pith. sign in

arxiv: 2604.25646 · v2 · pith:RQLNAZPLnew · submitted 2026-04-28 · 💻 cs.CV · cs.RO

SAMe: A Semantic Anatomy Mapping Engine for Robotic Ultrasound

Jing Zhang , Duojie Chen , Wentao Jiang , Zihan Lou , Jianxin Liu , Xinwu Cui , Qinghong Zhao , Bo Du
show 2 more authors
Christoph F. Dietrich Dacheng Tao
This is my paper

Pith reviewed 2026-05-21 00:08 UTC · model grok-4.3

classification 💻 cs.CV cs.RO
keywords robotic ultrasoundanatomical mappingsemantic groundingprobe initializationautonomous scanningmedical roboticspatient-specific anatomy6-DoF control
0
0 comments X

The pith

A single external body image suffices for robotic ultrasound to initialize scans on specific organs like the liver and kidney without preoperative CT or MRI.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces SAMe to give robotic ultrasound systems an explicit layer of anatomical knowledge. It turns vague patient complaints into target organs, builds a patient-specific anatomical representation from one external body image, and translates that into exact 6-DoF probe positions to begin scanning. If this holds, robotic systems could start scans based on what the patient reports without expert setup or pre-operative scans each time. Real-robot tests report 86.7 percent success for liver initialization and 80.0 percent for kidney, outperforming a body-keypoint baseline.

Core claim

SAMe addresses scan initiation as a target-to-anatomy-to-action process: it grounds under-specified clinical complaints into structured target organs, instantiates a patient-specific anatomical representation for the grounded targets from a single external body image, and translates this representation into control-facing 6-DoF probe initialization states without any additional registration using preoperative CT or MRI. The anatomical representation maintained by SAMe is explicit, lightweight, and compatible with downstream control by design. In real-robot experiments, centroid-based SAMe initialization achieved 86.7 percent success for liver and 80.0 percent for kidney under single-target,

What carries the argument

The semantic anatomy mapping engine that grounds complaints to organs, instantiates patient-specific anatomy from one external image, and outputs 6-DoF probe states as the mechanism that carries the explicit anatomical prior.

If this is right

  • Robotic ultrasound can begin scans from patient complaints without expert intervention or pre-operative imaging.
  • Initialization reaches higher success than body-keypoint heuristics for both liver and kidney in single-target settings.
  • Organ-hit rates rise to 97.3 percent for liver and 83.3 percent for kidney when multiple candidate targets are available.
  • The lightweight representation is built to connect directly to downstream autonomous scanning pipelines.
  • Semantic grounding handles different ways of describing the same target organ.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same single-image mapping could be tested on additional organs or combined with other robotic imaging tasks.
  • Performance differences across body sizes would indicate where more training data or alternative inputs are needed.
  • Linking the output directly to real-time image feedback could turn initialization into continuous adaptive scanning.
  • Deployment in clinics without on-site imaging experts would test whether the method improves access to ultrasound.

Load-bearing premise

That a single external body image plus learned semantic grounding is sufficient to produce a patient-specific anatomical representation accurate enough for reliable 6-DoF probe initialization across varying body types and complaint phrasings.

What would settle it

Experiments on a larger group of patients with diverse body types and varied complaint wordings that produce success rates below 60 percent for liver initialization would show the anatomical representation is not accurate enough.

Figures

Figures reproduced from arXiv: 2604.25646 by Bo Du, Christoph F. Dietrich, Dacheng Tao, Duojie Chen, Jianxin Liu, Jing Zhang, Qinghong Zhao, Wentao Jiang, Xinwu Cui, Zihan Lou.

