Multimodality GPU-based computer-assisted diagnosis of breast cancer using ultrasound and digital mammography images

dc.contributor.author	Σιδηρόπουλος, Κωνσταντίνος	el
dc.contributor.author	Κωστόπουλος, Σπύρος	el
dc.contributor.author	Γκλώτσος, Δημήτρης	el
dc.contributor.author	Αθανασιάδης, Εμμανουήλ	el
dc.contributor.author	Δημητρόπουλος, Νίκος	el
dc.date.accessioned	2015-06-07T15:02:37Z
dc.date.available	2015-06-07T15:02:37Z
dc.date.issued	2015-06-07
dc.identifier.uri	http://hdl.handle.net/11400/15476
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://link.springer.com	en
dc.subject	Graphics processing units
dc.subject	Multimodality
dc.subject	Parallel processing
dc.subject	Μονάδες επεξεργασίας γραφικών
dc.subject	Πολυτροπικότητα
dc.subject	Παράλληλη επεξεργασία
dc.title	Multimodality GPU-based computer-assisted diagnosis of breast cancer using ultrasound and digital mammography images	en
heal.type	journalArticle
heal.classification	Medicine
heal.classification	Medical physics
heal.classification	Ιατρική
heal.classification	Ιατρική φυσική
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh00006614
heal.classificationURI	http://skos.um.es/unesco6/240606
heal.classificationURI	N/A-Ιατρική
heal.classificationURI	N/A-Ιατρική φυσική
heal.keywordURI	http://id.loc.gov/authorities/subjects/sh2009010908
heal.contributorName	Stonham, John	en
heal.contributorName	Κάβουρας, Διονύσης	el
heal.identifier.secondary	DOI: 10.1007/s11548-013-0813-y
heal.language	en
heal.access	campus
heal.publicationDate	2013
heal.bibliographicCitation	Sidiropoulos, K., Kostopoulos, S., Glotsos, D., Athanasiadis, E., Dimitropoulos, N. et al. (2013) Multimodality GPU-based computer-assisted diagnosis of breast cancer using ultrasound and digital mammography images. "International Journal of Computer Assisted Radiology and Surgery", 8 (4), p.547-560	en
heal.abstract	Purpose To improve the computer-aided diagnosis of breast lesions, by designing a pattern recognition system (PR-system) on commercial graphics processing unit (GPU) cards using parallel programming and textural information from multimodality imaging. Material and methods Patients with histologically verified breast lesions underwent both ultrasound (US) and digital mammography (DM), lesions were outlined on the images by an experienced radiologist, and textural features were calculated. The PR-system was designed to provide highest possible precision by programming in parallel the multiprocessors of the NVIDIA's GPU cards, GeForce 8800GT or 580GTX, and using the CUDA programming framework and C++. The PR-system was built around the probabilistic neural network classifier, and its performance was evaluated by a re-substitution method, for estimating the system's highest accuracy, and by the external cross-validation method, for assessing the PR-system's unbiased accuracy to new, "unseen" by the system, data. Results Classification accuracies for discriminating malignant from benign lesions were as follows: 85.5 % using US-features alone, 82.3 % employing DM features alone, and 93.5 % combining US and DM features. Mean accuracy to new "unseen" data for the combined US and DM features was 81 %. Those classification accuracies were about 10 % higher than accuracies achieved on a single CPU, using sequential programming methods, and 150-fold faster. Conclusion The proposed PR-system improves breast-lesion discrimination accuracy, it may be redesigned on site when new verified data are incorporated in its depository, and it may serve as a second opinion tool in a clinical environment.	en
heal.journalName	International Journal of Computer Assisted Radiology and Surgery	en
heal.journalType	peer-reviewed
heal.fullTextAvailability	true