Rapid deployment of a Monte Carlo simulation system using Diskless Remote Boot in Linux in a PACS environment

Yuan Jen Chang; Yan Lin Liu; Cheng Ting Shih; Shu Jun Chang; Jay Wu

doi:10.1117/12.2007731

Rapid deployment of a Monte Carlo simulation system using Diskless Remote Boot in Linux in a PACS environment

Yuan Jen Chang
, Yan Lin Liu
, Cheng Ting Shih
, Shu Jun Chang
, Jay Wu^*

^*Corresponding author for this work

Department of Biomedical Imaging and Radiological Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

The Monte Carlo (MC) technique has been widely used as the gold standard for interaction of radiation with matter in the fields of medical physics, radiation therapy, and nuclear medicine. However, MC simulation is time consuming and requires a lot of computational resources. Generally, a dedicated high performance computing cluster is use to improve efficiency, but it is costly and lacks of the ability to run routine errands in healthcare facilities. In this study, we proposed a method for rapid deployment of computing platform for MC simulation in the PACS environment using review workstations as computing nodes. The workstations were booted from the network and initialed a RAM disk as the boot sector. The simplified Linux operating system and the Monte Carlo N-Particle Transport Code Version 5 (MCNP5) were transferred from the DRBL (Diskless Remote Boot in Linux) server to each node automatically. The cluster computing environment can be established within four minutes. We compared a commercially available dedicated cluster with the DRBL cluster. The results showed that the commercial cluster had a slightly higher acceleration factor than the DRBL cluster. The simulation time of the commercial and the DRBL clusters for 2×10⁸ particle histories was 37,151 and 40,021 sec, respectively. When the number of rendezvous increased to 20, the maximum time differences between both clusters were 95 and 85 sec for the megabit and the gigabit switches. We conclude that the DRBL cluster can be quickly deployed to the non-workloaded review workstations in the PACS. Thus, the MC technique could be broadly used to enhance the research capability of radiological sciences in healthcare facilities.

Original language	English
Title of host publication	Medical Imaging 2013
Subtitle of host publication	Advanced PACS-Based Imaging Informatics and Therapeutic Applications
DOIs	https://doi.org/10.1117/12.2007731
State	Published - 2013
Event	Medical Imaging 2013: Advanced PACS-Based Imaging Informatics and Therapeutic Applications - Lake Buena Vista, FL, United States Duration: 12 Feb 2013 → 14 Feb 2013

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	8674
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2013: Advanced PACS-Based Imaging Informatics and Therapeutic Applications
Country/Territory	United States
City	Lake Buena Vista, FL
Period	12/02/13 → 14/02/13

Keywords

Cluster computing
DRBL
Monte Carlo simulation
PACS

Access to Document

10.1117/12.2007731

Cite this

Chang, Y. J., Liu, Y. L., Shih, C. T., Chang, S. J., & Wu, J. (2013). Rapid deployment of a Monte Carlo simulation system using Diskless Remote Boot in Linux in a PACS environment. In Medical Imaging 2013: Advanced PACS-Based Imaging Informatics and Therapeutic Applications Article 86740T (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 8674). https://doi.org/10.1117/12.2007731

@inproceedings{740a087299a8491990dffce01d5ef2e2,

title = "Rapid deployment of a Monte Carlo simulation system using Diskless Remote Boot in Linux in a PACS environment",

abstract = "The Monte Carlo (MC) technique has been widely used as the gold standard for interaction of radiation with matter in the fields of medical physics, radiation therapy, and nuclear medicine. However, MC simulation is time consuming and requires a lot of computational resources. Generally, a dedicated high performance computing cluster is use to improve efficiency, but it is costly and lacks of the ability to run routine errands in healthcare facilities. In this study, we proposed a method for rapid deployment of computing platform for MC simulation in the PACS environment using review workstations as computing nodes. The workstations were booted from the network and initialed a RAM disk as the boot sector. The simplified Linux operating system and the Monte Carlo N-Particle Transport Code Version 5 (MCNP5) were transferred from the DRBL (Diskless Remote Boot in Linux) server to each node automatically. The cluster computing environment can be established within four minutes. We compared a commercially available dedicated cluster with the DRBL cluster. The results showed that the commercial cluster had a slightly higher acceleration factor than the DRBL cluster. The simulation time of the commercial and the DRBL clusters for 2×108 particle histories was 37,151 and 40,021 sec, respectively. When the number of rendezvous increased to 20, the maximum time differences between both clusters were 95 and 85 sec for the megabit and the gigabit switches. We conclude that the DRBL cluster can be quickly deployed to the non-workloaded review workstations in the PACS. Thus, the MC technique could be broadly used to enhance the research capability of radiological sciences in healthcare facilities.",

keywords = "Cluster computing, DRBL, Monte Carlo simulation, PACS",

author = "Chang, \{Yuan Jen\} and Liu, \{Yan Lin\} and Shih, \{Cheng Ting\} and Chang, \{Shu Jun\} and Jay Wu",

year = "2013",

doi = "10.1117/12.2007731",

language = "English",

isbn = "9780819494481",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

booktitle = "Medical Imaging 2013",

note = "Medical Imaging 2013: Advanced PACS-Based Imaging Informatics and Therapeutic Applications ; Conference date: 12-02-2013 Through 14-02-2013",

