发表机构
Leibniz University Hannover（莱布尼茨汉诺威大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
STORK提出一种弱监督多实例学习模型，利用动态胎儿MRI序列自动检测子宫收缩，通过分解3D卷积和均值池化实现高效训练，在约700个序列上达到95.0%的AUROC，显著优于基线，为子宫行为分析提供自动化工具。
AI 中文摘要
胎儿MRI中的子宫收缩通常被手动识别并丢弃，这限制了对收缩动力学的洞察。我们将子宫收缩活动检测（UCAD）形式化为一个弱监督学习问题，并引入STORK，一种仅在粗略的序列级标签上训练的动态MRI序列的多实例学习模型。STORK将三维时空卷积分解为跨时间超平面的并行分支，以在不增加完整4D卷积成本的情况下捕捉连贯的组织运动。结合强度和Demons估计位移场的逐帧嵌入，通过线性均值池化头进行聚合。这确保了可以在没有逐帧训练监督的情况下事后恢复逐帧收缩分数。在大约700个多供应商动态胎儿MRI序列上评估，STORK实现了序列级AUROC为95.0%和AUPRC为94.6%，显著优于3D ResNet和ConvNeXt基线。Grad-CAM分析表明，该模型利用了超出胎盘进入子宫组织的预测特征，为子宫行为的更丰富表型分析提供了自动化工具。
英文摘要
Uterine contractions in fetal MRI are typically identified manually and discarded, limiting insights into contraction dynamics. We formalize Uterine Contractile Activity Detection (UCAD) as a weakly-supervised learning problem and introduce STORK, a multi-instance learning model trained on dynamic MRI series using only coarse, series-level labels. STORK factorizes 3D spatio-temporal convolutions into parallel branches across temporal hyperplanes to capture coherent tissue motion without the cost of full 4D convolutions. Per-frame embeddings, combining intensity and Demons-estimated displacement fields, are aggregated by a linear mean-pooling head. This ensures that frame-level contraction scores can be recovered post-hoc without frame-level training supervision. Evaluated on around 700 multi-vendor dynamic fetal MRI series, STORK achieves a series-level AUROC of 95.0% and AUPRC of 94.6%, substantially outperforming 3D ResNet and ConvNeXt baselines. Grad-CAM analysis suggests that the model draws on predictive features extending beyond the placenta into the uterine tissue, offering an automated tool for richer phenotyping of uterine behavior.
CommentsAccepted at the PIPPI Workshop at MICCAI 2026 and will appear in the workshop proceedings (Springer)
