Selective Phase-Aware Training of nnU-Net for Robust Breast Cancer Segmentation in Multi-Center DCE-MRI

TL;DR

This paper introduces a phase-aware, quality-focused training approach for nnU-Net to improve breast cancer segmentation in multi-center DCE-MRI, emphasizing the importance of data quality and phase selection for robustness.

Contribution

The study proposes a selective, phase-aware training framework for nnU-Net that enhances segmentation robustness by analyzing data quality and variability across multiple datasets.

Findings

Training on high-quality, early phase images yields more stable results.

Including scans with motion artifacts and reduced contrast impairs segmentation performance.

Quality-aware data selection is crucial for reliable multi-center breast cancer segmentation.

Abstract

Breast cancer remains the most common cancer among women and is a leading cause of female mortality. Dynamic contrast-enhanced MRI (DCE-MRI) is a powerful imaging tool for evaluating breast tumors, yet the field lacks a standardized benchmark for analyzing treatment responses and guiding personalized care. We participated in the MAMA-MIA Challenge's Primary Tumor Segmentation task and this work presents a proposed selective, phase-aware training framework for the nnU-Net architecture, emphasizing quality-focused data selection to strengthen model robustness and generalization. We employed the No New Net (nnU-Net) framework with a selective training strategy that systematically analyzed the impact of image quality and center-specific variability on segmentation performance. Controlled experiments on the DUKE, NACT, ISPY1, and ISPY2 datasets revealed that including ISPY scans with motion artifacts and reduced contrast impaired segmentation performance, even with advanced preprocessing, such as contrast-limited adaptive histogram equalization (CLAHE). In contrast, training on DUKE and NACT data, which exhibited clearer contrast and fewer motion artifacts despite varying resolutions, with early phase images (0000-0002) provided more stable training conditions. Our results demonstrate the importance of phase-sensitive and quality-aware training strategies in achieving reliable segmentation performance in heterogeneous clinical datasets, highlighting the limitations of the expansion of naive datasets and motivating the need for future automation of quality-based data selection strategies.