# WASP: Weakly Aligned Spatiotemporal Pairs for Fetal Brain MRI-Ultrasound Learning

arXiv: https://arxiv.org/abs/2610.04601 · HTML: https://mlsanity.com/paper/2610.04601/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 54 references that are in the map.
- First posted on arXiv 3 Oct 2026.

## Builds on (most cited first, 20 of 20)

- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Optimal Transport for Domain Adaptation](https://mlsanity.com/paper/1507.00504/) (2015)
- [Correlation Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1612.01939/) (2016)
- [Gromov-Wasserstein Alignment of Word Embedding Spaces](https://mlsanity.com/paper/1809.00013/) (2018)
- [BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at once](https://mlsanity.com/paper/2405.12971/) (2024)
- [Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision](https://mlsanity.com/paper/2310.18689/) (2023)
- [USFM: A Universal Ultrasound Foundation Model Generalized to Tasks and Organs towards Label Efficient Image Analysis](https://mlsanity.com/paper/2401.00153/) (2023)
- [Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss](https://mlsanity.com/paper/1804.10916/) (2018)
- [FetalCLIP: A Visual-Language Foundation Model for Fetal Ultrasound Image Analysis](https://mlsanity.com/paper/2502.14807/) (2025)
- [Self-Supervised Ultrasound to MRI Fetal Brain Image Synthesis](https://mlsanity.com/paper/2008.08698/) (2020)
- [MRI-CORE: A Foundation Model for Magnetic Resonance Imaging](https://mlsanity.com/paper/2506.12186/) (2025)
- [AutoFB: Automating Fetal Biometry Estimation from Standard Ultrasound Planes](https://mlsanity.com/paper/2107.05255/) (2021)
- [A Fully Open and Generalizable Foundation Model for Ultrasound Clinical Applications](https://mlsanity.com/paper/2509.11752/) (2025)
- [Unified Cross-Modal Medical Image Synthesis with Hierarchical Mixture of Product-of-Experts](https://mlsanity.com/paper/2410.19378/) (2024)
- [General Methods Make Great Domain-specific Foundation Models: A Case-study on Fetal Ultrasound](https://mlsanity.com/paper/2506.19552/) (2025)
- [Advances in Automated Fetal Brain MRI Segmentation and Biometry: Insights from the FeTA 2024 Challenge](https://mlsanity.com/paper/2505.02784/) (2025)
- [Translation of Fetal Brain Ultrasound Images into Pseudo-MRI Images using Artificial Intelligence](https://mlsanity.com/paper/2504.02408/) (2025)
- [A multi-centre, multi-device benchmark dataset for landmark-based comprehensive fetal biometry](https://mlsanity.com/paper/2512.16710/) (2025)
- [The 4D Human Embryonic Brain Atlas: spatiotemporal atlas generation for rapid anatomical changes](https://mlsanity.com/paper/2503.07177/) (2025)

## Abstract (arXiv)

Magnetic Resonance Imaging (MRI) is widely regarded as the optimal sensor for fetal brain analysis due to its superior soft-tissue contrast and anatomical detail. However, its high cost and operational burden make it invasive and difficult to obtain at scale. Ultrasound (US), in contrast, is cheap, safe, and routinely acquired, and as a result it has produced substantially larger datasets and a growing ecosystem of pretrained models. This asymmetry raises a natural question: Can we teach a US-only model to understand fetal MRI from only a limited set of examples? The standard recipe, training a foundation model on subject-to-subject paired MRI-US scans, is not viable since no such paired fetal dataset is publicly available. In this paper we address this gap with Weakly Aligned Spatiotemporal Pairs (WASP), a framework that formulates cross-modal correspondence as an entropic Optimal Transport problem driven by clinical metadata, in particular Gestational Age (GA) and diagnostic planes, enabling the fitting of a lightweight alignment module that lifts MRI representations into the US latent space, without fine-tuning the backbone. Empirically, WASP yields its largest gains when MRI is unseen by the model during pretraining (on USFM, GA estimation error drops from 21.9 to 17.4 days and standard plane classification accuracy climbs from 61.9% to 69.0%), while providing smaller, backbone-dependent refinements for backbones pretrained on both modalities (e.g., BioMedParse GA estimation error from 6.5 to 6.0 days and SAM-Med2d plane accuracy from 83.3% to 88.1%). Code is available at https://github.com/miccunifi/WASP.