Dual Co-Train: Cross-Dataset Ultrasound Tongue Segmentation Under Extreme Data Scarcity

Alisher Myrgyyassov; Zhen Song; Bruce Xiao Wang; Yu Sun; Min Ney Wong; Yihao Zhou; Yongping Zheng

cs.CVAug 18, 2026

Dual Co-Train: Cross-Dataset Ultrasound Tongue Segmentation Under Extreme Data Scarcity

Authors: Alisher Myrgyyassov, Zhen Song, Bruce Xiao Wang, Yu Sun, Min Ney Wong, Yihao Zhou, Yongping Zheng

Organizations: Department of Biomedical Engineering Hong Kong Polytechnic University Hong Kong, China · Department of English and Communication Hong Kong Polytechnic University Hong Kong, China · Department of Language Science and Technology Hong Kong Polytechnic University Hong Kong, China · Department of Biomedical Engineering, Research Institute for Smart Ageing Hong Kong Polytechnic University Hong Kong, China

Abstract

Ultrasound tongue contour segmentation remains challenging under cross-dataset domain shift, where limited annotations, probe variability, and acquisition noise often degrade model generalization. We present a source-free domain adaptation framework for robust ultrasound tongue segmentation built on a lightweight UltraUNet backbone. Starting from a checkpoint pretrained on only five labeled source images, simulating an underfitted constrained source model, the proposed method adapts to a fully-unlabeled target domain by iteratively refining pseudo-labels, filtering unreliable masks with a contour-based quality-control module, and generating target-style synthetic image-mask pairs through a segmentation-guided conditional GAN. The student model is then trained on a mixture of clean pseudo-labeled target images, noisy pseudo-labels with consistency regularization, and synthetic samples, enabling closed-loop adaptation without access to source data. We evaluate the method on 12 source-target transfer pairs across eight ultrasound tongue imaging datasets, and conduct source-size scaling experiments and ablation studies. Across all comparisons, the proposed framework improves segmentation overlap and contour accuracy over the baselines, including supervised ones. These results suggest that task-specific pseudo-label refinement and synthetic target-style augmentation can substantially improve source-free adaptation for ultrasound tongue imaging.

Figures & tables

Figure 1: Two-dimensional embedding of image-level features from the eight ultrasound tongue imaging datasets extracted from the bottleneck of the pretrained UltraUNet, visualized using t-SNE. Each point corresponds to one 224 $\times$ 224 image, and colors indicate dataset identity.

Dataset	FG%	Speckle SNR	Norm. Grad.	Norm. Lap.
MTID	58.2	1.534	1.040	0.499
CTID	60.1	1.531	1.023	0.279
UXTD	52.9	1.010	2.069	1.144
UXSSD	52.1	1.007	2.063	1.114
TaL1	21.1	1.015	2.934	2.048
UPX	54.0	0.902	1.611	0.696

Table 1: Quantitative image-quality metrics for each dataset.

Dataset	A1 vs A2	A1 vs S	A2 vs S
Cleft	2.583 $\pm$ 3.517	3.151 $\pm$ 2.334	3.112 $\pm$ 3.660
CTID	1.969 $\pm$ 1.456	1.518 $\pm$ 0.676	1.541 $\pm$ 0.272
MTID	2.225 $\pm$ 2.347	2.160 $\pm$ 2.989	1.802 $\pm$ 1.084
TaL1	3.861 $\pm$ 2.684	3.571 $\pm$ 2.607	3.682 $\pm$ 2.674
UPX	1.526 $\pm$ 0.828	1.182 $\pm$ 0.286	1.529 $\pm$ 0.120
UX2020	2.686 $\pm$ 1.858	2.418 $\pm$ 1.325	2.310 $\pm$ 0.852

Table 2: Inter-rater MSD (in px) across the eight ultrasound tongue imaging datasets. A1 denotes the primary annotator, A2 denotes the secondary annotator, and S denotes the clinical sonographer. Values are reported as mean

\pm

standard deviation.

