Editorial for “Early Identification of Pathologic Complete Response to Neoadjuvant Chemotherapy Using Multiphase DCE‐MRI by Siamese Network in Breast Cancer: A Longitudinal Multicenter Study”
Year: 2023
Type: editorial
Abstract: Study" B reast cancer is a widespread cancer type, and neoadjuvant chemotherapy (NAC) has turn into a standard treatment for locally advanced cases. 1 Following NAC, pathologic complete response (pCR) indicates increased overall and diseasefree survival.Magnetic resonance imaging (MRI) has been used to predict pCR in breast cancer patients, 2 but it often relies on single-time point imaging, which may not capture evolving tumor characteristics.In this issue of JMRI, an article entitled "Early prediction of pathologic complete response to neoadjuvant chemotherapy using multi-phases DCE-MRI by the Siamese network in breast cancer: a prospective longitudinal study" by Zhang et al. has brought attention to this point and has stated that longitudinal changes in tumor heterogeneity, assessed through MRI during NAC, are important for predicting pCR.To their study deep learning, particularly Siamese networks, has the potential for predicting pCR based on longitudinal images.3 This study aims to develop and validate a model using Siamese networks to predict pCR based on longitudinal DCE-MRI.It also introduces the concept of isochronous proportional sampling (IPS) for selecting DCE-MRI phases judiciously.The IPS technique was introduced by the authors to tackle the issue of utilizing multi-phased DCE-MRI.This approach entails the selection of multiple phases as model inputs, thereby integrating the dynamic alterations in the inflow and outflow of contrast agents in tumor tissue into the predictive model.The study focuses on predicting pathological complete response (pCR) in breast cancer treatment using deep learning and dynamic contrast-enhanced MRI (DCE-MRI).It has several strengths, including addressing a clinically significant problem, employing a prospective longitudinal design to track changes in tumor characteristics during treatment, well-defined inclusion/exclusion criteria, a comprehensive DCE-MRI imaging protocol, and the use of Siamese
DOI: 10.1002/jmri.29190
Authors: Irmak Durur‐Subasi, Afak Durur‐Karakaya
Institutions: Istanbul Medipol University, Koç University
Language: English
Topic: MRI in cancer diagnosis
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: bronze
OpenAlex ID: W4390126153