Background parenchymal enhancement and uptake as breast cancer imaging biomarkers: A state-of-the-art review

Contrast-Enhanced Mammography (CEM) Capability to Distinguish Molecular Breast Cancer Subtypes

“…The results for BPE (breast parenchyma enhancement) should also be discussed. It is assumed that this phenomenon may affect the disease course and treatment results, as determined by Bauer et al [ 20 ]. In one of the studies concerning the analysis of parenchyma enhancement on MRI, the authors observed that the average BPE pattern was only significantly more common in luminal B (HER2-).…”

Editorial for “Breast MRI Background Parenchymal Enhancement Categorization Using Deep Learning: Outperforming the Radiologist”

“…In a study by Saha et al, the authors developed a machine learning model utilizing an automatic pipeline for BPE classification and demonstrated its potential usage for predicting future breast cancer on high‐risk patients undergoing screening MRI 9 . The possible role of BPE as a breast cancer imaging biomarker, and its current clinical applications, is detailed in a recent state‐of‐the‐art review by Bauer et al 10 …”

“…8 In a study by Saha et al, the authors developed a machine learning model utilizing an automatic pipeline for BPE classification and demonstrated its potential usage for predicting future breast cancer on high-risk patients undergoing screening MRI. 9 The possible role of BPE as a breast cancer imaging biomarker, and its current clinical applications, is detailed in a recent state-of-the-art review by Bauer et al 10 Even though there is increasing evidence that BPE might serve as an independent marker of breast cancer risk and response to breast cancer treatment, the existing knowledge is mostly based on small retrospective studies with variations in patient populations, MRI protocols, methods for assessing BPE, and with no adjustment for individual factors that can influence the level of BPE. Before BPE can become a valuable biomarker for clinical use, we thus need to validate and further investigate the promising results in further studies, including prospective studies with adjustment for confounding variables.…”

Editorial for “4D Machine Learning Radiomics for the Prediction of Breast Cancer Pathologic Complete Response to Neoadjuvant Chemotherapy in Dynamic Contrast‐Enhanced MRI”

“…To date, the gold standard of determining pCR remains histological inspection obtained by operation, regardless of the radiological response evaluation, which includes radiological apparent CR. Yet, several MRI sequences have demonstrated promising utility in predicting and monitoring the response to NAC 3–6 . More recently, the adoption of novel radiomics and machine learning (ML) techniques to breast imaging have been shown to add diagnostic value for various applications 7 .…”

“…Yet, several MRI sequences have demonstrated promising utility in predicting and monitoring the response to NAC. [3][4][5][6] More recently, the adoption of novel radiomics and machine learning (ML) techniques to breast imaging have been shown to add diagnostic value for various applications. 7 Radiomics is a quantitative approach to image analysis, which utilizes advanced mathematical breakdown to extract and correlate multiple texture features.…”