Figure 2: Detailed fine-tuning procedure. Teacher-generated pseudo-masks on unlabeled target images are separated into clean and noisy subsets by a rule-based quality-control module. Clean pseudo-labels and GAN-synthesized image-mask pairs are used for supervised segmentation training, while noisy pseudo-labels are handled through Mean Teacher consistency regularization. The GAN is periodically fine-tuned using updated pseudo-masks to remain aligned with the evolving target-domain mask distribution.

Figure 3: Mask augmentation pipeline. The original image is segmented to extract the input mask, which is then passed through the augmentation pipeline to generate new synthetic samples through deformation, moving, and rotation.

Figure 4: Comparison of synthetic and nearest real images generated using pretrained GANs from 12 transfer scenarios. (Top row) Aligned synthetic images generated from identical input masks. (Bottom row) The nearest corresponding real images, retrieved based on pixel value similarity (L2 distance).

Figure 5: Representative qualitative comparison between 5 methodologies. Each column represents a dataset, and the rows are as follows: (1) original image, (2) human annotations overlay, (3) the proposed Dual Co-Train framework, (4) SFM baseline, (5) EMA teacher baseline, (6) SHOT baseline, (7) checkpoint trained on the target dataset

No.	Source	Target	Ours	SHOT	EMA	FSM	UPL	AIF
1	MTID	TaL1	0.790	0.768	0.793	0.564	0.752	0.746
2	MTID	UX2020	0.811	0.755	0.758	0.623	0.765	0.766
3	MTID	UXTD	0.782	0.726	0.767	0.666	0.714	0.735
4	CTID	Cleft	0.747	0.705	0.708	0.599	0.682	0.591
5	CTID	UXSSD	0.801	0.771	0.776	0.712	0.748	0.731
6	UPX	UXTD	0.802	0.771	0.778	0.702	0.723	0.727

Table 3: Dice score comparison across the 12 source-to-target transfer pairs. Ours denotes the full dual co-training method, SHOT denotes the SHOT-style pseudo-label baseline, EMA denotes the EMA teacher baseline, FSM denotes the Fourier Style Mining baseline, UPL denotes the Uncertainty-aware Pseudo Label Guided baseline, and AIF denotes the Autonomous Information Filter-driven baseline.

No.	Source	Target	Ours	SHOT	EMA	FSM	UPL	AIF
1	MTID	TaL1	1.902	2.136	1.810	9.117	2.145	2.018
2	MTID	UX2020	1.528	2.223	2.198	4.592	2.206	1.907
3	MTID	UXTD	2.453	3.188	2.486	3.413	5.372	3.683
4	CTID	Cleft	2.193	2.508	2.552	4.222	3.417	6.743
5	CTID	UXSSD	1.750	2.086	2.164	2.917	2.037	1.928
6	UPX	UXTD	2.131	2.613	2.465	2.910	2.920	2.549

Table 4: MSD (px) comparison across the 12 source-to-target transfer pairs. Ours denotes the full dual co-training method, SHOT denotes the SHOT-style pseudo-label baseline, EMA denotes the EMA teacher baseline, FSM denotes the Fourier Style Mining baseline, UPL denotes the Uncertainty-aware Pseudo Label Guided baseline, and AIF denotes the Autonomous Information Filter-driven baseline.

			Dice $\uparrow$				MSD $\downarrow$
No.	Source	Target	Full	EMA	GAN FT	QC	Full	EMA	GAN FT	QC
1	MTID	TaL1	0.790	0.786	0.789	0.780	1.902	1.918	1.949	2.134
2	MTID	UX2020	0.811	0.812	0.807	0.733	1.528	1.524	1.536	2.619
3	MTID	UXTD	0.782	0.777	0.779	0.763	2.453	2.650	2.517	2.266
4	CTID	Cleft	0.747	0.740	0.734	0.721	2.193	2.268	2.407	2.281
5	CTID	UXSSD	0.801	0.800	0.793	0.754	1.750	1.859	1.890	2.156

Table 5: Ablation study on the proposed dual co-training framework. Full denotes the full method, "EMA" removes the EMA teacher, "GAN FT" removes periodic GAN refinement, and "QC" removes pseudo-label quality control.