Figure 1
Figure 1. Figure 1: From manual expertise to autonomous robotic ultrasonography. view at source ↗
Figure 2
Figure 2. Figure 2: The SAMe system architecture bridging clinical semantics to robotic execution. view at source ↗
Figure 3
Figure 3. Figure 3: Overview of the SAMe semantic prior database and RAG performance across LLM view at source ↗
Figure 4
Figure 4. Figure 4: Clinical Semantics Grounding results. (a) System role of the semantic layer in SAMe: clinical complaint or report text is retrieved against the SAMe semantic prior and grounded into a structured target specification comprising target organ, related anatomy, prioritized location or ROI, and task-ready targets. (b) Baseline-versus-RAG grounding performance across evaluated model backends. (c) Output-quality … view at source ↗
Figure 5
Figure 5. Figure 5: Actionable Target Initialization in real robotic ultrasound. view at source ↗
Figure 6
Figure 6. Figure 6: Failure case (BMI 35.5), showing a superior offset in the predicted initialization re￾gion, with uncontrolled respira￾tion likely further increasing the anatomy–probe mismatch. servation beyond the learned prior distribution, and uncontrolled deep breathing introducing respiration-dependent liver motion not represented in the static, one-shot prior. More broadly, this failure highlights a fundamental bound… view at source ↗
Figure 7
Figure 7. Figure 7: Overview of the organ-layer modeling pipeline. Starting from CT-derived skin, skele view at source ↗
Figure 8
Figure 8. Figure 8: Skeleton-conditioned prior regression. A local joint subset in rest space is converted view at source ↗
Figure 9
Figure 9. Figure 9: Control-facing geometric interface. Anatomical targets are projected to candidate view at source ↗
read the original abstract

Robotic ultrasound has advanced local image-driven control, contact regulation, and view optimization, yet current systems lack the anatomical understanding needed to determine what to scan, where to begin, and how to adapt to individual patient anatomy. These gaps make systems still reliant on expert intervention to initiate scanning. Here we present SAMe, a semantic anatomy mapping engine that provides robotic ultrasound with an explicit anatomical prior layer. SAMe addresses scan initiation as a target-to-anatomy-to-action process: it grounds under-specified clinical complaints into structured target organs, instantiates a patient-specific anatomical representation for the grounded targets from a single external body image, and translates this representation into control-facing 6-DoF probe initialization states without any additional registration using preoperative CT or MRI. The anatomical representation maintained by SAMe is explicit, lightweight (single-organ inference in 0.08s), and compatible with downstream control by design. Across semantic grounding, anatomical instantiation, and real-robot evaluation, SAMe shows strong performance across the full initialization pipeline. In real-robot experiments, centroid-based SAMe initialization outperformed the body-keypoint-based heuristic baseline under a budget-matched single-target setting for both liver (86.7% versus 46.7%) and kidney (80.0% versus 73.3%) initialization. Furthermore, The trial-level organ-hit rate reached 97.3% for liver and 83.3% for kidney when multiple candidate targets were available. These results establish an explicit anatomical prior layer that addresses scan initialization and is designed to support broader downstream autonomous scanning pipelines, providing the anatomical foundation for complaint-driven, anatomically informed robotic ultrasonography.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper introduces SAMe, a semantic anatomy mapping engine for robotic ultrasound. It grounds clinical complaints to target organs, instantiates patient-specific anatomical representations from a single external RGB body image, and produces 6-DoF probe initialization poses without preoperative CT/MRI registration. Real-robot experiments report 86.7% success for liver and 80.0% for kidney initialization (outperforming a body-keypoint baseline), rising to 97.3% and 83.3% with multiple candidate targets; the representation is explicit, lightweight (0.08 s inference), and designed for downstream control compatibility.

