UNIVERS: Learning UNIversal Voxel-wise Embedding via Randomized Synthesis for generalizable one-shot landmark localization

Derong Yu; Qingsong Zhao; Yanbing Yue; Yikai Li; Zhi Zhang; Guoyan Zheng

cs.CVOct 21, 2026

UNIVERS: Learning UNIversal Voxel-wise Embedding via Randomized Synthesis for generalizable one-shot landmark localization

Authors: Derong Yu, Qingsong Zhao, Yanbing Yue, Yikai Li, Zhi Zhang, Guoyan Zheng

Organizations: Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China. · Department of Cardiology, Shanghai General Hospital (originally named Shanghai First People’s Hospital), Shanghai Jiao Tong University School of Medicine, Shanghai 200080, China.

Abstract

One-shot landmark localization in volume scans with varying fields of view (FOVs) is challenging. While existing self-supervised learning methods have shown promising performance, they rely on contrastive learning built upon augmented views of the same image, which inherently limits their generalization in cross-modality scenarios. This motivates research on cross-modality embedding learning using paired multi-modality images. However, existing methods suffer from not only limited training data, but also the requirement of multi-stage iterative training. To address these limitations, we propose UNIVERS, an end-to-end trainable framework that learns UNIversal Voxel-wise Embedding via Randomized Synthesis. Our framework leverages diverse pseudo-data synthesized from organ shape templates, with randomization applied to semantic layout, visual appearance, FOV, and spatial pose. Coupled with cross-domain discriminative voxel-wise contrastive learning, this domain randomization strategy forces the network to disregard domain-specific biases and learn features that are robust against variations in imaging contrast, resolution, and spatial context. Consequently, the trained model enables one-shot landmark localization in multi-modality volume scans with arbitrary FOVs. In this study, the efficacy of the proposed method is demonstrated by applying it to the task of localizing the adrenal glands, which are paired, small, and irregular endocrine organs. In particular, comprehensive experiments are conducted on three challenging adrenal gland datasets. The experimental results demonstrate that UNIVERS consistently outperforms the state-of-the-art (SOTA) one-shot landmark localization approaches, with particularly prominent advantages in cross-modality scenarios. The source code is publicly available at https://github.com/Kendra9999/UNIVERS.

Figures & tables

Fig. 1: A schematic overview of UNIVERS. (a) We construct an image pair database and a patch quadruplet database from shape templates. (b) UNIVERS consists of a shared CNN encoder with a Domain-invariant Discriminative (DD) decoder and a Domain-invariant Semantic (DS) decoder. During training, patch quadruplets are randomly sampled to train the DD decoder via a Cross-domain Discriminative Voxel-wise Contrastive (CDVC) loss, while image pairs are randomly sampled to optimize the DS decoder via a Cross-domain Prototypical Semantic Contrastive (CPSC) loss. (c) During inference, UNIVERS can generate Domain-invariant Voxel-wise (DV) embeddings for multi-modality volumes with arbitrary FOVs. Embeddings are reduced to 3 dimensions via PCA and visualized as RGB images. RGA : Random Geometric Augmentation. Embed. : Embedding.

Fig. 2: Illustration of the coarse-to-fine adrenal gland localization framework built upon a single frozen UNIVERS network. Adrenal gland centers are shown as projections of 3D points along the frontal plane for visualization purposes only. Embeddings are reduced to 3 dimensions via PCA and visualized as RGB images. Embed.: Embedding.

Fig. 3: Visualization of the single support sample for all three one-shot settings. The left two columns respectively display transverse and frontal slices passing through the GT right adrenal gland center points (red circles), while the right two columns show corresponding slices for the left adrenal gland center points (green circles).

Fig. 4: Visual comparison of intra-dataset one-shot adrenal gland localization. The left two columns respectively display transverse and frontal slices passing through the GT or predicted right adrenal gland center points (red circles), while the right two columns show corresponding slices for the left adrenal gland center points (green circles).

Method	${\rm SDR}_{\rm 10}$	${\rm SDR}_{\rm 20}$	${\rm MED}$	$p$ -value
Method	(%) $\uparrow$	(%) $\uparrow$	(mm) $\downarrow$	$p$ -value
Reference Baselines
Lower Bound	55.80	75.45	31.63 $\pm$ 65.29	-
Upper Bound	98.66	99.55	3.04 $\pm$ 13.26	-
One-shot Methods
Affine [ 32 ]	4.91	36.16	35.37 $\pm$ 31.19	$<$ 0.001

TABLE I: Quantitative comparison of intra-dataset one-shot adrenal gland localization. Bold indicates the best results, and underline indicates the second-best results.

