iBet uBet web content aggregator. Adding the entire web to your favor.
iBet uBet web content aggregator. Adding the entire web to your favor.



Link to original content: https://pubmed.ncbi.nlm.nih.gov/35965637/
Autonomous Scanning Target Localization for Robotic Lung Ultrasound Imaging - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Sep-Oct:2021:9467-9474.
doi: 10.1109/iros51168.2021.9635902. Epub 2021 Dec 16.

Autonomous Scanning Target Localization for Robotic Lung Ultrasound Imaging

Xihan Ma  1 , Ziming Zhang  2 , Haichong K Zhang  1   3
Affiliations

Autonomous Scanning Target Localization for Robotic Lung Ultrasound Imaging

Xihan Ma et al. Rep U S. 2021 Sep-Oct.

Abstract

Under the ceaseless global COVID-19 pandemic, lung ultrasound (LUS) is the emerging way for effective diagnosis and severeness evaluation of respiratory diseases. However, close physical contact is unavoidable in conventional clinical ultrasound, increasing the infection risk for health-care workers. Hence, a scanning approach involving minimal physical contact between an operator and a patient is vital to maximize the safety of clinical ultrasound procedures. A robotic ultrasound platform can satisfy this need by remotely manipulating the ultrasound probe with a robotic arm. This paper proposes a robotic LUS system that incorporates the automatic identification and execution of the ultrasound probe placement pose without manual input. An RGB-D camera is utilized to recognize the scanning targets on the patient through a learning-based human pose estimation algorithm and solve for the landing pose to attach the probe vertically to the tissue surface; A position/force controller is designed to handle intraoperative probe pose adjustment for maintaining the contact force. We evaluated the scanning area localization accuracy, motion execution accuracy, and ultrasound image acquisition capability using an upper torso mannequin and a realistic lung ultrasound phantom with healthy and COVID-19-infected lung anatomy. Results demonstrated the overall scanning target localization accuracy of 19.67 ± 4.92 mm and the probe landing pose estimation accuracy of 6.92 ± 2.75 mm in translation, 10.35 ± 2.97 deg in rotation. The contact force-controlled robotic scanning allowed the successful ultrasound image collection, capturing pathological landmarks.

PubMed Disclaimer

Figures

Fig. 1.
Fig. 1.
An example visualization of extracting chest region using Dense-Pose. a) shows DensePose output format. b) shows the anterior chest region mask overlaid on the input image. c) shows the vertical u coordinate of the mapping from each pixel on chest region to the SMPL model. d) shows the horizontal v coordinate of the same mapping. b)-d) are from our previous work in [29].
Fig. 2.
Fig. 2.
Mapping of a 2D target to a 3D pose. a) DensePose output from an input image. The red mask is the segmented chest area, R1 to R4 are the scanning regions in [5], the center of the white circles marked with 1 to 4 corresponds to the 2D scanning targets. b) The generated patch in image space. c) The deprojected patch in 3D and the calculation of one sub-plane normal vector V12 given by P1′P0′×P2′P0′. d) The averaged normal vector Vsum (dashed orange line) by summing all sub-plane normal (solid orange line) and its normalized unite vector Vavg (solid blue line).
Fig. 3.
Fig. 3.
Robot setup and coordinate frame convention. The left figure shows the robot’s home configuration and its coordinate frame definitions. The right figure shows the robot working under contact mode. Cd is the displacement along the normal. (red arrow represents x-aixs, green represents y-axis, blue represents z-axis)
Fig. 4.
Fig. 4.
System Integration. a) The hardware & software integration of the proposed RUS system. b) The workflow of the system to perform the LUS scanning. c) The robot configuration when scanning each of the four anterior targets.
Fig. 5.
Fig. 5.
Validation of 2D scanning targets. VERT and HORIZ correspond to vertical and horizontal direction of the test table respectively. 0 offset is the default location to place the mannequin. The error bar reflects the standard deviation.
Fig. 6.
Fig. 6.
Validation of 3D probe pose. a) The virtual gird overlay placed on top of the mannequin, where cell (1,2), (1,3), (2,2), (2,3) cover the four anterior targets respectively. b) The error of the targets’ 3D position (top) and the error of their normal vectors (bottom). The error bar reflects the standard deviation.
Fig. 7.
Fig. 7.
Recorded robot motion when executing the trajectory for targets 1 to 4 a) The translational error relative to the robot base. b) The rotational error relative to the robot base.
Fig. 8.
Fig. 8.
Results scanning the lung phantom. a) The lung phantom picture with the two manually selected scanning targets labeled as A and B, respectively. The target A simulates the lung of healthy patients and the target B simulates that of the COVID-19 patients. b) The logged end-effector force when scanning targets A and B during the presence of respiratory motion. c) Example US images collected at target A and target B, respectively.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Fang Y et al., “Sensitivity of Chest CT for COVID-19: Comparison to RT-PCR,” Radiology vol. 296 (2), pp. E115–E117, 2020. - PMC - PubMed
    1. Ayebare RR, Flick R, Okware S, Bodo B, and Lamorde M, “Adoption of COVID-19 triage strategies for low-income settings,” Lancet Respir. Med, vol. 8 (4), p. e22, 2020. - PMC - PubMed
    1. Xia Y, Ying Y, Wang S, Li W, and Shen H, “Effectiveness of lung ultrasonography for diagnosis of pneumonia in adults: A systematic review and meta-analysis,” J. Thorac. Dis, vol. 8, pp. 2822–2831, 2016. - PMC - PubMed
    1. Smith MJ, Hayward SA, Innes SM, and Miller ASC, “Point-of-care lung ultrasound in patients with COVID -19 – a narrative review,” Anaesthesia, vol. 75, no. 8, pp. 1096–1104, 2020. - PMC - PubMed
    1. Lichtenstein DA, “BLUE-Protocol and FALLS-Protocol: Two applications of lung ultrasound in the critically ill,” Chest, vol. 147, no. 6, pp. 1659–1670, 2015. - PubMed

LinkOut - more resources