Significance. If the results hold, SAMe supplies a practical explicit anatomical prior layer that directly addresses the scan-initiation gap in robotic ultrasound, potentially enabling more autonomous, complaint-driven pipelines. The real-robot validation under budget-matched conditions and the emphasis on control-facing outputs are concrete strengths; the lightweight design supports integration with existing view-optimization and contact-regulation modules.

major comments (2)
  1. [Real-robot experiments] Real-robot evaluation: success rates of 86.7 % (liver) and 80.0 % (kidney) are reported without accompanying details on trial count, patient demographics, body-habitus distribution, or error bars; this leaves the central claim that the single-image instantiation produces reliable patient-specific 6-DoF poses only partially supported.
  2. [Anatomical instantiation] Anatomical instantiation module: the headline performance rests on the assumption that one external body image plus learned semantic grounding recovers sufficiently accurate internal organ positions across body-type variation, yet no quantitative surface-to-internal error metric or results stratified by BMI/age/posture are provided; without these the reported organ-hit rates cannot be shown to generalize beyond the tested cohort.
minor comments (2)
  1. [Abstract] Abstract: 'Furthermore, The trial-level' contains an erroneous capital 'T'.
  2. [Discussion] The manuscript would benefit from an explicit limitations paragraph discussing sensitivity to body-habitus variation and the absence of preoperative imaging ground truth.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments on our manuscript. We address each major comment point by point below, providing clarifications and indicating revisions where they strengthen the presentation without altering the core contributions.

read point-by-point responses

  1. Referee: [Real-robot experiments] Real-robot evaluation: success rates of 86.7 % (liver) and 80.0 % (kidney) are reported without accompanying details on trial count, patient demographics, body-habitus distribution, or error bars; this leaves the central claim that the single-image instantiation produces reliable patient-specific 6-DoF poses only partially supported.

    Authors: We agree that these experimental details should be stated more explicitly to support the claims. The manuscript already specifies 30 trials per organ and condition in the evaluation section; we have revised the text to highlight this number prominently, include the available cohort demographics and body-habitus notes from the volunteer pool, and add error bars to the success-rate figures. These changes make the support for reliable 6-DoF pose generation clearer while remaining within the scope of the collected data. revision: yes

  2. Referee: [Anatomical instantiation] Anatomical instantiation module: the headline performance rests on the assumption that one external body image plus learned semantic grounding recovers sufficiently accurate internal organ positions across body-type variation, yet no quantitative surface-to-internal error metric or results stratified by BMI/age/posture are provided; without these the reported organ-hit rates cannot be shown to generalize beyond the tested cohort.

    Authors: We acknowledge the desire for direct internal-position metrics. Because SAMe is explicitly designed to function without preoperative CT or MRI, ground-truth internal coordinates are unavailable by construction, so a surface-to-internal error metric cannot be computed. The real-robot organ-hit rates therefore serve as the appropriate end-to-end proxy for instantiation accuracy. On stratification, the tested cohort exhibited limited variation in BMI, age, and posture; we have added an explicit limitations paragraph noting this constraint and the consequent inability to provide stratified breakdowns, while pointing to the multi-candidate results as evidence of robustness within the evaluated population. revision: partial

Circularity Check

0 steps flagged

No significant circularity; claims rest on empirical robot trials

full rationale

The paper describes SAMe as an engineered system that grounds clinical complaints, instantiates anatomy from a single RGB image, and outputs 6-DoF probe poses, with performance quantified by real-robot success rates (86.7 % liver, 80.0 % kidney). No mathematical derivation chain is presented that reduces a claimed prediction or first-principles result to its own inputs by construction. The reported pipeline is evaluated externally via physical trials rather than through fitted parameters renamed as predictions or self-citation chains that bear the central load. The single-image anatomical instantiation is treated as a learned module whose accuracy is tested rather than assumed tautologically.

Axiom & Free-Parameter Ledger

1 free parameters · 0 axioms · 0 invented entities

The approach relies on trained models for semantic grounding and anatomical instantiation whose parameters are fitted to data; these constitute free parameters. No new physical axioms or invented entities are introduced.

free parameters (1)
  • Neural network weights for semantic grounding and anatomy prediction
    Learned parameters that map body images and text complaints to organ locations and shapes; central to the instantiation step.

pith-pipeline@v0.9.0 · 5853 in / 1241 out tokens · 30418 ms · 2026-05-21T00:08:12.738709+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

71 extracted references · 71 canonical work pages

  1. [1]

    J.et al.Practice guidelines for performance of the routine mid-trimester fetal ultrasound scan.Ultrasound in Obstetrics & Gynecology37(2011)

    Salomon, L. J.et al.Practice guidelines for performance of the routine mid-trimester fetal ultrasound scan.Ultrasound in Obstetrics & Gynecology37(2011)

    work page 2011

  2. [2]

    I.et al.Normative spatiotemporal fetal brain maturation with satisfactory development at 2 years.Nature623, 106–114 (2023)

    Namburete, A. I.et al.Normative spatiotemporal fetal brain maturation with satisfactory development at 2 years.Nature623, 106–114 (2023)

    work page 2023

  3. [3]

    E.et al.Deep-learning-assisted analysis of echocardiographic videos im- proves predictions of all-cause mortality.Nature Biomedical Engineering5, 546–554 (2021)

    Ulloa Cerna, A. E.et al.Deep-learning-assisted analysis of echocardiographic videos im- proves predictions of all-cause mortality.Nature Biomedical Engineering5, 546–554 (2021)

    work page 2021

  4. [4]

    Stein, J. H.et al.Use of carotid ultrasound to identify subclinical vascular disease and evaluate cardiovascular disease risk: a consensus statement from the american society of echocardiography carotid intima-media thickness task force endorsed by the society for vascular medicine.Journal of the American Society of echocardiography21, 93–111 (2008)

    work page 2008

  5. [5]

    R., Buckley, A

    Tahmasebpour, H. R., Buckley, A. R., Cooperberg, P. L. & Fix, C. H. Sonographic exami- nation of the carotid arteries.Radiographics25, 1561–1575 (2005)

    work page 2005

  6. [6]

    & Monteiro, L

    Ferraioli, G. & Monteiro, L. B. S. Ultrasound-based techniques for the diagnosis of liver steatosis.World journal of gastroenterology25, 6053 (2019)

    work page 2019

  7. [7]

    Ferraioli, G.et al.Liver ultrasound elastography: an update to the world federation for ul- trasound in medicine and biology guidelines and recommendations.Ultrasound in medicine & biology44, 2419–2440 (2018)

    work page 2018

  8. [8]

    Leenhardt, L.et al.2013 european thyroid association guidelines for cervical ultrasound scan and ultrasound-guided techniques in the postoperative management of patients with thyroid cancer.European thyroid journal2, 147–159 (2013)

    work page 2013

  9. [9]

    Lin, M.et al.A fully integrated wearable ultrasound system to monitor deep tissues in moving subjects.Nature biotechnology42, 448–457 (2024)

    work page 2024

  10. [10]

    Hu, H.et al.A wearable cardiac ultrasound imager.Nature613, 667–675 (2023). 25

    work page 2023

  11. [11]

    Wang, C.et al.Monitoring of the central blood pressure waveform via a conformal ultrasonic device.Nature biomedical engineering2, 687–695 (2018)

    work page 2018

  12. [12]

    & Scott, D

    Beales, L., Wolstenhulme, S., Evans, J., West, R. & Scott, D. Reproducibility of ultrasound measurement of the abdominal aorta.Journal of British Surgery98, 1517–1525 (2011)

    work page 2011

  13. [13]

    Joakimsen, O., Bønaa, K. H. & Stensland-Bugge, E. Reproducibility of ultrasound assess- ment of carotid plaque occurrence, thickness, and morphology: the tromsø study.Stroke 28, 2201–2207 (1997)

    work page 1997

  14. [14]

    Kojcev, R.et al.On the reproducibility of expert-operated and robotic ultrasound acqui- sitions.International journal of computer assisted radiology and surgery12, 1003–1011 (2017)

    work page 2017

  15. [15]

    Journal of ultrasound in medicine43, 1289–1301 (2024)

    Won, D.et al.Sound the alarm: the sonographer shortage is echoing across healthcare. Journal of ultrasound in medicine43, 1289–1301 (2024)

    work page 2024

  16. [16]

    2023 radiologic sciences workplace and staffing survey

    American Society of Radiologic Technologists. 2023 radiologic sciences workplace and staffing survey. Tech. Rep., American Society of Radiologic Technologists (2023). URLhttps://www.asrt.org/docs/default-source/research/staffing-surveys/ radiologic-sciences-workplace-and-staffing-survey-2023.pdf

    work page 2023

  17. [17]

    Department of Labor

    Bureau of Labor Statistics, U.S. Department of Labor. Diagnostic medical sonographers. Occupational Outlook Handbook (2025). URLhttps://www.bls.gov/ooh/healthcare/ diagnostic-medical-sonographers.htm. Last modified August 28, 2025

    work page 2025

  18. [18]

    & Moss, C

    McGregor, R., Pollard, K., Davidson, R. & Moss, C. Providing a sustainable sonographer workforce in australia: clinical training solutions.Sonography7, 141–147 (2020)

    work page 2020

  19. [19]

    Addressing health human resource issues in diagnostic medical imag- ing – sonography: Pre-budget submission for the 2024–25 federal budget

    Sonography Canada. Addressing health human resource issues in diagnostic medical imag- ing – sonography: Pre-budget submission for the 2024–25 federal budget. Tech. Rep., Sonography Canada (2023). URLhttps://sonographycanada.ca/app/uploads/2023/ 10/Sonography-Canada-Pre-Budget-Final.pdf

    work page 2024

  20. [20]

    Sonography vacancy rates have increased dramatically, sor ultrasound census reveals (2026)

    Society of Radiographers. Sonography vacancy rates have increased dramatically, sor ultrasound census reveals (2026). URLhttps://www.sor.org/news/ultrasound/ sonography-vacancy-rates-have-increased-dramatical. Accessed 14 Apr 2026

    work page 2026

  21. [21]

    & Harrison, G

    Parker, P. & Harrison, G. Educating the future sonographic workforce: membership survey report from the british medical ultrasound society.Ultrasound23, 231–241 (2015)

    work page 2015

  22. [22]

    & Strudwick, R

    Coleman, G., Hyde, E. & Strudwick, R. Exploring uk sonographers’ views on the use of professional supervision in clinical practice–stage one findings of a mixed method study. Radiography30, 252–256 (2024)

    work page 2024

  23. [23]

    R., Cleary, K., Wilson, E., Azizi-Koutenaei, B

    Swerdlow, D. R., Cleary, K., Wilson, E., Azizi-Koutenaei, B. & Monfaredi, R. Robotic arm– assisted sonography: Review of technical developments and potential clinical applications. American Journal of Roentgenology208, 733–738 (2017)

    work page 2017

  24. [24]

    Monfaredi, R.et al.Robot-assisted ultrasound imaging: Overview and development of a parallel telerobotic system.Minimally Invasive Therapy & Allied Technologies24, 54–62 (2015)

    work page 2015

  25. [25]

    Huang, Q., Zhou, J. & Li, Z. Review of robot-assisted medical ultrasound imaging systems: Technology and clinical applications.Neurocomputing559, 126790 (2023). 26

    work page 2023

  26. [26]

    The International Journal of Medical Robotics and Computer Assisted Surgery20, e2660 (2024)

    Du, H.et al.A review of robot-assisted ultrasound examination: Systems and technology. The International Journal of Medical Robotics and Computer Assisted Surgery20, e2660 (2024)

    work page 2024

  27. [27]

    Su, K.et al.A fully autonomous robotic ultrasound system for thyroid scanning.Nature communications15, 4004 (2024)

    work page 2024

  28. [28]

    Jiang, H.et al.Towards expert-level autonomous carotid ultrasonography with large-scale learning-based robotic system.Nature Communications16, 7893 (2025)

    work page 2025

  29. [29]

    & Navab, N

    Bi, Y., Jiang, Z., Duelmer, F., Huang, D. & Navab, N. Machine learning in robotic ul- trasound imaging: Challenges and perspectives.Annual Review of Control, Robotics, and Autonomous Systems7(2024)

    work page 2024

  30. [30]

    Liu, Y.et al.From screens to scenes: A survey of embodied ai in healthcare.Information Fusion119, 103033 (2025)

    work page 2025

  31. [31]

    Merouche, S.et al.A robotic ultrasound scanner for automatic vessel tracking and three- dimensional reconstruction of b-mode images.IEEE transactions on ultrasonics, ferro- electrics, and frequency control63, 35–46 (2015)

    work page 2015

  32. [32]

    In2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 3784–3791 (IEEE, Prague, Czech Republic, 2021)

    Akbari, M.et al.Robot-assisted breast ultrasound scanning using geometrical analysis of the seroma and image segmentation. In2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 3784–3791 (IEEE, Prague, Czech Republic, 2021)

    work page 2021

  33. [33]

    Jiang, Z.et al.Autonomous robotic screening of tubular structures based only on real-time ultrasound imaging feedback.IEEE Transactions on Industrial Electronics69, 7064–7075 (2021)

    work page 2021

  34. [34]

    Wang, Z.et al.Autonomous robotic system for carotid artery ultrasound scanning with visual servo navigation.IEEE Transactions on Medical Robotics and Bionics6, 1436–1447 (2024)

    work page 2024

  35. [35]

    In2023 IEEE International Conference on Robotics and Automation (ICRA), 2690–2696 (IEEE, London, UK, 2023)

    Chen, M.et al.Fully robotized 3d ultrasound image acquisition for artery. In2023 IEEE International Conference on Robotics and Automation (ICRA), 2690–2696 (IEEE, London, UK, 2023)

    work page 2023

  36. [36]

    Jiang, Z.et al.Skeleton graph-based ultrasound-ct non-rigid registration.IEEE Robotics and Automation Letters8, 4394–4401 (2023)

    work page 2023

  37. [37]

    In2021 IEEE International Conference on Robotics and Automation (ICRA), 12494–12500 (IEEE, Xi’an, China, 2021)

    Jiang, Z.et al.Motion-aware robotic 3d ultrasound. In2021 IEEE International Conference on Robotics and Automation (ICRA), 12494–12500 (IEEE, Xi’an, China, 2021)

    work page 2021

  38. [38]

    In2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 5534–5541 (IEEE, 2020)

    Hase, H.et al.Ultrasound-guided robotic navigation with deep reinforcement learning. In2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 5534–5541 (IEEE, 2020)

    work page 2020

  39. [39]

    In2021 IEEE International Conference on Robotics and Automation (ICRA), 8302–8308 (IEEE, 2021)

    Li, K.et al.Autonomous navigation of an ultrasound probe towards standard scan planes with deep reinforcement learning. In2021 IEEE International Conference on Robotics and Automation (ICRA), 8302–8308 (IEEE, 2021)

    work page 2021

  40. [40]

    & Liao, H

    Ning, G., Zhang, X. & Liao, H. Autonomic robotic ultrasound imaging system based on reinforcement learning.IEEE transactions on biomedical engineering68, 2787–2797 (2021)

    work page 2021

  41. [41]

    Bi, Y.et al.Vesnet-rl: Simulation-based reinforcement learning for real-world us probe navigation.IEEE Robotics and Automation Letters7, 6638–6645 (2022). 27

    work page 2022

  42. [42]