\uparrow

indicates higher is better,

\downarrow

indicates lower is better.

Fig. 5: Visual comparison of cross-dataset intra-modality one-shot adrenal gland localization. The left two columns respectively display transverse and frontal slices passing through the GT or predicted right adrenal gland center points (red circles), while the right two columns show those slices for the left adrenal gland center points (green circles).

Method	${\rm SDR}_{\rm 10}$	${\rm SDR}_{\rm 20}$	${\rm MED}$	$p$ -value
Method	(%) $\uparrow$	(%) $\uparrow$	(mm) $\downarrow$	$p$ -value
Reference Baselines
Lower Bound	0.00	0.00	351.56 $\pm$ 106.53	-
Upper Bound	96.59	98.86	3.70 $\pm$ 3.36	-
One-shot Methods
Affine [ 32 ]	9.85	43.18	26.46 $\pm$ 20.89	$<$ 0.001

TABLE II: Quantitative comparison of cross-dataset intra-modality one-shot adrenal gland localization. Bold indicates the best results, and underline indicates the second-best results.

\uparrow

indicates higher is better,

\downarrow

indicates lower is better.

Fig. 6: Visual comparison of cross-dataset cross-modality one-shot adrenal gland localization. The left two columns respectively display transverse and frontal slices passing through the GT or predicted right adrenal gland center points (red circles), while the right two columns show those slices for the left adrenal gland center points (green circles).

Method	${\rm SDR}_{\rm 10}$	${\rm SDR}_{\rm 20}$	${\rm MED}$	$p$ -value
Method	(%) $\uparrow$	(%) $\uparrow$	(mm) $\downarrow$	$p$ -value
Reference Baselines
Lower Bound	0.00	0.22	120.70 $\pm$ 46.76	-
Upper Bound	88.96	97.19	5.56 $\pm$ 6.05	-
One-shot Methods
Affine [ 32 ]	3.46	26.84	30.30 $\pm$ 15.48	$<$ 0.001

TABLE III: Quantitative comparison of cross-dataset cross-modality one-shot adrenal gland localization. Bold indicates the best results, and underline indicates the second-best results.

\uparrow

indicates higher is better,

\downarrow

indicates lower is better.

Model Configuration	Intra-dataset		Cross-dataset Intra-modality		Cross-dataset Cross-modality
Model Configuration	${\rm SDR}_{\rm 10}$ (%) $\uparrow$	${\rm MED}$ (mm) $\downarrow$	${\rm SDR}_{\rm 10}$ (%) $\uparrow$	${\rm MED}$ (mm) $\downarrow$	${\rm SDR}_{\rm 10}$ (%) $\uparrow$	${\rm MED}$ (mm) $\downarrow$
Full Model (Ours)	87.50	6.16 $\pm$ 3.73	78.03	7.46 $\pm$ 4.50	64.72	9.65 $\pm$ 7.61
(a) Ablation on the Pseudo-patch Quadruplet Generation Strategy
Cropping-only	76.34	8.20 $\pm$ 7.43	61.74	11.35 $\pm$ 11.20	58.44	12.34 $\pm$ 11.88
Geometric-augmentation-only	83.48	7.38 $\pm$ 8.17	61.74	12.15 $\pm$ 15.12	54.98	11.03 $\pm$ 8.44
Cropping-and-geometric-augmentation	85.71	6.64 $\pm$ 5.59	68.56	9.70 $\pm$ 9.68	55.84	11.41 $\pm$ 9.12

TABLE IV: Quantitative results of the ablation study on all three one-shot settings. Bold indicates the best results.

\uparrow

indicates higher is better,

\downarrow

indicates lower is better. ”w/o”: without.

