skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: SU-G-JeP4-01: An Assessment of a Microsoft Kinect V2 Sensor for Voluntary Breath-Hold Monitoring in Radiotherapy

Abstract

Purpose: To determine whether the Microsoft Kinect Version 2 (Kinect v2), a commercial off-the-shelf (COTS) depth sensors designed for entertainment purposes, were robust to the radiotherapy treatment environment and could be suitable for monitoring of voluntary breath-hold compliance. This could complement current visual monitoring techniques, and be useful for heart sparing left breast radiotherapy. Methods: In-house software to control Kinect v2 sensors, and capture output information, was developed using the free Microsoft software development kit, and the Cinder creative coding C++ library. Each sensor was used with a 12m USB 3.0 active cable. A solid water block was used as the object. The depth accuracy and precision of the sensors was evaluated by comparing Kinect reported distance to the object with a precision laser measurement across a distance range of 0.6m to 2.0 m. The object was positioned on a high-precision programmable motion platform and moved in two programmed motion patterns and Kinect reported distance logged. Robustness to the radiation environment was tested by repeating all measurements with a linear accelerator operating over a range of pulse repetition frequencies (6Hz to 400Hz) and dose rates 50 to 1500 monitor units (MU) per minute. Results: The complex, consistent relationship between truemore » and measured distance was unaffected by the radiation environment, as was the ability to detect motion. Sensor precision was < 1 mm and the accuracy between 1.3 mm and 1.8 mm when a distance correction was applied. Both motion patterns were tracked successfully with a root mean squared error (RMSE) of 1.4 and 1.1 mm respectively. Conclusion: Kinect v2 sensors are capable of tracking pre-programmed motion patterns with an accuracy <2 mm and appear robust to the radiotherapy treatment environment. A clinical trial using Kinect v2 sensor for monitoring voluntary breath hold has ethical approval and is open to recruitment. The authors are supported by a National Institute of Health Research (NIHR) Career Development Fellowship (CDF-2013-06-005). Microsoft Corporation donated three sensors. The views expressed in this publication are those of the author(s) and not necessarily those of the NHS, the National Institute for Health Research or the Department of Health.« less

Authors:
;  [1]
  1. The Royal Marsden NHS Foundation Trust, Sutton, London (United Kingdom)
Publication Date:
OSTI Identifier:
22649451
Resource Type:
Journal Article
Resource Relation:
Journal Name: Medical Physics; Journal Volume: 43; Journal Issue: 6; Other Information: (c) 2016 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; 61 RADIATION PROTECTION AND DOSIMETRY; ACCURACY; CLINICAL TRIALS; COMPUTER CODES; DISTANCE; DOSE RATES; LINEAR ACCELERATORS; MAMMARY GLANDS; MONITORING; MONITORS; PARTICLE TRACKS; RADIOTHERAPY; SENSORS

