发表机构
Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学梅维斯研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FME团队针对MAMA-MIA挑战赛，提出基于相减输入的nnU-Net集成肿瘤分割方法与基于病灶裁剪块的3D视频分类器集成pCR预测方法，两项任务均获第二名，为跨站点肿瘤分割及pCR预测提供了参考
AI 中文摘要
本文介绍了FME团队提交至MAMA-MIA挑战赛的方案，该挑战赛基于外部多国队列的治疗前动态对比增强乳腺MRI，评估原发肿瘤分割及病理完全缓解（pCR）预测任务。分割任务中，我们仅使用第一期对比后图像减去对比前图像的差值图，训练五折残差编码器nnU-Net集成模型，结合镜像测试时数据增强与最大连通分量过滤。pCR预测任务中，我们集成25个预训练3D视频分类器，这些分类器基于对比前及前两期对比后图像的以病灶为中心的裁剪块训练。FME团队在两项任务中均排名第二。分割方法的综合性能公平性得分为0.882，Dice系数为0.713，归一化豪斯多夫距离为0.099；pCR方法的综合得分为0.664，平衡准确率为0.541，均等赔率差异为0.212。结果表明，基于相减的输入及集成方法可在跨站点域偏移下实现鲁棒的肿瘤分割，而仅基于基线DCE-MRI的pCR预测仍存在局限。提交代码仓库见此httpsURL
英文摘要
We describe the submission of team FME to the MAMA-MIA Challenge, which evaluated primary tumor segmentation and prediction of pathological complete response (pCR) from pretreatment dynamic contrast-enhanced breast MRI on an external multi-country cohort. For segmentation, we trained a five-fold residual-encoder nnU-Net ensemble using only the first post-contrast minus pre-contrast image, combined with mirroring test-time augmentation and largest-connected-component filtering. For pCR prediction, we ensembled 25 pretrained 3D video classifiers trained on lesion-centred crops from the pre-contrast and first two post-contrast volumes. FME ranked second in both tasks. The segmentation method achieved a combined performance-fairness score of 0.882, with Dice 0.713 and normalized Hausdorff distance 0.099. The pCR method achieved a combined score of 0.664, balanced accuracy of 0.541, and equalized-odds disparity of 0.212. The results indicate that subtraction-based input and ensembling support robust tumor segmentation under cross-site domain shift, whereas pCR prediction from baseline DCE-MRI alone remains limited. For the submission repository, see https://github.com/FraunhoferMEVIS/MAMA-MIA-Challenge-FME
