SAPPHIRE: A toolkit for building efficient stream programs for medical video analysis

Sean R. Stanek, Wallapak Tavanapong, Johnny Wong, JungHwan Oh, Ruwan D. Nawarathna, Jayantha Muthukudage, Piet C. de Groen

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

This paper describes the design and implementation of SAPPHIRE - a novel middleware and software development kit for stream programing on a heterogeneous system of multi-core multi-CPUs with optional hardware accelerators such as graphics processing unit (GPU). A stream program consists of a set of tasks where the same tasks are repeated over multiple iterations of data (e.g., video frames). Examples of such programs are video analysis applications for computer-aided diagnosis and computer-assisted surgeries. Our design goal is to reduce the implementation efforts and ease collaborative software development of stream programs while supporting efficient execution of the programs on the target hardware. To validate the toolkit, we implemented EM-Automated-RT software with the toolkit and reported our experience. EM-Automated-RT performs real-time video analysis for quality of a colonoscopy procedure and provides visual feedback to assist the endoscopist to achieve optimal inspection of the colon during the procedure. The software has been deployed in a hospital setting to conduct a clinical trial.

Original languageEnglish (US)
Pages (from-to)407-421
Number of pages15
JournalComputer Methods and Programs in Biomedicine
Volume112
Issue number3
DOIs
StatePublished - Dec 2013

Fingerprint

Software engineering
Software
Computer aided diagnosis
Middleware
Surgery
Computer hardware
Particle accelerators
Program processors
Computer systems
Inspection
Computer-Assisted Surgery
Feedback
Hardware
Sensory Feedback
Program Development
Colonoscopy
Colon
Clinical Trials
Graphics processing unit

Keywords

  • Medical video analysis
  • Multi-core multi CPUs
  • Software development kit
  • Stream programs

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Health Informatics

Cite this

Stanek, S. R., Tavanapong, W., Wong, J., Oh, J., Nawarathna, R. D., Muthukudage, J., & de Groen, P. C. (2013). SAPPHIRE: A toolkit for building efficient stream programs for medical video analysis. Computer Methods and Programs in Biomedicine, 112(3), 407-421. https://doi.org/10.1016/j.cmpb.2013.07.028

SAPPHIRE : A toolkit for building efficient stream programs for medical video analysis. / Stanek, Sean R.; Tavanapong, Wallapak; Wong, Johnny; Oh, JungHwan; Nawarathna, Ruwan D.; Muthukudage, Jayantha; de Groen, Piet C.

In: Computer Methods and Programs in Biomedicine, Vol. 112, No. 3, 12.2013, p. 407-421.

Research output: Contribution to journalArticle

Stanek, SR, Tavanapong, W, Wong, J, Oh, J, Nawarathna, RD, Muthukudage, J & de Groen, PC 2013, 'SAPPHIRE: A toolkit for building efficient stream programs for medical video analysis', Computer Methods and Programs in Biomedicine, vol. 112, no. 3, pp. 407-421. https://doi.org/10.1016/j.cmpb.2013.07.028
Stanek, Sean R. ; Tavanapong, Wallapak ; Wong, Johnny ; Oh, JungHwan ; Nawarathna, Ruwan D. ; Muthukudage, Jayantha ; de Groen, Piet C. / SAPPHIRE : A toolkit for building efficient stream programs for medical video analysis. In: Computer Methods and Programs in Biomedicine. 2013 ; Vol. 112, No. 3. pp. 407-421.
@article{6e8519a3546a424db09e85ee6510049e,
title = "SAPPHIRE: A toolkit for building efficient stream programs for medical video analysis",
abstract = "This paper describes the design and implementation of SAPPHIRE - a novel middleware and software development kit for stream programing on a heterogeneous system of multi-core multi-CPUs with optional hardware accelerators such as graphics processing unit (GPU). A stream program consists of a set of tasks where the same tasks are repeated over multiple iterations of data (e.g., video frames). Examples of such programs are video analysis applications for computer-aided diagnosis and computer-assisted surgeries. Our design goal is to reduce the implementation efforts and ease collaborative software development of stream programs while supporting efficient execution of the programs on the target hardware. To validate the toolkit, we implemented EM-Automated-RT software with the toolkit and reported our experience. EM-Automated-RT performs real-time video analysis for quality of a colonoscopy procedure and provides visual feedback to assist the endoscopist to achieve optimal inspection of the colon during the procedure. The software has been deployed in a hospital setting to conduct a clinical trial.",
keywords = "Medical video analysis, Multi-core multi CPUs, Software development kit, Stream programs",
author = "Stanek, {Sean R.} and Wallapak Tavanapong and Johnny Wong and JungHwan Oh and Nawarathna, {Ruwan D.} and Jayantha Muthukudage and {de Groen}, {Piet C.}",
year = "2013",
month = "12",
doi = "10.1016/j.cmpb.2013.07.028",
language = "English (US)",
volume = "112",
pages = "407--421",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",
number = "3",

}

TY - JOUR

T1 - SAPPHIRE

T2 - A toolkit for building efficient stream programs for medical video analysis

AU - Stanek, Sean R.

AU - Tavanapong, Wallapak

AU - Wong, Johnny

AU - Oh, JungHwan

AU - Nawarathna, Ruwan D.

AU - Muthukudage, Jayantha

AU - de Groen, Piet C.

PY - 2013/12

Y1 - 2013/12

N2 - This paper describes the design and implementation of SAPPHIRE - a novel middleware and software development kit for stream programing on a heterogeneous system of multi-core multi-CPUs with optional hardware accelerators such as graphics processing unit (GPU). A stream program consists of a set of tasks where the same tasks are repeated over multiple iterations of data (e.g., video frames). Examples of such programs are video analysis applications for computer-aided diagnosis and computer-assisted surgeries. Our design goal is to reduce the implementation efforts and ease collaborative software development of stream programs while supporting efficient execution of the programs on the target hardware. To validate the toolkit, we implemented EM-Automated-RT software with the toolkit and reported our experience. EM-Automated-RT performs real-time video analysis for quality of a colonoscopy procedure and provides visual feedback to assist the endoscopist to achieve optimal inspection of the colon during the procedure. The software has been deployed in a hospital setting to conduct a clinical trial.

AB - This paper describes the design and implementation of SAPPHIRE - a novel middleware and software development kit for stream programing on a heterogeneous system of multi-core multi-CPUs with optional hardware accelerators such as graphics processing unit (GPU). A stream program consists of a set of tasks where the same tasks are repeated over multiple iterations of data (e.g., video frames). Examples of such programs are video analysis applications for computer-aided diagnosis and computer-assisted surgeries. Our design goal is to reduce the implementation efforts and ease collaborative software development of stream programs while supporting efficient execution of the programs on the target hardware. To validate the toolkit, we implemented EM-Automated-RT software with the toolkit and reported our experience. EM-Automated-RT performs real-time video analysis for quality of a colonoscopy procedure and provides visual feedback to assist the endoscopist to achieve optimal inspection of the colon during the procedure. The software has been deployed in a hospital setting to conduct a clinical trial.

KW - Medical video analysis

KW - Multi-core multi CPUs

KW - Software development kit

KW - Stream programs

UR - http://www.scopus.com/inward/record.url?scp=84885429170&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885429170&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2013.07.028

DO - 10.1016/j.cmpb.2013.07.028

M3 - Article

C2 - 24001925

AN - SCOPUS:84885429170

VL - 112

SP - 407

EP - 421

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

IS - 3

ER -