Citation Formats

Edmunds, D, and Donovan, E. SU-G-JeP4-01: An Assessment of a Microsoft Kinect V2 Sensor for Voluntary Breath-Hold Monitoring in Radiotherapy. United States: N. p., 2016. Web. doi:10.1118/1.4957111.
Edmunds, D, & Donovan, E. SU-G-JeP4-01: An Assessment of a Microsoft Kinect V2 Sensor for Voluntary Breath-Hold Monitoring in Radiotherapy. United States. doi:10.1118/1.4957111.
Edmunds, D, and Donovan, E. 2016. "SU-G-JeP4-01: An Assessment of a Microsoft Kinect V2 Sensor for Voluntary Breath-Hold Monitoring in Radiotherapy". United States. doi:10.1118/1.4957111.
@article{osti_22649451,
title = {SU-G-JeP4-01: An Assessment of a Microsoft Kinect V2 Sensor for Voluntary Breath-Hold Monitoring in Radiotherapy},
author = {Edmunds, D and Donovan, E},
abstractNote = {Purpose: To determine whether the Microsoft Kinect Version 2 (Kinect v2), a commercial off-the-shelf (COTS) depth sensors designed for entertainment purposes, were robust to the radiotherapy treatment environment and could be suitable for monitoring of voluntary breath-hold compliance. This could complement current visual monitoring techniques, and be useful for heart sparing left breast radiotherapy. Methods: In-house software to control Kinect v2 sensors, and capture output information, was developed using the free Microsoft software development kit, and the Cinder creative coding C++ library. Each sensor was used with a 12m USB 3.0 active cable. A solid water block was used as the object. The depth accuracy and precision of the sensors was evaluated by comparing Kinect reported distance to the object with a precision laser measurement across a distance range of 0.6m to 2.0 m. The object was positioned on a high-precision programmable motion platform and moved in two programmed motion patterns and Kinect reported distance logged. Robustness to the radiation environment was tested by repeating all measurements with a linear accelerator operating over a range of pulse repetition frequencies (6Hz to 400Hz) and dose rates 50 to 1500 monitor units (MU) per minute. Results: The complex, consistent relationship between true and measured distance was unaffected by the radiation environment, as was the ability to detect motion. Sensor precision was < 1 mm and the accuracy between 1.3 mm and 1.8 mm when a distance correction was applied. Both motion patterns were tracked successfully with a root mean squared error (RMSE) of 1.4 and 1.1 mm respectively. Conclusion: Kinect v2 sensors are capable of tracking pre-programmed motion patterns with an accuracy <2 mm and appear robust to the radiotherapy treatment environment. A clinical trial using Kinect v2 sensor for monitoring voluntary breath hold has ethical approval and is open to recruitment. The authors are supported by a National Institute of Health Research (NIHR) Career Development Fellowship (CDF-2013-06-005). Microsoft Corporation donated three sensors. The views expressed in this publication are those of the author(s) and not necessarily those of the NHS, the National Institute for Health Research or the Department of Health.},
doi = {10.1118/1.4957111},
journal = {Medical Physics},
number = 6,
volume = 43,
place = {United States},
year = 2016,
month = 6
}
  • Purpose: To analyze tumor position reproducibility of feedback-guided voluntary deep inspiration breath-hold (FGBH) gating for cone beam computed tomography (CBCT)-based stereotactic body radiotherapy (SBRT). Methods and materials: Thirteen early-stage lung cancer patients eligible for SBRT with tumor motion of >1cm were evaluated for FGBH-gated treatment. Multiple FGBH CTs were acquired at simulation, and single FGBH CBCTs were also acquired prior to each treatment. Simulation CTs and treatment CBCTs were analyzed to quantify reproducibility of tumor positions during FGBH. Benefits of FGBH gating compared to treatment during free breathing, as well treatment with gating at exhalation, were examined for lung sparing,more » motion margins, and reproducibility of gross tumor volume (GTV) position relative to nonmoving anatomy. Results: FGBH increased total lung volumes by 1.5 times compared to free breathing, resulting in a proportional drop in total lung volume receiving 10 Gy or more. Intra- and inter-FGBH reproducibility of GTV centroid positions at simulation were 1.0 {+-} 0.5 mm, 1.3 {+-} 1.0 mm, and 0.6 {+-} 0.4 mm in the anterior-posterior (AP), superior-inferior (SI), and left-right lateral (LR) directions, respectively, compared to more than 1 cm of tumor motion at free breathing. During treatment, inter-FGBH reproducibility of the GTV centroid with respect to bony anatomy was 1.2 {+-} 0.7 mm, 1.5 {+-} 0.8 mm, and 1.0 {+-} 0.4 mm in the AP, SI, and LR directions. In addition, the quality of CBCTs was improved due to elimination of motion artifacts, making this technique attractive for poorly visualized tumors, even with small motion. Conclusions: The extent of tumor motion at normal respiration does not influence the reproducibility of the tumor position under breath hold conditions. FGBH-gated SBRT with CBCT can improve the reproducibility of GTV centroids, reduce required margins, and minimize dose to normal tissues in the treatment of mobile tumors.« less
  • Purpose: Voluntary deep inhalation breath hold (VDIBH) reduces heart dose during left breast irradiation. We present results of the first study performed to quantify reproducibility of breath hold using bony anatomy, heart position, and heart dose for VDIBH patients at treatment table. Methods and Materials: Data from 10 left breast cancer patients undergoing VDIBH whole-breast irradiation were analyzed. Two computed tomography (CT) scans, free breathing (FB) and VDIBH, were acquired to compare dose to critical structures. Pretreatment weekly kV orthogonal images and tangential ports were acquired. The displacement difference from spinal cord to sternum across the isocenter between coregistered planningmore » Digitally Reconstructed Radiographs (DRRs) and kV imaging of bony thorax is a measure of breath hold reproducibility. The difference between bony coregistration and heart coregistration was the measured heart shift if the patient is aligned to bony anatomy. Results: Percentage of dose reductions from FB to VDIBH: mean heart dose (48%, SD 19%, p = 0.002), mean LAD dose (43%, SD 19%, p = 0.008), and maximum left anterior descending (LAD) dose (60%, SD 22%, p = 0.008). Average breath hold reproducibility using bony anatomy across the isocenter along the anteroposterior (AP) plane from planning to treatment is 1 (range, 0-3; SD, 1) mm. Average heart shifts with respect to bony anatomy between different breath holds are 2 {+-} 3 mm inferior, 1 {+-} 2 mm right, and 1 {+-} 3 mm posterior. Percentage dose changes from planning to delivery: mean heart dose (7%, SD 6%); mean LAD dose, ((9%, SD 7%)S, and maximum LAD dose, (11%, SD 11%) SD 11%, p = 0.008). Conclusion: We observed excellent three-dimensional bony registration between planning and pretreatment imaging. Reduced delivered dose to heart and LAD is maintained throughout VDIBH treatment.« less
  • Purpose: To evaluate the reproducibility of target position using moderate voluntary breath-hold during liver stereotactic ablative radiotherapy (SABR). Methods: Two patients who underwent liver SABR on a Varian TrueBeam STx linac were used for this study. Fiducial markers were placed in and around the target in the liver as surrogates for the target position and motion. GTVs were contoured by assessing tumor extent on contrast enhanced CT. The PTV was created from the GTV by adding 2 mm margins to account for the residual motion during breath-holds. A portable biofeedback system was used to facilitate the breath-hold to a reproduciblemore » position. The Varian RPM system was used for gating the linac. Proceeding each treatment, orthogonal kV pairs were taken, and alignment to nearby bony anatomy was performed. Then the breath-hold CBCT was acquired to align the fiducial markers. On-line fluoroscopy was used to fine-tune the breath-hold gating thresholds to correlate with the positions of the fiducial markers. The inter-fraction reproducibility of the target was evaluated by the offsets of the daily breath-hold CBCTs from the paired kV matches as a direct measure of the target position relative to the bony anatomy. The intra-fraction reproducibility of the target position was assessed by the gated window of the RPM marker block for each fraction. Results: The absolute mean offsets between the CBCT and paired kV matches in the vertical, longitudinal, and lateral directions were 0.06 cm, 0.10 cm, and 0.06 cm for patient 1, and 0.37 cm, 0.62 cm, and 0.09 cm for patient 2. The gated window of the RPM marker block for the breath-hold for each fraction was within 0.63 ± 0.16 cm and 0.59 ± 0.12 cm for patients 1 and 2, respectively. Conclusion: Moderate voluntary breath-hold showed good inter- and intra-fraction reproducibility of target position during liver SABR.« less
  • Purpose: The voluntary breath-hold (BH) technique is a simple method to control the respiration-related motion of a tumor during irradiation. However, the abdominal and chest wall position may not be accurately reproduced using the BH technique. The purpose of this study was to examine whether visual feedback can reduce the fluctuation in wall motion during BH using a new respiratory monitoring device. Methods and Materials: We developed a laser-based BH monitoring and visual feedback system. For this study, five healthy volunteers were enrolled. The volunteers, practicing abdominal breathing, performed shallow end-expiration BH (SEBH), shallow end-inspiration BH (SIBH), and deep end-inspirationmore » BH (DIBH) with or without visual feedback. The abdominal and chest wall positions were measured at 80-ms intervals during BHs. Results: The fluctuation in the chest wall position was smaller than that of the abdominal wall position. The reproducibility of the wall position was improved by visual feedback. With a monitoring device, visual feedback reduced the mean deviation of the abdominal wall from 2.1 {+-} 1.3 mm to 1.5 {+-} 0.5 mm, 2.5 {+-} 1.9 mm to 1.1 {+-} 0.4 mm, and 6.6 {+-} 2.4 mm to 2.6 {+-} 1.4 mm in SEBH, SIBH, and DIBH, respectively. Conclusions: Volunteers can perform the BH maneuver in a highly reproducible fashion when informed about the position of the wall, although in the case of DIBH, the deviation in the wall position remained substantial.« less
  • Current techniques to acquire patient surface data are often very expensive and lack flexibility. In this study, the use of the Microsoft Kinect to reliably acquire 3D scans of patient surface is investigated. A design is presented to make the system easily applicable to the clinic. Potential applications of the device to radiotherapy are also presented. Scan reproducibility was tested by repeatedly scanning an anthropomorphic phantom. Scan accuracy was tested by comparing Kinect scans to the surface extracted from a CT dataset of a Rando® anthropomorphic phantom, which was considered as the true reference surface. Average signed distances of 0.12more » ± 2.34 mm and 0.13 ± 2.04 mm were obtained between the compared surfaces for reproducibility and accuracy respectively. This is conclusive, since it indicates that the variations observed come largely from noise distributed around an average distance close to 0 mm. Moreover, the range of the noise is small enough for the system to reliably capture a patient's surface. A system was also designed using two Kinects used together to acquire 3D surfaces in a quick and stable way that is applicable to the clinic. Finally, applications of the device to radiotherapy are demonstrated. Its use to detect local positioning errors is presented, where small local variations difficult to see with the naked eye are clearly visible. The system was also used to predict collisions using gantry and patient scans and thus ensure the safety of unconventional trajectories.« less