Figure 6: Source-size scaling comparison between the dual co-training framework and the plain pretrained checkpoint across four transfer configurations. Dice (top) and MSD (bottom) are reported as a function of training-set size $N$ , averaged over three random seeds; shaded bands denote standard deviation. The dual co-training framework saturates at substantially smaller $N$ and exhibits lower variance across seeds than the baseline.

Ultrasound Image Segmentation

Ultrasound image segmentation delineates organs, lesions, and other structures in ultrasound scans for measurement, diagnosis, and image-guided care.

See all 73 papers

Tell2Adapt: A Unified Framework for Source Free Unsupervised Domain Adaptation via Vision Foundation Model
Mar 5, 2026Yulong Shi, Shijie Li, Ziyi Li +1Source-Free Domain Adaptation Medical Image Segmentation
College of Medicine and Biological Information Engineering, Northeastern University · Engineering Research Center of Medical Imaging and Intelligent Analysis, Ministry of Education · Key Laboratory of Medical Image Computing, Ministry of Education, Northeastern University
SymmAdapt: Symmetrical Flow Matching for Source-Free Domain Adaptation in Medical Image Segmentation
Aug 23, 2026Tal Grossman, Noa Cahan, Hayit GreenspanSource-Free Domain Adaptation Medical Image Segmentation
Faculty of Engineering, Tel Aviv University, Tel Aviv, Israel
Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision
May 27, 2026Yuyue Zhou, Shrimanti Ghosh, Michael +7Ultrasound Image Segmentation Unsupervised Domain Adaptation
Kai Yue · Department of Radiology and Diagnostic Imaging, University of Alberta, 8303 112 St NW, Edmonton, T6G 2T4, AB, Canada

Mar 5, 2026J/K move · Enter open · S save

Tell2Adapt: A Unified Framework for Source Free Unsupervised Domain Adaptation via Vision Foundation Model

Yulong Shi, Shijie Li, Ziyi Li, Lin Qi

College of Medicine and Biological Information Engineering, Northeastern University · Engineering Research Center of Medical Imaging and Intelligent Analysis, Ministry of Education · Key Laboratory of Medical Image Computing, Ministry of Education, Northeastern University

Source-Free Domain Adaptation Medical Image Segmentation Vision Foundation Model Adaptation

Open paper AskPDF arXiv

Source Free Unsupervised Domain Adaptation (SFUDA) is critical for deploying deep learning models across diverse clinical settings. However, existing methods are typically designed for low-gap, specific domain shifts and cannot generalize into a unified, multi-modalities, and multi-target framework, which presents a major barrier to real-world application. To overcome this issue, we introduce Tell2Adapt, a novel SFUDA framework that harnesses the vast, generalizable knowledge of the Vision Foundation Model (VFM). Our approach ensures high-fidelity VFM prompts through Context-Aware Prompts Regularization (CAPR), which robustly translates varied text prompts into canonical instructions. This enables the generation of high-quality pseudo-labels for efficiently adapting the lightweight student model to target domain. To guarantee clinical reliability, the framework incorporates Visual Plausibility Refinement (VPR), which leverages the VFM's anatomical knowledge to re-ground the adapted model's predictions in target image's low-level visual features, effectively removing noise and false positives. We conduct one of the most extensive SFUDA evaluations to date, validating our framework across 10 domain adaptation directions and 22 anatomical targets, including brain, cardiac, polyp, and abdominal targets. Our results demonstrate that Tell2Adapt consistently outperforms existing approaches, achieving SOTA for a unified SFUDA framework in medical image segmentation. Code are avaliable at https://github.com/derekshiii/Tell2Adapt.

Abstract

Ultrasound Image Segmentation

Explore similar work

Tell2Adapt: A Unified Framework for Source Free Unsupervised Domain Adaptation via Vision Foundation Model

SymmAdapt: Symmetrical Flow Matching for Source-Free Domain Adaptation in Medical Image Segmentation

Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision