Premium
MO‐FG‐202‐01: A Fast Yet Sensitive EPID‐Based Real‐Time Treatment Verification System
Author(s) -
Ahmad M,
Nourzadeh H,
Neal B,
Watkins W,
Siebers J
Publication year - 2016
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.4957303
Subject(s) - image guided radiation therapy , dicom , computer science , truebeam , computer vision , software , medical imaging , attenuation , artificial intelligence , image resolution , linear particle accelerator , optics , physics , beam (structure) , programming language
Purpose: To create a real‐time EPID‐based treatment verification system which robustly detects treatment delivery and patient attenuation variations. Methods: Treatment plan DICOM files sent to the record‐and‐verify system are captured and utilized to predict EPID images for each planned control point using a modified GPU‐based digitally reconstructed radiograph algorithm which accounts for the patient attenuation, source energy fluence, source size effects, and MLC attenuation. The DICOM and predicted images are utilized by our C++ treatment verification software which compares EPID acquired 1024×768 resolution frames acquired at ∼8.5hz from Varian Truebeam™ system. To maximize detection sensitivity, image comparisons determine (1) if radiation exists outside of the desired treatment field; (2) if radiation is lacking inside the treatment field; (3) if translations, rotations, and magnifications of the image are within tolerance. Acquisition was tested with known test fields and prior patient fields. Error detection was tested in real‐time and utilizing images acquired during treatment with another system. Results: The computational time of the prediction algorithms, for a patient plan with 350 control points and 60×60×42cm^3 CT volume, is 2–3minutes on CPU and <27 seconds on GPU for 1024×768 images. The verification software requires a maximum of ∼9ms and ∼19ms for 512×384 and 1024×768 resolution images, respectively, to perform image analysis and dosimetric validations. Typical variations in geometric parameters between reference and the measured images are 0.32°for gantry rotation, 1.006 for scaling factor, and 0.67mm for translation. For excess out‐of‐field/missing in‐field fluence, with masks extending 1mm (at isocenter) from the detected aperture edge, the average total in‐field area missing EPID fluence was 1.5mm2 the out‐of‐field excess EPID fluence was 8mm^2, both below error tolerances. Conclusion: A real‐time verification software, with EPID images prediction algorithm, was developed. The system is capable of performing verifications between frames acquisitions and identifying source(s) of any out‐of‐tolerance variations. This work was supported in part by Varian Medical Systems.