Aug 2026· Nan fang yi ke da xue xue bao = Journal of Southern Medical University· Vol 46 8, pp.
1967-1980
· 0 citations
Medicine
TL;DR
The proposed rigid motion artifact correction algorithm demonstrates good performance in estimating motion trajectories and compensating for image artifacts, thus providing a viable and robust solution for suppressing rigid motion artifacts in clinical CBCT imaging.
PURPOSE
Motion artifacts remain a major challenge in applying multi-shot 2D imaging to motion prone patient populations. Through-plane motion is especially problematic, where the lack of encoding cannot be easily recovered, even using deep-learning (DL)-regularized reconstruction. We demonstrate the benefits of combining prospective and retrospective motion correction, where the Scout Accelerated Motion Estimation and Reduction (SAMER) technique is utilized for on-the-fly motion estimation with field-of-view (FoV) updates along with retrospective correction of potential residual motion.
METHODS
Four prospective motion correction (pMoCo) strategies were implemented within a custom 2D turbo-spin-echo (TSE) SAMER enabled sequence. They were evaluated in vivo across representative subject motion, with associated simulations to characterize artifacts and the correction performance. In addition, motion trajectories measured during inpatient clinical exams were used to further demonstrate the robustness of the combined motion correction approach.
RESULTS
Prospectively applying FoV updates significantly improved the image quality of SAMER reconstructions. Simulated artifact patterns were shown to closely match those observed in vivo, and across 274 simulations using clinical motion trajectories, the combined approach reduced NRMSE in 90% of moderate-to-severe motion cases and significantly decreased the overall reconstruction error.
CONCLUSION
Utilizing on-the-fly SAMER motion estimates, a combined prospective and retrospective motion correction approach was demonstrated for 2D TSE imaging. The proposed method improved image quality in several representative in vivo motion experiments and across simulations of a wide range of clinical inpatient motion conditions. In addition, simulated artifact patterns were shown to closely match those observed in vivo. This capability should enable on-the-fly prediction of motion artifacts for efficient/intelligent acquisition strategies for the most challenging motion scenarios.
Hongli Fan, B. Clifford, Michael Koenig et al.· Magnetic Resonance in Medici...· 0 citations
Purpose
Rigid head motion during interventional C-arm cone-beam CT (CBCT) is a major source of image degradation. Learning-based motion estimation requires realistic training data, but ground-truth motion is scarce, limiting direct validation of compensation trajectories. We address this gap with an open resource consisting of tracked real motion and pregenerated synthetic motion, along with a pretrained variational autoencoder (VAE) to generate larger ground-truth datasets.
Approach
Using stereo optical tracking, we recorded rigid 6-DoF head motion trajectories from 25 volunteers lying head-first supine on an examination table, resembling a clinical setting. After data preprocessing, we trained a VAE on 120 sequences of 10 s at 30 Hz. Motion is represented in patient-centered coordinates to support transformation to arbitrary scan geometries. Similarity between measured and generated data is assessed via distributional distances, correlation metrics, low-dimensional embeddings, and a posthoc analysis of the learned latent space.
Results
Evaluated based on 120 generated sequences, the trained VAE is capable of producing diverse 6-DoF trajectories that preserve real-world data correlation structure. Distributional and frequency-domain metrics, along with t-SNE embeddings, show overlap between real and synthetic samples without evidence of mode collapse or training data replication.
Conclusions
This work provides an openly released resource comprising measured trajectories, a synthetic dataset, and pretrained VAE weights together with full training and evaluation code, combining rigid 6-DoF head motion measured in a realistic C-arm setting with a retrainable generative model. It is intended to support reproducible development, benchmarking, and comparison of head motion estimation methods in medical imaging modalities.
M. Goldmann, Felix Damm, F. Goldmann et al.· Journal of Medical Imaging· 0 citations
Respiratory motion in thoracic positron emission tomography (PET) introduces spatially heterogeneous non-rigid deformation that can blur lesions, weaken local boundary definition, and reduce structural fidelity. To address this problem, we developed TLCE-morph, a Tri-Path Lie Convolution Encoder-based learning framework for deformable respiratory motion correction in thoracic PET. The framework combines an SO(3)-based group-aware convolution module with a Tri-Path Fusion Encoder to couple orientation-aware geometric modeling with structurally guided feature encoding at local, global, and cross-scale levels. TLCE-morph was evaluated on simulated respiratory motion datasets and a two-center clinical gated PET cohort using Dice, correlation coefficient, and 95th percentile Hausdorff distance. Additional analyses included lesion-level normalized PET uptake consistency, local line-profile and full width at half maximum measurements in motion-sensitive regions, architectural ablation, group-representation comparison, and computational profiling. Across the simulated datasets, TLCE-morph remained comparatively stable as deformation increased from relatively regular displacement to more heterogeneous and coupled motion. In the clinical gated PET cohort, it achieved the most favorable overall quantitative performance among the evaluated methods and showed more consistent local structural recovery in representative motion-sensitive regions. Additional comparisons of group representations and architectural ablation indicated that the observed advantage was associated with the joint contribution of 3D orientation-aware feature modeling and complementary structural constraints rather than with any single component alone. These findings suggest that stable respiratory motion correction in thoracic PET may benefit from coupling geometric sensitivity with structurally guided feature encoding under heterogeneous deformation, rather than relying on appearance matching alone.
Hui Zhou, Longxi He, Siyu Wang et al.· Frontiers of Physics· 0 citations
Abstract Background Accurate motion estimation remains a key challenge in adaptive radiotherapy (ART). Voxel‐wise accuracy is required, as registration errors can compromise the treatment quality. Locally constrained image registration is a promising technique to further improve ART treatment, but relies heavily on quick and accurate delineations of the local areas used to constrain. In online clinical scenarios, these delineations are often available on pre‐treatment image volumes, but not on the online data due to accuracy and time constraints. Purpose We developed a deformable image registration (DIR) framework that integrates inverse consistency with local biomechanical constraints, enabling tissue‐specific motion modeling using contours from only a single image volume. This approach enforces tissue‐specific constraints on the inverse deformation field and propagates them to the forward deformation through inverse consistency optimization, yielding anatomically plausible motion estimates for ART workflows. Methods The proposed framework was evaluated in three scenarios relevant to ART: abdominal CT‐CT and multi‐modality CT‐MR registration with incompressibility constraints on the liver and kidneys, as well as thoracic CT‐CT registration with local rigidity constraints on the ribs and vertebrae. We also investigated the robustness of the framework to image degradation by evaluating motion estimates under added Gaussian noise and artificially induced streaking artifacts. Performance was compared to a baseline DIR model and an unconstrained inverse‐consistent model. Accuracy and anatomical consistency were assessed using landmark alignment, contour overlap, and physics‐based motion analysis. Results We demonstrate that local biomechanical constraints imposed on the inverse deformation field are successfully propagated to the forward motion field through inverse consistency optimization. The proposed framework improves the biomechanical plausibility of the resulting deformation fields at a small cost of landmark‐based accuracy, and maintaining comparable results in terms of contour‐based evaluation. The method is applicable to both mono‐ and multimodality registration and is more robust to noise and artifacts that appear from image acquisition and reconstruction. Conclusions The proposed framework uses inverse consistency to propagate local constraints between motion fields. This work demonstrates the use of local biomechanical constraints for DIR in several use‐cases for ART. This methodology requires delineations of local tissue on only one of the image volumes. This approach can become beneficial for applications where voxel‐wise accuracy and anatomical consistency are required, but quick and accurate delineations of new anatomies are unavailable, such as online ART.
T. J. W. Draper, C. Zachiu, B. Raaymakers· Medical Physics (Lancaster)· 0 citations
The accurate extraction of full-field dynamic parameters of large cylindrical shell structures is important for structural design optimization and health monitoring. To address the difficulty of reconciling wide-FOV coverage with high spatial resolution in visual measurements of complex curved surfaces, together with the cumulative errors readily introduced by stitching overlapping regions across multiple views, this paper proposes a FOV-constrained optimization method and a non-overlapping full-field stitching method based on partitioned mode shapes. Specifically, instead of relying on cascaded features in overlapping adjacent measurement regions, the algorithm independently maps and stitches the mode shape of each partition in a pre-established global coordinate system to achieve 360° full-field coverage of the cylindrical shell. First, by jointly considering the frequency-domain signal-to-noise ratio requirement for micro-amplitude vibration measurement and the depth-of-field boundary of curved-surface imaging, a FOV optimization model under multi-physical constraints is established, and a partitioning criterion for maximizing the effective single-view FOV is derived. Second, based on the fact that mode shapes are inherent spatial properties of linear time-invariant systems, the local mode shapes acquired from different partitions are assembled into full-field 3D mode shapes through global coordinate mapping, excitation-energy normalization, and unified phase reference. A stitching error analysis model based on the modal assurance criterion (MAC) is also established. Experiments on an aluminum alloy cylindrical shell demonstrate that the natural frequencies and damping ratios extracted by the vision-based method agree well with accelerometer measurements and finite element results. Furthermore, cross-validation between the reconstructed full-field mode shapes and 60 accelerometer measurement points yields MAC values above 0.90, verifying the effectiveness of the proposed method.
Xiaolin Zhai, Qihui Zhu, Junhao Lv et al.· Measurement science and tech...· 0 citations
Objective. Traditional radiotherapy dosimetric analyses are often limited by cone-beam CT artifacts and correlated longitudinal data mismanagement. This study uses artifact-free fan-beam CT (FBCT) and a generalized linear mixed Lasso (glmmLasso) model to decouple interfraction setup errors and anatomical deformations within a simulated image-guided radiotherapy workflow, providing quantitative support for future site-specific ART research. Approach. We retrospectively analyzed 84 patients (head and neck [H&N], thorax, pelvis; n = 28 each). Weekly diagnostic-quality FBCTs served as ground truth. To isolate error sources, we recalculated 1 260 dose distributions under three scenarios: isolated setup errors, isolated deformations, and combined effects. A glmmLasso model, using patient-specific random intercepts and L1 penalization, identified the primary geometric drivers of dosimetric variation. Main Results. H&N exhibited minimal setup deviations (< 2.0 mm); dosimetric variance was driven by inter-patient baseline heterogeneity (ICC > 0.73) rather than interfraction deformations. Thoracic setup uncertainties (mean≈4.0 mm) reduced minimum target dose up to 50% for displacements ⩾ 5 mm, but overall variance was primarily governed by non-rigid deformations (marginal R2 = 0.423). Pelvic anatomy demonstrated pronounced variability due to bladder filling (DSC: 0.2–0.9), and the coupled scenario further amplified relative deviations in bladder and femoral-head dose metrics. Significance. Utilizing FBCT and high-dimensional feature selection, we decoupled site-specific drivers of dosimetric variation. Quantifying these coupled effects establishes a robust, validated foundation for tailored potential factors to inform ART decision-making.
Lianzi Zhao, Ying Guo, Yuanshuai Di et al.· Physics in Medicine and Biol...· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comAug 31, 2026
What if pathology foundation models could do more with less? GigaPath-Flash and GigaTIME-Flash cut computational demands while maintaining strong performance, opening the door to larger studies and broader exploration. The post GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduAug 31, 2026
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
MIT News · Artificial Intelligence· news.mit.eduAug 27, 2026
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.