Author: Mustapha, B.
Paper Title Page
MO3I1 Developments towards a Compact Carbon Ion Linac for Cancer Therapy 14
 
  • B. Mustapha, D.A. Meyer, A. Nassiri, Y. Yang
    ANL, Lemont, Illinois, USA
  • R.B. Agustsson, A. Araujo, S.V. Kutsaev, A.Yu. Smirnov
    RadiaBeam, Santa Monica, California, USA
 
  Funding: This work was supported by the U.S. Department of Energy, Office of Nuclear Physics, under Contract No. DE-AC02-06CH11357 and Office of High Energy Physics SBIR/STTR Award DE-SC0015717.
Hadron therapy offers improved localization of the dose to the tumor and much improved sparing of healthy tissues, compared to traditional X-ray therapy. Combined proton/carbon therapy can achieve the most precise dose confinement to the tumor. Moreover, recent studies indicated that adding FLASH capability to such system may provide significant breakthrough in cancer treatment. The Advanced Compact Carbon Ion Linac (ACCIL) is a conceptual design for a compact ion linac based on high-gradient accelerating structures operating in the S-band frequency range. Thanks to this innovation, the footprint of this accelerator is only 45 m, while its capabilities are well beyond the current state of the art for hadron therapy machines and include: operation up to 1000 pulses per second, pulse to pulse energy variation to treat moving tumors in layer-by-layer regime. ACCIL is capable of accelerating all ions with mass-to-charge ratio A/q ~ 2 to a full energy of 450 MeV/u, and that includes protons, helium, carbon, oxygen and neon. With very short beam pulses of ~ 1 ’s and high instantaneous dose delivery, ACCIL is capable of delivering FLASH-like doses (>100 Gy/sec) for most ion species. In close collaboration between Argonne and Radiabeam, we have developed different design options and prototypes of the high-gradient structures needed for ACCIL. Following an overview of the ACCIL design and its capabilities, the most recent results from the high-gradient structure R&D and future plans will be presented and discussed.
 
slides icon Slides MO3I1 [3.259 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-HIAT2022-MO3I1  
About • Received ※ 27 June 2022 — Revised ※ 10 August 2022 — Accepted ※ 05 September 2022 — Issue date ※ 05 September 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TH1I2 Reinforcement Learning and Bayesian Optimization for Ion Linac Operations 130
 
  • J.L. Martinez Marin, B.R. Blomberg, K.J. Bunnell, G.M. Dunn, E. Letcher, B. Mustapha, D. Stanton
    ANL, Lemont, Illinois, USA
 
  Funding: This work was supported by the U.S. Department of Energy, under Contract No. DE-AC02-06CH11357. This research used the ATLAS facility, which is a DOE Office of Nuclear Physics User Facility.
The use of artificial intelligence can significantly reduce the time needed to tune an accelerator system such as the Argonne Tandem Linear Accelerator System (ATLAS) where a new beam is tuned once or twice a week. After establishing automatic data collection procedures and having analysed the data, machine learning models were developed and tested to tune subsections of the linac. Models based on Reinforcement Learning (RL) and Bayesian Optimization (BO) were developed, their respec-tive results are discussed and compared. RL and BO are well known AI techniques, often used for control systems. The results were obtained for a subsection of ATLAS that contains complex elements such as the radio-frequency quadrupole (RFQ). The models will be later generalized to the whole ATLAS linac, and similar models can be devel-oped for any accelerator with a modern control system.
 
slides icon Slides TH1I2 [4.617 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-HIAT2022-TH1I2  
About • Received ※ 09 July 2022 — Revised ※ 10 August 2022 — Accepted ※ 19 September 2022 — Issue date ※ 19 September 2022
Cite • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)