Accelerating the design of probabilistic neural networks for computer aided diagnosis in mammography, employing graphics processing units

dc.contributor.author	Σιδηρόπουλος, Κωνσταντίνος	el
dc.contributor.author	Κάβουρας, Διονύσης Α.	el
dc.contributor.author	Παγώνης, Νικόλαος	el
dc.contributor.author	Δημητρόπουλος, Νικόλαος	el
dc.contributor.author	Stonham, John T.	en
dc.date.accessioned	2015-01-30T18:01:03Z
dc.date.available	2015-01-30T18:01:03Z
dc.date.issued	2015-01-30
dc.identifier.uri	http://hdl.handle.net/11400/5169
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	*
dc.source	http://e-jst.teiath.gr/	en
dc.subject	Nuclear medicine
dc.subject	Πυρηνική ιατρική
dc.subject	Probabilistic neural networks
dc.subject	Graphics processing units
dc.subject	Πιθανοτικά νευρωνικά δίκτυα
dc.subject	Μονάδες επεξεργασίας γραφικών
dc.title	Accelerating the design of probabilistic neural networks for computer aided diagnosis in mammography, employing graphics processing units	en
heal.type	journalArticle
heal.generalDescription	Special issue: Scientific papers presented on the 3nd International Conference on Experiments/Process/System Modeling/Simulation & Optimization in Athens, 8-11 July, 2009. Mini symposium on Medical Imaging, organized by G. Panayiotakis, I. Kandarakis, G. Fountos and I. Valais	en
heal.classification	Medicine
heal.classification	Medical physics
heal.classification	Ιατρική
heal.classification	Ιατρική φυσική
heal.classification	Technology
heal.classification	Τεχνολογία
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh00006614
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh85083001
heal.classificationURI	N/A-Ιατρική
heal.classificationURI	N/A-Ιατρική φυσική
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh85133147
heal.classificationURI	N/A-Τεχνολογία
heal.keywordURI	http://id.loc.gov/authorities/subjects/sh85093011
heal.language	en
heal.access	free
heal.recordProvider	Τεχνολογικό Εκπαιδευτικό Ίδρυμα Αθήνας. Σχολή Τεχνολογικών Εφαρμογών. Tμήμα Μηχανικών Βιοϊατρικής Τεχνολογίας	el
heal.publicationDate	2010
heal.bibliographicCitation	Sidiropoulos, K., Cavouras, D.A., Pagonis, N., Dimitropoulos, N. and Stonham, J.T. (2010). Accelerating the design of probabilistic neural networks for computer aided diagnosis in mammography, employing graphics processing units. "e-Journal of Science & Technology". [Online] 5(2): 49-54. Available from: http://e-jst.teiath.gr/	en
heal.abstract	The aim of this study is to propose a Probabilistic Neural Network (PNN) classifier system that can operate on a consumer-level graphics processing unit (GPU) and thus, harvest its tremendous parallel computation potential in order to accelerate the training phase. Therefore, the computationally intensive training of a PNN classifier system incorporating the exhaustive search of feature combinations and the leave-one-out techniques, was effectively ported on a medium class GPU device. Programming of the GPU was accomplished by means of the CUDA framework. The proposed system was tested on a real training dataset comprising 80 patterns, each consisting of 20 textural features extracted from digital mammograms (40 normal and 40 containing micro-calcifications) by an experienced physician. The developed GPU-based classifier was trained and the required time was measured. The latter was then compared with the respective training time of the same classifier running on a typical CPU and programmed in the C programming language. According to experimental results, the proposed GPU-based classifier achieved significantly higher training speed, outperforming the CPU-based system by a factor that ranged from 10 to 75 times.	en
heal.publisher	Νερατζής, Ηλίας	el
heal.publisher	Σιανούδης, Ιωάννης	el
heal.publisher	Βαλαής, Ιωάννης Γ.	el
heal.publisher	Φούντος, Γεώργιος Π.	el
heal.journalName	e-Journal of Science & Technology	en
heal.journalName	e-Περιοδικό Επιστήμης & Τεχνολογίας	el
heal.journalType	peer-reviewed
heal.fullTextAvailability	true