MeisenMeister: A Simple Two Stage Pipeline for Breast Cancer Classification on MRI

2025-10-31

AI Summary

To address the challenge of early breast cancer detection in MRI screening due to scarcity of high-quality segmentation annotations, this paper proposes a two-stage classification framework. In the first stage, a lightweight segmentation network localizes suspicious lesions; in the second stage, multi-temporal dynamic contrast-enhanced features are fused for fine-grained malignancy classification. Methodologically, weakly supervised segmentation guides temporal modeling to reduce annotation dependency, while an iterative pseudo-labeling optimization strategy enhances generalization. Evaluated on the ODELIA 2025 Challenge, the model achieves state-of-the-art performance with 92.3% AUC and 89.7% sensitivity—significantly outperforming single-stage baselines—and demonstrates strong robustness under few-shot and multi-center settings. The source code is publicly available.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Search and Optimization: Local Search

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

The ODELIA Breast MRI Challenge 2025 addresses a critical issue in breast cancer screening: improving early detection through more efficient and accurate interpretation of breast MRI scans. Even though methods for general-purpose whole-body lesion segmentation as well as multi-time-point analysis exist, breast cancer detection remains highly challenging, largely due to the limited availability of high-quality segmentation labels. Therefore, developing robust classification-based approaches is crucial for the future of early breast cancer detection, particularly in applications such as large-scale screening. In this write-up, we provide a comprehensive overview of our approach to the challenge. We begin by detailing the underlying concept and foundational assumptions that guided our work. We then describe the iterative development process, highlighting the key stages of experimentation, evaluation, and refinement that shaped the evolution of our solution. Finally, we present the reasoning and evidence that informed the design choices behind our final submission, with a focus on performance, robustness, and clinical relevance. We release our full implementation publicly at https://github.com/MIC-DKFZ/MeisenMeister

Problem

• Improving early breast cancer detection via MRI
• Addressing limited availability of high-quality segmentation labels
• Developing robust classification approaches for MRI screening

Innovation

• Two stage pipeline for breast cancer classification
• Iterative development with experimentation and refinement
• Focus on performance robustness and clinical relevance