Spatial Multi-Task Learning for Breast Cancer Molecular Subtype Prediction from Single-Phase DCE-MRI

TL;DR

This paper introduces a spatial multi-task deep learning framework that accurately predicts breast cancer molecular subtypes from single-phase DCE-MRI, reducing reliance on invasive biopsies and enhancing clinical workflows.

Contribution

The study presents a novel multi-task learning architecture that integrates spatial attention and ROI weighting to improve molecular subtype prediction from practical imaging data.

Findings

Achieved high AUC scores for ER, PR, and HER2 classification.

Significantly outperformed radiomics and single-task models.

Demonstrated feasibility of non-invasive molecular subtype prediction.

Abstract

Accurate molecular subtype classification is essential for personalized breast cancer treatment, yet conventional immunohistochemical analysis relies on invasive biopsies and is prone to sampling bias. Although dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) enables non-invasive tumor characterization, clinical workflows typically acquire only single-phase post-contrast images to reduce scan time and contrast agent dose. In this study, we propose a spatial multi-task learning framework for breast cancer molecular subtype prediction from clinically practical single-phase DCE-MRI. The framework simultaneously predicts estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2) status, and the Ki-67 proliferation index -- biomarkers that collectively define molecular subtypes. The architecture integrates a deep feature extraction network with multi-scale spatial attention to capture intratumoral and peritumoral characteristics, together with a region-of-interest weighting module that emphasizes the tumor core, rim, and surrounding tissue. Multi-task learning exploits biological correlations among biomarkers through shared representations with task-specific prediction branches. Experiments on a dataset of 960 cases (886 internal cases split 7:1:2 for training/validation/testing, and 74 external cases evaluated via five-fold cross-validation) demonstrate that the proposed method achieves an AUC of 0.893, 0.824, and 0.857 for ER, PR, and HER2 classification, respectively, and a mean absolute error of 8.2\% for Ki-67 regression, significantly outperforming radiomics and single-task deep learning baselines. These results indicate the feasibility of accurate, non-invasive molecular subtype prediction using standard imaging protocols.