STORK: Spatio-Temporal Observation of uterine contRactions via neural networKs
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.
ProofPaper ↗
Key points
- Uterine contractions in fetal MRI are typically identified manually and discarded, limiting insights into contraction dynamics.
- STORK factorizes 3D spatio-temporal convolutions into parallel branches across temporal hyperplanes to capture coherent tissue motion without the cost of full 4D convolutions.
- 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.
Sources (1)
- [1]STORK: Spatio-Temporal Observation of uterine contRactions via neural networKsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 07:44 AM
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.
Uterine contractions in fetal MRI are typically identified manually and discarded, limiting insights into contraction dynamics.
Extractive summary: sentences quoted from the sources.