonstrated the power of transforming imaging data into multi-dimensional mineable radiomic features [181,182] that are relatable to gene expression patterns [183][184][185]. Machine-learning methods can be used to select radiomic features and build predictive models for clinical outcomes [186,187]. With the advances in high-resolution breast imaging techniques [188][189][190][191], detailed radiologic information along with consequential molecular signatures can be extracted, correlated, trained, and learned, yielding models with significant predictive and prognostic power [183,[192][193][194].…”

Image Texture Analysis for Medical Image Mining: A Comparative Study Direct to Osteoarthritis Classification using Knee X-ray Image

“…Furthermore, texture analysis applications have been widely applied in the medical research for the detection of various diseases including: tumor heterogeneity [9], [17], [18]; brain tumor [19], [20]; head and neck cancer [21], [22]; emphysema [23], [24]; prostate segmentation [25]- [27], colon cancer [28], [29]; small vessel disease and blood brain barrier [30], breast cancer [31]- [34]; skin cancer [35]- [37] retinal vessel segmentation [38], [39] and lung cancer [40], [41].…”