DCE-MRI 中乳腺癌分类的特征空间引导
Feature Space Guidance for Breast Cancer Classification in DCE-MRI
浏览论文内容
中文总结 AI 辅助
针对 DCE-MRI 乳腺癌分类中协议差异和空间变异挑战，提出动态分析潜在表示、选择时间特征并利用分割预训练的框架，在 ODELIA 和 AMBL 数据集上显著优于基线，并获 MICCAI 2025 挑战赛冠军。
中文摘要 AI 辅助
动态对比增强乳腺 MRI（DCE-MRI）是乳腺癌检测的强大临床工具，提供高分辨率解剖细节以及丰富的时相对比信息。然而，高维 4D 输入、小病灶以及不同临床中心间异质的采集协议阻碍了健康、良性和恶性病例的稳健自动分类。为解决这些挑战，我们提出一个框架，动态分析潜在表示以适应特定协议的特征。通过减少混杂的背景摄取并补偿由可变形软组织引起的错位，缓解空间变异性。此外，利用跨时相潜在空间中的关系来选择最具信息量的时间特征，提高对特定协议时间变异性的鲁棒性。最后，通过大规模监督病灶分割预训练促进任务特定的判别性特征，这显著增强了下游微调。在 ODELIA 数据集上采用留一中心验证并在保留的 AMBL 队列上评估，所提出的框架显著优于微调的放射学基础模型和先前方法，与最强基线相比，平均 AUROC 提高了近 8 个百分点，平衡准确率提高了 4 个百分点。此外，我们的方法在 MICCAI ODELIA 乳腺 MRI 挑战赛 2025 中获得第一名，进一步证明了其在稳健乳腺癌分类中的有效性。我们在该 https URL 下公开发布了我们的代码库。
英文摘要
Dynamic contrast enhanced breast MRI (DCE-MRI) is a powerful clinical tool for breast cancer detection, providing high resolution anatomical detail together with rich temporal contrast information. However, high dimensional 4D inputs, small lesions, and heterogeneous acquisition protocols across clinical sites hinder robust automated classification of healthy, benign, and malignant cases. To address these challenges, we propose a framework that dynamically analyzes latent representations to adapt to protocol-specific characteristics. Spatial variability is mitigated by reducing confounding background uptake and compensating for misalignment caused by deformable soft tissue. Additionally, relationships in the latent space across phases are leveraged to select the most informative temporal features, improving robustness to protocol-specific temporal variability. Finally, task specific discriminative features are promoted through large scale supervised lesion segmentation pretraining, which substantially enhances downstream finetuning. Evaluated under leave-one-center-out validation on the ODELIA dataset and the held-out AMBL cohort, the proposed framework substantially outperforms finetuned radiology foundation models and prior methods, improving mean AUROC by nearly 8 points and balanced accuracy by 4 points over the strongest baseline. Additionally, our method achieved first place in the MICCAI ODELIA Breast MRI Challenge 2025, further demonstrating its effectiveness for robust breast cancer classification. We publicly release our codebase under https://github.com/MIC-DKFZ/CURIAtor.
