Share Email Print
cover

Proceedings Paper

Use of machine learning in CARNA proton imager
Author(s): Gabriel Varney; Catherine Dema; Burak E. Gul; Collin J. Wilkinson; Ugur Akgun
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Proton therapy has potential for high precision dose delivery, provided that high accuracy is achieved in imaging. Currently, X-ray based techniques are preferred for imaging prior to proton therapy, and the stopping power conversion tables cause irreducible uncertainty. The proposed proton imaging methods aim to reduce this source of error, as well as lessen the radiation exposure of the patient. CARNA is a homogeneous compact calorimeter that utilizes a novel highdensity scintillating glass as an active medium. The compact design and unique geometry of the calorimeter eliminate the need for a tracker system and allow it to be directly attached to a gantry. Thus, giving CARNA potential to be used for insitu imaging during the hadron therapy, possibly to detect the prompt gammas. The novel glass development and the traditional image reconstruction studies performed with CARNA have been reported before. However, to improve the image reconstruction, a machine learning implementation with CARNA is reported. A proof-of-concept Artificial Neural Network, is shown to efficiently predict the density and the shape of the tumors.

Paper Details

Date Published: 1 March 2019
PDF: 9 pages
Proc. SPIE 10948, Medical Imaging 2019: Physics of Medical Imaging, 109485P (1 March 2019); doi: 10.1117/12.2512565
Show Author Affiliations
Gabriel Varney, Coe College (United States)
Catherine Dema, William Jewell College (United States)
Burak E. Gul, Coe College (United States)
Collin J. Wilkinson, Penn State Univ. (United States)
Ugur Akgun, Coe College (United States)


Published in SPIE Proceedings Vol. 10948:
Medical Imaging 2019: Physics of Medical Imaging
Taly Gilat Schmidt; Guang-Hong Chen; Hilde Bosmans, Editor(s)

© SPIE. Terms of Use
Back to Top