    Droste, R., Drukker, L., Papageorghiou, A. T. & Noble, J. A. Automatic probe movement guidance for freehand obstetric ultrasound. InInternational Conference on Medical Image Computing and Computer-Assisted Intervention, 583–592 (Springer, 2020)

    work page 2020

  43. [43]

    Men, Q., Teng, C., Drukker, L., Papageorghiou, A. T. & Noble, J. A. Multimodal- guidenet: Gaze-probe bidirectional guidance in obstetric ultrasound scanning. InInter- national Conference on Medical Image Computing and Computer-Assisted Intervention, 94–103 (Springer, 2022)

    work page 2022

  44. [44]

    Deng, X., Chen, Y., Chen, F. & Li, M. Learning robotic ultrasound scanning skills via human demonstrations and guided explorations. In2021 IEEE International Conference on Robotics and Biomimetics (ROBIO), 372–378 (IEEE, 2021)

    work page 2021

  45. [45]

    & Navab, N

    Jiang, Z., Gao, Y., Xie, L. & Navab, N. Towards autonomous atlas-based ultrasound acquisitions in presence of articulated motion.IEEE Robotics and Automation Letters7, 7423–7430 (2022)

    work page 2022

  46. [46]

    Hennersperger, C.et al.Towards mri-based autonomous robotic us acquisitions: a first feasibility study.IEEE transactions on medical imaging36, 538–548 (2016)

    work page 2016

  47. [47]

    Jiang, Z.et al.Precise repositioning of robotic ultrasound: Improving registration-based motion compensation using ultrasound confidence optimization.IEEE Transactions on Instrumentation and Measurement71, 1–11 (2022)

    work page 2022

  48. [48]

    InIntelligent Systems Conference, 610–625 (Springer, 2024)

    Long, J.et al.Localizing scan targets from human pose for autonomous lung ultrasound imaging. InIntelligent Systems Conference, 610–625 (Springer, 2024)

    work page 2024

  49. [49]

    E.et al.Mimic-iv, a freely accessible electronic health record dataset.Scientific Data10, 1 (2023)

    Johnson, A. E.et al.Mimic-iv, a freely accessible electronic health record dataset.Scientific Data10, 1 (2023)

    work page 2023

  50. [50]

    Wu, J.et al.Medical graph rag: Towards safe medical large language model via graph retrieval-augmented generation.arXiv preprint arXiv:2408.04187(2024)

    work page arXiv 2024

  51. [51]

    mimic ex dataset.https://huggingface.co/datasets/morson/mimic_ex (2024)

    Morson. mimic ex dataset.https://huggingface.co/datasets/morson/mimic_ex (2024). Accessed: 2025-10-22

    work page 2024

  52. [52]

    & J´ egou, H

    Johnson, J., Douze, M. & J´ egou, H. Billion-scale similarity search with GPUs.IEEE Transactions on Big Data7, 535–547 (2019)

    work page 2019

  53. [53]

    Gutschmayer, S.et al.Whole-body [18f] fdg-pet/ct imaging of healthy controls: Test/retest data for systemic, multi-organ analysis.Scientific Data12, 1707 (2025)

    work page 2025

  54. [54]

    URLhttps://doi.org/10

    Gutschmayer, S., Yu, J.et al.Whole-body [18f]fdg-pet/ct imaging of healthy controls: Test/retest data for systemic, multi-organ analysis (2025). URLhttps://doi.org/10. 5281/zenodo.16364694

    work page 2025

  55. [55]

    Shetty, K.et al.BOSS: Bones, organs and skin shape model.Computers in Biology and Medicine165, 107383 (2023)

    work page 2023

  56. [56]

    Kats, E.et al.Depth to anatomy: Learning internal organ locations from surface depth images.arXiv preprint arXiv:2601.18260(2026)

    work page arXiv 2026

  57. [57]

    & Mathis-Ullrich, F

    Henrich, P. & Mathis-Ullrich, F. Looc: Localizing organs using occupancy networks and body surface depth images.IEEE Access(2025)

    work page 2025

  58. [59]

