Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision
This paper proposes a target-informed self-supervised pretraining and model-ensemble strategy that leverages unlabeled target-domain data to improve cross-device generalization of medical imaging AI. Applied to pediatric wrist fracture assessment using point-of-care ultrasound, the method achieves over 6% Dice improvement on the target domain, demonstrating a label-efficient and privacy-preserving approach.
Article intelligence
Key points
- Combines masked image modeling and contrastive learning for self-supervised pretraining without target-domain labels.
- Introduces a confidence-aware infusion head to adaptively integrate predictions from source and target branches.
- Validated on 318 images from 62 pediatric POCUS videos, achieving over 6% Dice improvement on target domain.
- Framework extendable to multi-center studies or federated learning settings.
Why it matters
This matters because combines masked image modeling and contrastive learning for self-supervised pretraining without target-domain labels.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.29122] Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision
[Submitted on 27 May 2026]
Title:Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision
View a PDF of the paper titled Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision, by Yuyue Zhou and 8 other authors
View PDF HTML (experimental)
Abstract:It is often desirable to generalize medical imaging AI models trained with dense annotations to data acquired from different ultrasound scanners or clinical sites; however, retraining these models with new annotations is often difficult and costly. We examine this challenge in pediatric wrist fracture assessment using point-of-care ultrasound (POCUS), where fractures are common and can be effectively triaged via ultrasound. AI has shown radiologist-level performance for fracture detection, often aided by high-quality bony structure segmentation. However, due to significant domain shifts, models perform poorly on data from other centers or probes, and obtaining segmentation labels across devices is impractical due to manual annotation effort and data privacy concerns. To address this, we propose a target-informed self-supervised pretraining and model-ensemble strategy. Specifically, our approach combines masked image modeling (MIM) and contrastive learning to learn target-domain structural representations without labels, and introduces a confidence-aware infusion head to adaptively integrate predictions. The source dataset, collected with a Philips Lumify probe, contained dense labels, while the target dataset, acquired with a TeleMED portable probe, was unlabeled. The datasets were kept strictly separate throughout the entire process. Our method used labeled source data for supervised training and leveraged target-domain pretraining to improve generalization. On 318 images from 62 pediatric POCUS videos, this approach significantly improved cross-device performance, achieving over 6% Dice improvement on the target domain versus the baseline. These results demonstrate a label-efficient and privacy-preserving approach for cross-device-robust ultrasound AI, offering a framework that can be extended to multi-center studies or federated learning setups.
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2605.29122 [cs.CV]
(or arXiv:2605.29122v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2605.29122
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yuyue Zhou [view email] [v1] Wed, 27 May 2026 21:29:31 UTC (699 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision, by Yuyue Zhou and 8 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)