DinoMUSE: A DINOv2-guided Framework for Unsupervised Lateral Motion Estimation in Ultrasound Elastography
Authors: Xiyao Meng, Xingyue Wei, Baihua Luo, Bo Peng, Jianwen Luo
Organizations: School of Biomedical Engineering, Tsinghua Medicine, Tsinghua University, Beijing 100084, China · School of Computer Science, Southwest Petroleum University, Chengdu, Sichuan 610000, China
Quasi-static ultrasound elastography (USE) is a non-invasive imaging method for assessing soft tissue mechanical properties. Limited by low resolution, low sampling frequency and lack of phase information in the lateral direction, accurate lateral motion estimation remains a critical bottleneck in USE. Existing methods mainly rely on local image matching and physical constraints (such as tissue incompressibility assumption and effective Poisson's ratio), which lack sufficient contextual information. We present DinoMUSE, a DINO-guided mixture-of-experts (MoE) framework for unsupervised lateral motion estimation in USE. DinoMUSE incorporates high-level visual representations learned by DINOv2 into the motion estimation network to provide global contextual guidance. To facilitate effective interaction between DINOv2 features and local matching features, an MoE-based feature-fusion module adaptively transforms and integrates the two representations. Evaluations against NCC, GLUE, RAFT, and sPICTURE on simulation and in-vivo breast datasets show that DinoMUSE substantially improves lateral estimation accuracy while maintaining competitive axial performance. Specifically, DinoMUSE reduces the mean square error (MSE) of lateral displacement and strain estimation by 60% and 65%, respectively, compared with a SOTA algorithm on the simulation dataset. For in-vivo breast data, DinoMUSE achieves axial strain SNR and CNR of 5.70 and 4.82, and lateral strain SNR and CNR of 4.61 and 2.23, compared to 4.11 and 3.32, and 4.57 and 2.13 for the best competing method, alongside improved lesion visualization. These findings indicate the potential of leveraging transferable visual representations and adaptive feature fusion to improve lateral motion estimation in USE. The code is available at xxxxxxxx.
Ultrasound imaging uses sound waves to visualize anatomy and function, with AI improving image reconstruction, diagnosis, measurement, and scan guidance.
Motion estimation in echocardiography is essential for quantitative assessment of cardiac function and myocardial mechanics, but remains challenging due to image artifacts, limited image information, speckle decorrelation, and the scarcity of ground-truth displacement fields. Anatomy-guided approaches can provide structural information, yet often rely on expert-labeled myocardial segmentations. We propose EchoDiST, a framework for unsupervised echocardiographic myocardial motion estimation that integrates self-distillation-based joint learning with a diffusion-conditioned motion estimation network. Here, unsupervised motion estimation refers to learning without ground-truth displacement fields. The self-distillation strategy jointly optimizes anatomical segmentation and myocardial motion estimation under limited anatomical annotations. Diffusion-based conditioning is used during training with stochastic perturbations, while inference requires only a single deterministic forward pass without iterative reverse-diffusion sampling. EchoDiST was evaluated on three echocardiographic datasets, including two external test datasets under cross-view and cross-dataset settings. Compared with seven representative learning-based methods, EchoDiST consistently improved anatomical alignment, myocardial strain assessment, and motion-derived functional and cardiac-phase assessment. These gains were statistically significant across the evaluated tasks and datasets. Overall, EchoDiST provides an effective approach for reliable myocardial motion estimation under limited anatomical supervision and supports downstream quantitative assessment of cardiac function.
Feiyue Qi, Xingyue Wei, Jianwen Luo
School of Biomedical Engineering, Tsinghua Medicine, Tsinghua University, Beijing, 100084, China
Ultrasound visual servoing is essential for autonomous robotic ultrasound, yet 6-DoF probe control from 2D B-mode images remains challenging due to limited and ambiguous out-of-plane motion cues. Existing methods typically rely on anatomical priors or handcrafted visual features, limiting their generalizability across imaging targets. Inspired by trackerless 3D ultrasound reconstruction, we propose Recon2Servo, a visual servoing framework that learns image-to-motion inference directly from B-mode images for 6-DoF probe control. A DINOv3 encoder with low-rank adaptation and a bidirectional relation module estimate the relative probe pose between current and target images to guide iterative closed-loop target-view alignment. The framework combines supervised relative-pose learning, reconstruction-guided closed-loop adaptation, and bounded residual pose correction to improve motion inference during servoing. Evaluations on a public dataset and an in-house dataset collected from 12 healthy volunteers using different ultrasound systems demonstrate its effectiveness in reconstructed-volume servoing. Additional real-robot demonstrations of target-view alignment and dynamic tracking on a human forearm are provided in the supplementary video: https://youtu.be/qwsOdI-GMYk.
Yameng Zhang, Pei Liu, Dianye Huang +5
Department of Mechanical Engineering, The University of Hong Kong, Hong Kong SAR. · Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong SAR. · School of Computation, Information and Technology, Technical University of Munich, Germany. +2
Ultrasound is the most widely used real-time imaging modality in clinical practice, yet per-frame video annotation remains a major bottleneck: expert labels are scarce and costly, and image appearance varies with speckle, shadowing, attenuation, and operator-dependent probe pose. This is especially limiting because clinically relevant information is often dynamic, from left-ventricular motion in echocardiography to muscle and bone kinematics in musculoskeletal imaging. Population atlases can amortize annotation cost by registering observations to a shared canonical coordinate system, but existing neural atlas methods mainly target single videos, small test-time image sets, or object-centric image collections. We introduce a cohort-scale neural atlas for ultrasound video: a single canonical chart with per-video Generative Latent Optimization embeddings, trained jointly over thousands of frames in DINOv3 feature space. Across five cardiac and musculoskeletal datasets with point landmarks and segmentation masks, our method learns coherent canonical templates and enables accurate atlas-space annotation transfer. On EchoNet-Dynamic and MSK-Bone, it supports single- and few-shot transfer with accuracy competitive with strong dense-correspondence baselines, while training in minutes on a single consumer GPU. The learned embeddings are interpretable: linear projections reveal structured cohort variation, image-decoder interpolation produces anatomically plausible intermediate frames, and test-time latent inversion reconstructs held-out frames through the atlas. These results suggest that cohort-scale neural atlases offer a practical, interpretable representation for reducing expert annotation burden in ultrasound video analysis.
Zhuorui Zhang, Roger Pallarès-López, Xuan Wu +2
Department of Mechanical Engineering, MIT · Institute for Medical Engineering and Science, MIT · 3MIT.nano Immersion Lab, MIT