Follow the Curve: Robotic Ultrasound Navigation With Learning-Based Localization of Spinous Processes for Scoliosis Assessment

Victorova, Maria; Ka-Shing, Lee, Michael; Navarro-Alarcon, David; Zheng, Yongping

doi:10.1109/access.2022.3165936

Cited by 15 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The measurement accuracy might be affected by volumetric distortion and did not present the reconstructed anatomic features. The robot-assisted US system was also applied to scoliosis assessment with five human subjects in [37]. Unfortunately, only reconstructed transverse processes were included in the assessment, while the analysis was not applied to all the anatomic features.…”

Section: Discussionmentioning

confidence: 99%

Robot-assisted Ultrasound Reconstruction for Minimally Invasive Spine Surgery: from Bench-top to Pre-clinical Study

Li¹

2022

Preprint

View full text Add to dashboard Cite

<p>Objective: Robot-assisted ultrasound (US) system could potentially provide a non-radiative three-dimensional (3D) reconstruction for minimally invasive spine surgery. Despite promising studies on this technology, few researchers provide a comprehensive analysis with technical details. The performance is only showcased in one specific experimental setting without offering insight into robustness and generality of the approach by e.g. verifying performance in various testing scenarios. This limitation impedes the translation of this technology toward clinical practice. Therefore, this study provides a comprehensive assessment of the performance of robot-assisted US system. This study provides all essential technical details from experiments starting at the bench-top up to pre-clinical study. Methods: A hybrid control strategy was proposed to ensure continuous and smooth scanning, while a U-Net based US reconstruction framework was utilized to process the anatomic features automatically. Experiments were conducted on two synthetic spine phantoms and two ex-vivo cadavers. Results: The average deviation of scanning force was 2.84 ± 0.45 N on the synthetic phantom and 5.64 ± 1.10 N on the ex-vivo cadaver. The reconstruction yielded a mean 3D representation error of 1.28 ± 0.87 mm and 1.74 ± 0.89 mm for the synthetic and cadaveric experiments, respectively. Conclusion: The experiments indicated the proposed robot-assisted US system is feasible for relatively independent experiment settings, varying from laboratory experiments to pre-clinical studies. Significance: The developed system offers an improved understanding of the potential for this technology and paves the way for deploying the robotic US system towards in-vivo clinical study.</p>

show abstract

Section: Discussionmentioning

confidence: 99%

Robot-assisted Ultrasound Reconstruction for Minimally Invasive Spine Surgery: from Bench-top to Pre-clinical Study

Li¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The robot uses a machine‐learning algorithm to follow the spinal curvature and detect the spinal region for rotation adjustments, described in earlier stage of the current work 16 . The fully connected network model was designed to detect the spinous process location to indicate the spine centre at each ultrasound B‐mode frame in real‐time.…”

Section: Methodsmentioning

confidence: 99%

“…The robotic ultrasound system used in this study (Figure 1B) was designed for scoliosis assessment and was initially presented in Victorova et al 12 . and extended in Victorova et al 16 . It uses a DL‐based navigation control to detect the centre of the spine, which is defined as spinous process tip, in real‐time at each B‐mode ultrasound frame; thus, there is no need for additional external sensors, such as a camera.…”

Section: Introductionmentioning

confidence: 99%

“…To reduce the effect of the human factor on spinal ultrasound examinations, several research groups proposed using robotic ultrasound systems. [12][13][14][15] The robotic ultrasound system used in this study (Figure 1B) was designed for scoliosis assessment and was initially presented in Victorova et al 12 and extended in Victorova et al 16 It uses a DL-based navigation control to detect the centre of the spine, which is defined as spinous process tip, in real-time at each B-mode ultrasound frame; thus, there is no need for additional external sensors, such as a camera. The proposed robotic system can also adjust the probe orientation to keep the ultrasound probe normal to the surface and maintain good acoustic coupling with the back of the subject.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Comparison of ultrasound scanning for scoliosis assessment: Robotic versus manual

