Ultrasound Imaging Techniques for Bone Surface Segmentation
Summary
Ultrasound imaging has emerged as a promising non-ionising modality for visualising bone surfaces, offering real-time feedback, portability and cost efficiency compared with conventional CT or MRI. Bone–soft-tissue interfaces produce strong echoes, yet the interpretation of these echoes is hampered by speckle noise, acoustic shadowing and limited field-of-view. Traditional approaches to bone segmentation have relied on heuristic filters, edge detectors and active shape models to delineate cortical margins in two-dimensional B-mode images. More recently, freehand three-dimensional ultrasound acquisition combined with image registration to preoperative volumes has enabled volumetric reconstruction of bone structures intraoperatively. The past several years have witnessed a shift towards machine-learning frameworks—principally convolutional neural networks—for automated bone contour extraction, followed by statistical shape-model-based completion of occluded regions. These advances are driving practical applications in computer-assisted orthopaedic surgery, arthroplasty planning and ultrasound-guided interventions, with submillimetric accuracy now achievable in live settings.
Research from Nature Portfolio
No recent Nature Portfolio content available.
Ultrasound Imaging Techniques for Bone Surface Segmentation publication trend
The graph below shows the total number of articles in ultrasound imaging techniques for bone surface segmentation across all publications each year (not limited to Nature Index journals).
Technical terms
Speckle noise: Grainy interference pattern in ultrasound caused by coherent scattering, which obscures fine structural details.
U-Net: A convolutional neural network architecture with symmetric encoder–decoder paths and skip connections, widely used for biomedical image segmentation.
Statistical Shape Model (SSM): A deformable model constructed from a training set of anatomies, used to infer complete structures from partial observations.
Dice similarity coefficient: A metric for overlap between predicted and reference segmentations, ranging from 0 (no overlap) to 1 (perfect match).
Level-set loss: A segmentation loss function that emphasises boundary localisation by modelling contour evolution in the network’s output.
References
- Improved Surface‐Based Registration of CT and Intraoperative 3D Ultrasound of Bones. Journal of Healthcare Engineering (2018).
- Knee Bone Models From Ultrasound. IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control (2023).
- Ultrasound-based 3D bone modelling in computer assisted orthopedic surgery – a review and future challenges. Computer Assisted Surgery (2024).
- Segmentation of bone surface from ultrasound using a lightweight network UBS-Net. Biomedical Physics & Engineering Express (2024).
About these summaries
This Nature Research Intelligence Topic summary is created with the cited references and a large language model. We take care to ground generated text with facts, and have systems in place to gain human feedback on the overall quality of the process in line with our AI principles. We strive to create accurate and useful summaries for people unfamiliar with the research topic and that supports this goal. These pages are a beta release and will be updated as we learn how best to help people gain value from a research topic summary.
Turn complex research questions into confident strategic decisions
When you're under pressure to set direction, justify investment, or understand your competitive position, you need more than raw data — you need trusted insights you can act on.
Benchmark your performance against global peers using robust, methodologically sound analysis.
Combine quantitative metrics with qualitative expert insight to uncover strengths, gaps and emerging opportunities.
Gain tailored, decision-ready recommendations aligned to your strategic priorities.
Talk to us to learn more about our data dashboards and bespoke strategy reports.
Grow research skills, confidence and careers with training built for every stage of the research lifecycle.
Developed with Nature Portfolio journal Editors and internationally renowned experts. Discover three ways to learn:
Self-paced, online courses in convenient bite-sized units, covering key skills across scientific writing, publishing, grant writing, data analysis, and more.
Expert trainer-led workshops with hands-on exercises and real-time feedback across core research skills, delivered via interactive group sessions.
Editor-led workshops combining core principles in writing and publishing, personalised 1:1 feedback from Nature Portfolio Editors and hands-on exercises.
Explore course catalogues and workshop agendas, enquire about the options or request institutional pricing.