Anatomical Landmark Detection

See all 18 papers

Mar 17, 2025

UniReg: Conditional Unified Model for Medical Image Registration

Learning-based medical image registration has matched the accuracy of conventional methods while offering superior computational efficiency. However, existing approaches suffer from poor generalization across diverse clinical scenarios, requiring the laborious development of multiple isolated networks for specific registration tasks, e.g., inter-/intra-subject registration or anatomical region-specific alignment, leading to cumbersome development pipelines. To overcome this limitation, we propose UniReg, the first conditional unified model for multi-scenario medical image registration, which combines the precision advantages of task-specific learning methods with the generalization of traditional optimization methods. Our key innovation is a unified registration framework that adaptively estimates deformation fields conditioned on: (1) anatomical structure priors, (2) registration type constraints (inter/intra-subject), and (3) instance-specific features, enabling effective alignment across heterogeneous CT and MR registration scenarios within a single model. Through comprehensive experiments on multiple CT/MR registration datasets, UniReg achieves superior average registration accuracy compared with current state-of-the-art learning-based methods while exhibiting strong cross-scenario generalization. Moreover, by replacing multiple isolated task-specific models with a compact unified model, UniReg substantially reduces the overall training burden in terms of total training cost and model redundancy.

Zi Li, Jianpeng Zhang, Tai Ma +7

Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong SAR, China · DAMO Academy, Alibaba Group · The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China +1

Healthcare Medical Image Registration Deformable Image Registration

Ask PDF

Mar 3, 2022

Structure-Guided Self-Supervised Matching for One-Shot Medical Landmark Detection

Medical landmark detection usually requires accurate expert annotations, which are laborious and difficult to scale across anatomical regions. In this work, we study an extreme annotation-efficient setting where only a single annotated template image is available. We propose SGB-Match, a structure-guided coarse-to-fine self-supervised matching framework for one-shot medical landmark detection. The framework first learns dense anatomical correspondence from unlabeled augmented image pairs, and then transfers the landmark definition from the annotated template to each target image through feature matching. Different from standard contrastive correspondence learning, where negative candidates are penalized by a structure-agnostic rule, we introduce a structure-guided bias into the contrastive objective. The bias is constructed from relative distance and edge-aware anatomical cues, and explicitly reweights the negative gradients: nearby structure-relevant candidates are weakly repelled, while distant or structure-irrelevant negatives are strongly suppressed. As a result, the learned feature space better preserves local anatomical structures around template landmarks and reduces confusing responses from repeated textures. We further adopt a global-to-local design, where a global encoder provides coarse landmark localization and a local encoder refines the prediction in a cropped region. Extensive experiments on four 2D radiological landmark datasets demonstrate that SGB-Match achieves strong one-shot performance across both public and newly collected datasets and consistently benefits from both structure-guided bias and two-stage refinement.

Qingsong Yao, Zhen Huang, Ao Wang +4

Soochow School of Artificial Intelligence Renmin University of China · Department of Computer Science University of Science and Technology of China · School of Biomedical Engineering University of Science and Technology of China +3

Few-Shot Learning Image Matching Local Feature Matching Self-Supervised Learning Medical Image Representation Learning Medical Image Localization+1

Ask PDF

Aug 10, 2026

Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction

Accurate landmark localization in medical images is a fundamental step for quantitative clinical measurement and downstream analysis. Existing localization methods have advanced, among which multi-stage refinement is a superior solution. Although this strategy mitigates the anatomical ambiguity inherent in single-stage global predictions, its high computational cost limits practical applicability. In this work, we propose a parameter-economic model, PPOC-LL, which leverages Prototype learning-based Progressive Offset Correction for Landmark Localization. Our contribution is three-fold. First, to drive coarse-to-fine landmark optimization, we introduce a multi-scale dynamic perception strategy for patch-level feature pyramid modeling. Second, to effectively handle anatomically similar patterns, we design a similarity-driven prototype learning mechanism that captures informative local semantics for robust offset prediction. Last, to stabilize the model learning and improve the overall performance, we incorporate a novel error-aware reliability regularization via tolerance-based balancing. We collected a large validation cohort, including two public and one private datasets spanning X-ray and ultrasound modalities, covering cephalometric, symphysis-fetal head, and fetal heart landmarks. Extensive experiments demonstrate that PPOC-LL achieves satisfactory performance with a favorable trade-off between accuracy and model complexity.

Jingxian Xu, Yuhao Huang, Rusi Chen +2

Medical Ultrasound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, China · Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong, China · Boston Children’s Hospital, Harvard Medical School, Boston, USA +3

Prototype Learning Medical Image Localization Anatomical Landmark Detection

Ask PDF

Abstract

Anatomical Landmark Detection

Explore similar work

UniReg: Conditional Unified Model for Medical Image Registration

Structure-Guided Self-Supervised Matching for One-Shot Medical Landmark Detection

Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction