Use of machine learning in CARNA proton imager

Gabriel Varney; Catherine Dema; Burak E. Gul; Collin J. Wilkinson; Ugur Akgun

doi:10.1117/12.2512565

1 March 2019 Use of machine learning in CARNA proton imager

Gabriel Varney, Catherine Dema, Burak E. Gul, Collin J. Wilkinson, Ugur Akgun

Proceedings Volume 10948, Medical Imaging 2019: Physics of Medical Imaging; 109485P (2019) https://doi.org/10.1117/12.2512565
Event: SPIE Medical Imaging, 2019, San Diego, California, United States

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.

Citation Download Citation

Gabriel Varney, Catherine Dema, Burak E. Gul, Collin J. Wilkinson, and Ugur Akgun "Use of machine learning in CARNA proton imager", Proc. SPIE 10948, Medical Imaging 2019: Physics of Medical Imaging, 109485P (1 March 2019); https://doi.org/10.1117/12.2512565

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available