}

Chang, YJ, Liu, YL, Shih, CT, Chang, SJ & Wu, J 2013, Rapid deployment of a Monte Carlo simulation system using Diskless Remote Boot in Linux in a PACS environment. in Medical Imaging 2013: Advanced PACS-Based Imaging Informatics and Therapeutic Applications., 86740T, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 8674, Medical Imaging 2013: Advanced PACS-Based Imaging Informatics and Therapeutic Applications, Lake Buena Vista, FL, United States, 12/02/13. https://doi.org/10.1117/12.2007731

Rapid deployment of a Monte Carlo simulation system using Diskless Remote Boot in Linux in a PACS environment. / Chang, Yuan Jen; Liu, Yan Lin; Shih, Cheng Ting et al.
Medical Imaging 2013: Advanced PACS-Based Imaging Informatics and Therapeutic Applications. 2013. 86740T (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 8674).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Rapid deployment of a Monte Carlo simulation system using Diskless Remote Boot in Linux in a PACS environment

AU - Chang, Yuan Jen

AU - Liu, Yan Lin

AU - Shih, Cheng Ting

AU - Chang, Shu Jun

AU - Wu, Jay

PY - 2013

Y1 - 2013

N2 - The Monte Carlo (MC) technique has been widely used as the gold standard for interaction of radiation with matter in the fields of medical physics, radiation therapy, and nuclear medicine. However, MC simulation is time consuming and requires a lot of computational resources. Generally, a dedicated high performance computing cluster is use to improve efficiency, but it is costly and lacks of the ability to run routine errands in healthcare facilities. In this study, we proposed a method for rapid deployment of computing platform for MC simulation in the PACS environment using review workstations as computing nodes. The workstations were booted from the network and initialed a RAM disk as the boot sector. The simplified Linux operating system and the Monte Carlo N-Particle Transport Code Version 5 (MCNP5) were transferred from the DRBL (Diskless Remote Boot in Linux) server to each node automatically. The cluster computing environment can be established within four minutes. We compared a commercially available dedicated cluster with the DRBL cluster. The results showed that the commercial cluster had a slightly higher acceleration factor than the DRBL cluster. The simulation time of the commercial and the DRBL clusters for 2×108 particle histories was 37,151 and 40,021 sec, respectively. When the number of rendezvous increased to 20, the maximum time differences between both clusters were 95 and 85 sec for the megabit and the gigabit switches. We conclude that the DRBL cluster can be quickly deployed to the non-workloaded review workstations in the PACS. Thus, the MC technique could be broadly used to enhance the research capability of radiological sciences in healthcare facilities.

AB - The Monte Carlo (MC) technique has been widely used as the gold standard for interaction of radiation with matter in the fields of medical physics, radiation therapy, and nuclear medicine. However, MC simulation is time consuming and requires a lot of computational resources. Generally, a dedicated high performance computing cluster is use to improve efficiency, but it is costly and lacks of the ability to run routine errands in healthcare facilities. In this study, we proposed a method for rapid deployment of computing platform for MC simulation in the PACS environment using review workstations as computing nodes. The workstations were booted from the network and initialed a RAM disk as the boot sector. The simplified Linux operating system and the Monte Carlo N-Particle Transport Code Version 5 (MCNP5) were transferred from the DRBL (Diskless Remote Boot in Linux) server to each node automatically. The cluster computing environment can be established within four minutes. We compared a commercially available dedicated cluster with the DRBL cluster. The results showed that the commercial cluster had a slightly higher acceleration factor than the DRBL cluster. The simulation time of the commercial and the DRBL clusters for 2×108 particle histories was 37,151 and 40,021 sec, respectively. When the number of rendezvous increased to 20, the maximum time differences between both clusters were 95 and 85 sec for the megabit and the gigabit switches. We conclude that the DRBL cluster can be quickly deployed to the non-workloaded review workstations in the PACS. Thus, the MC technique could be broadly used to enhance the research capability of radiological sciences in healthcare facilities.

KW - Cluster computing

KW - DRBL

KW - Monte Carlo simulation

KW - PACS

UR - https://www.scopus.com/pages/publications/84878385024

U2 - 10.1117/12.2007731

DO - 10.1117/12.2007731

M3 - Conference contribution

AN - SCOPUS:84878385024

SN - 9780819494481

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2013

T2 - Medical Imaging 2013: Advanced PACS-Based Imaging Informatics and Therapeutic Applications

Y2 - 12 February 2013 through 14 February 2013

ER -

Rapid deployment of a Monte Carlo simulation system using Diskless Remote Boot in Linux in a PACS environment

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this