Victorova

Lau

Lee

et al. 2022

Robotics Computer Surgery

Self Cite

View full text Add to dashboard Cite

Background Ultrasound (US) imaging for scoliosis assessment is challenging for a non‐experienced operator. The robotic scanning was developed to follow a spinal curvature with deep learning and apply consistent forces to the patient's back. Methods Twenty three scoliosis patients were scanned with US device both, robotically and manually. Two human raters measured each subject's spinous process angles on robotic and manual coronal images. Results The robotic method showed high intra‐ (ICC > 0.85) and inter‐rater (ICC > 0.77) reliabilities. Compared with the manual method, the robotic approach showed no significant difference (p < 0.05) when measuring coronal deformity angles. The mean absolute deviation for intra‐rater analysis lies within an acceptable range from 0 to 5° for the minimum of 86% and maximum 97% of a total number of the measured angles. Conclusions This study demonstrated that scoliosis deformity angles measured on ultrasound images obtained with robotic scanning are comparable to those obtained by manual scanning.

show abstract

“…Further, Cheung et al [35,36] and Zheng et al [37] introduced a commercialised scoliosis assessment system Scolioscan for the three-dimensional (3D) spine reconstruction using freehand 2D T-US. Scolioscan was further used to study spinal curvatures in the coronal [38,39] and sagittal plane [40] and was recently equipped with a robotic arm for the automatic learning-based localisation of the spinous process [30]. Those studies have shown that 2D US measures of curvature are comparable with those obtained using X-ray and MRI based imaging methods, however, de Reuver et al [41] and Brink et al [42] showed that reconstructions based on 2D US typically underestimate the Cobb angle, indicating potentially relevant errors in the US image registration procedure.…”

Section: Introductionmentioning

confidence: 99%

Assessment of thoracic spinal curvatures in static postures using spatially tracked 3D ultrasound volumes: A proof-of-concept study

Meszaros-Beller¹,

Antico²,

Fontanarosa³

et al. 2022

Preprint

View full text Add to dashboard Cite

<div>Measurement of vertebral spinal motion is a difficult endeavor given the lack of reachable bony landmarks for placement of reflective markers for common optoelectronic systems and large skin movement artifacts along the spine affecting the accuracy of surface-mounted techniques. The objective of this proof-of-concept study was to develop an experimental framework to assess spinal curvatures with high accuracy by using ultrasound (US) imaging. A phantom spine model (T1-T12) immersed in water was scanned using both Magnetic resonance imaging (MRI) and three dimensional (3D) US. The US scans were obtained for the phantom spine in different postures while the US probe was localized by three electromagnetic tracking sensors (NDI system) attached to the probe head and later identified on the acquired US volumes via visual inspection. Spinal landmarks were selected on the US images and validated using US-MRI registration. Their position was then related to the position of the tracking sensors, enabling the precise localization of landmarks and reconstruction of spinal curvatures in a global reference frame. The obtained anatomical reconstructions were further refined using an automatic registration algorithm and validated by an experienced sonographer (ground-truth solution). Results of this study show that localized 3D US enables tracking of spinal landmarks and allows for an accurate reconstruction of static postures. A high reliability in sensor identification of 0.49 mm was found on average while the inter-observer variability was strongly correlated to the intra-observer error with maximum deviance of 0.8 mm. The NDI-based spine reconstruction had a mean error of 5.6 mm compared to the ground-truth, which is significantly lower than errors obtained by current gold standards (>10 mm). Combining US probe tracking and semi-automatic registration methods anatomical reconstructions comparable to clinical standards were obtained. This study implies that US holds the potential for advancing vertebral motion assessment and the reconstruction of spinal curvatures. In future, this could overcome limitations of marker-based approaches.</div>

show abstract

Follow the Curve: Robotic Ultrasound Navigation With Learning-Based Localization of Spinous Processes for Scoliosis Assessment

Cited by 15 publications

References 29 publications

Robot-assisted Ultrasound Reconstruction for Minimally Invasive Spine Surgery: from Bench-top to Pre-clinical Study

Robot-assisted Ultrasound Reconstruction for Minimally Invasive Spine Surgery: from Bench-top to Pre-clinical Study

Comparison of ultrasound scanning for scoliosis assessment: Robotic versus manual

Assessment of thoracic spinal curvatures in static postures using spatially tracked 3D ultrasound volumes: A proof-of-concept study

Contact Info

Product

Resources

About