Click here to

Session: Tracking Strategies [Return to Session]

A Smartphone-Based Surface Guided Radiation Therapy Tracking System for Respiratory Monitoring in Radiation Therapy

D Capaldi1*, M Axente2, A Yu3, L Skinner3, N Prionas1, E Hirata1, T Nano1, (1) University of California, San Francisco, San Francisco, CA, (2) Emory University School of Medicine, Atlanta, GA, (3) Stanford University, Palo Alto, CA


MO-H345-IePD-F5-6 (Monday, 7/11/2022) 3:45 PM - 4:15 PM [Eastern Time (GMT-4)]

Exhibit Hall | Forum 5

Purpose: Surface-guided radiation-therapy (SGRT) systems are becoming standard-of-care for patient setup and motion monitoring. However, commercial systems remain inaccessible to resource-limited clinics around the world. Alternative to current solutions, we have previously developed and evaluated the feasibility of an audiovisual feedback system that leverages depth information from the front facing TrueDepth sensor onboard iOS devices. More recently released iOS devices now have LiDAR capabilities on the back facing camera. The purpose of this study was to further develop and validate the platform using the back facing LiDAR camera.

Methods: The iOS application was developed in Swift and implemented on an iPhone 13 Pro® with a build-in the LiDAR camera system. The application contains different feature, such as 1) visualizing both the depth as well as the camera video feed, 2) selecting a region-of-interest (ROI) over the area that motion will be evaluated, 3) determining the angle of the plane that the ROI makes on the surface, 4) a chart displaying the average depth over time in the ROI, and 5) saving and exporting the motion traces as well as the surface map over the ROI. Tests were performed to 1) evaluate the depth measurement (depth:30-175cm) and 2) evaluate the object distance versus field-of-view (FOV) over a length of distances (FOV:10-40cm). Measurements were analyzed using linear regressions and Bland-Altman analysis

Results: Ground truth distances versus measured iOS distances show excellent agreement (r=1.000, p<0.0001; bias=-0.41±0.69cm, 95%-confidence-interval=−1.76cm,0.94cm). Similarly, FOV versus the depth measurement also show excellent agreement (r=1.000, p<0.0001; bias=-0.01±0.42cm, 95%-confidence-interval=−0.83cm,0.81cm).

Conclusion: We have demonstrated the accuracy of measuring depth with an iOS application. Future work will involve further testing and validating this device for SGRT applications as this work has the potential to provide a low-cost platform that could improve the dissemination and efficacy of radiation therapy in low-to-middle income countries.


Not Applicable / None Entered.


Not Applicable / None Entered.

Contact Email