What type of study is this?

This is a Quantitative Study study.

September 17, 2025

Novel MRI-based Hyper-Fused Radiomics for Predicting Pathologic Complete Response to Neoadjuvant Therapy in Breast Cancer

Key Points

The hyper-fused model significantly improves predictive accuracy for pathologic complete response in breast cancer.
Higher area under the curve (AUC) metrics indicate better predictive performance than conventional methods.
Extracted hyper-fused features provide a comprehensive approach by integrating voxel-wise MRI data.
This research suggests hyper-fused radiomics could enhance personalized treatment strategies in oncology.

Abstract

Motivation: Predicting pathologic complete response (pCR) to neoadjuvant therapy (NAT) in breast cancer (BC) is essential for personalized treatment planning. Goal(s): This study aimed to enhance predictive accuracy of MRI-based radiomics by developing a hyper-fused radiomic model. Approach: Hyper-fused radiomic features were extracted by combining voxel-wise data from multiple MRI parametric volumes, transformed into spherical coordinates for more comprehensive analysis. Results: The hyper-fused model demonstrated higher predictive performance compared to conventional methods, with greater AUCs and robust associations with pCR, validated in an external test set. Impact: This research highlights hyper-fused radiomics as a promising tool in precision oncology, potentially replacing contrast-based imaging for patients with contraindications and advancing predictive accuracy in therapy response.

KI fragen

Bookmark