    & Tao, D

    Xu, Y., Zhang, J., Zhang, Q. & Tao, D. Vitpose: Simple vision transformer baselines for human pose estimation.Advances in neural information processing systems35, 38571– 38584 (2022)

    work page 2022

  59. [60]

    Yang, X.et al.Sam 3d body: Robust full-body human mesh recovery.arXiv preprint arXiv:2602.15989(2026)

    work page arXiv 2026

  60. [61]

    H.et al.A scoping review of human digital twins in healthcare applications and usage patterns.npj Digital Medicine8, 587 (2025)

    Tudor, B. H.et al.A scoping review of human digital twins in healthcare applications and usage patterns.npj Digital Medicine8, 587 (2025)

    work page 2025

  61. [62]

    Foundational research gaps and future directions for digital twins(Na- tional Academies Press Washington, DC, USA, 2023)

    Willcox, K.et al. Foundational research gaps and future directions for digital twins(Na- tional Academies Press Washington, DC, USA, 2023)

    work page 2023

  62. [63]

    & Gonsard, A

    Drummond, D. & Gonsard, A. Definitions and characteristics of patient digital twins being developed for clinical use: scoping review.Journal of Medical Internet Research26, e58504 (2024)

    work page 2024

  63. [64]

    R.et al.Low-dose ct images of healthy cohort (healthy- total-body-cts) (2023)

    Selfridge, A. R.et al.Low-dose ct images of healthy cohort (healthy- total-body-cts) (2023). URLhttps://www.cancerimagingarchive.net/collection/ healthy-total-body-cts/

    work page 2023

  64. [65]

    Lorensen, W. E. & Cline, H. E. Marching cubes: A high resolution 3d surface construction algorithm. In Kaufman, A. (ed.)Seminal graphics: pioneering efforts that shaped the field, 347–353 (ACM Press, New York, NY, USA, 1998)

    work page 1998

  65. [66]

    InProceedings IEEE Conf

    Pavlakos, G.et al.Expressive body capture: 3d hands, face, and body from a single image. InProceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)(2019)

    work page 2019

  66. [67]

    & Black, M

    Romero, J., Tzionas, D. & Black, M. J. Embodied hands: Modeling and capturing hands and bodies together.ACM Transactions on Graphics, (Proc. SIGGRAPH Asia)36(2017)

    work page 2017

  67. [68]

    & Black, M

    Loper, M., Mahmood, N., Romero, J., Pons-Moll, G. & Black, M. J. SMPL: A skinned multi-person linear model.ACM Transactions on Graphics, (Proc. SIGGRAPH Asia)34, 248:1–248:16 (2015)

    work page 2015

  68. [69]

    arXiv preprint arXiv:2511.15586 , year=

    Ferguson, A.et al.Mhr: Momentum human rig (2025). URLhttps://arxiv.org/abs/ 2511.15586.2511.15586

    work page arXiv 2025

  69. [70]

    A solution for the best rotation to relate two sets of vectors.Acta Crystallo- graphica Section A32, 922–923 (1976)

    Kabsch, W. A solution for the best rotation to relate two sets of vectors.Acta Crystallo- graphica Section A32, 922–923 (1976)

    work page 1976

  70. [71]

    InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 20814–20823 (2022)

    Guo, H.et al.Smpl-a: Modeling person-specific deformable anatomy. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 20814–20823 (2022)

    work page 2022

  71. [72]

    InACM ToG, Proc

    Keller, M.et al.From skin to skeleton: Towards biomechanically accurate 3d digital humans. InACM ToG, Proc. SIGGRAPH Asia, vol. 42 (2023). Acknowledgements This work was supported in part by the New Generation Artificial Intelligence-National Science and Technology Major Project under Grant No. 2025ZD0123602. 29 Author contributions J.Z. and D.C. conceive...

    work page 2023