Accelerating Colonic Polyp Detection Using Commodity Graphics Hardware

David Williams; Valeriu Codreanu; Jos B.T.M. Roerdink; Po Yang; Baoquan Liu; Feng Dong; Alessandro Chiarini

Accelerating Colonic Polyp Detection Using Commodity Graphics Hardware

David Williams, Valeriu Codreanu, Jos B.T.M. Roerdink, Po Yang, Baoquan Liu, Feng Dong, Alessandro Chiarini

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic

5 Citations (Scopus)

318 Downloads (Pure)

Abstract

We present a parallel implementation of an algorithm for the detection of colonic polyps from CT data sets. This implementation is designed specifically to take advantage of the computational power available on modern Graphics Processing Units (GPUs), which significantly reduces the execution time to streamline the workflow of clinicians examining the data. We provide details about the changes which were made to the existing algorithm to suit the new target hardware, and perform tests which demonstrate that the results are a very close match to the reference implementation while being computed in a fraction of the time.

Original language	English
Title of host publication	EPRINTS-BOOK-TITLE
Publisher	University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science
Number of pages	6
ISBN (Print)	9781467352130
Publication status	Published - 2013

Keywords

GPU computing
Colon screening
Computer aided diagnosis

Access to Document

2013ProcICCMAWilliams.pdfFinal publisher's version, 372 KB

Handle.net

Persistent link

Cite this

@inbook{3137a16a756a4bbeb83de6bb7a3840b6,

title = "Accelerating Colonic Polyp Detection Using Commodity Graphics Hardware",

abstract = "We present a parallel implementation of an algorithm for the detection of colonic polyps from CT data sets. This implementation is designed specifically to take advantage of the computational power available on modern Graphics Processing Units (GPUs), which significantly reduces the execution time to streamline the workflow of clinicians examining the data. We provide details about the changes which were made to the existing algorithm to suit the new target hardware, and perform tests which demonstrate that the results are a very close match to the reference implementation while being computed in a fraction of the time.",

keywords = "GPU computing, Colon screening, Computer aided diagnosis",

author = "David Williams and Valeriu Codreanu and Roerdink, {Jos B.T.M.} and Po Yang and Baoquan Liu and Feng Dong and Alessandro Chiarini",

note = "Relation: http://www.rug.nl/research/jbi/ Rights: University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science",

year = "2013",

language = "English",

isbn = "9781467352130",

booktitle = "EPRINTS-BOOK-TITLE",

publisher = "University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science",

}

TY - CHAP

T1 - Accelerating Colonic Polyp Detection Using Commodity Graphics Hardware

AU - Williams, David

AU - Codreanu, Valeriu

AU - Roerdink, Jos B.T.M.

AU - Yang, Po

AU - Liu, Baoquan

AU - Dong, Feng

AU - Chiarini, Alessandro

N1 - Relation: http://www.rug.nl/research/jbi/ Rights: University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science

PY - 2013

Y1 - 2013

N2 - We present a parallel implementation of an algorithm for the detection of colonic polyps from CT data sets. This implementation is designed specifically to take advantage of the computational power available on modern Graphics Processing Units (GPUs), which significantly reduces the execution time to streamline the workflow of clinicians examining the data. We provide details about the changes which were made to the existing algorithm to suit the new target hardware, and perform tests which demonstrate that the results are a very close match to the reference implementation while being computed in a fraction of the time.

AB - We present a parallel implementation of an algorithm for the detection of colonic polyps from CT data sets. This implementation is designed specifically to take advantage of the computational power available on modern Graphics Processing Units (GPUs), which significantly reduces the execution time to streamline the workflow of clinicians examining the data. We provide details about the changes which were made to the existing algorithm to suit the new target hardware, and perform tests which demonstrate that the results are a very close match to the reference implementation while being computed in a fraction of the time.

KW - GPU computing

KW - Colon screening

KW - Computer aided diagnosis

M3 - Chapter

SN - 9781467352130

BT - EPRINTS-BOOK-TITLE

PB - University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science

ER -

Accelerating Colonic Polyp Detection Using Commodity Graphics Hardware

Abstract

Keywords

Access to Document

Handle.net

Fingerprint

Cite this