A GPU-based computer-assisted microscopy system for assessing the importance of different families of histological characteristics in cancer diagnosis

dc.contributor.author	Γκλώτσος, Δημήτριος	el
dc.contributor.author	Σιδηρόπουλος, Κωνσταντίνος	el
dc.contributor.author	Κωστόπουλος, Σπυρίδων	el
dc.contributor.author	Ραβαζούλα, Παναγιώτα	el
dc.contributor.author	Καλατζής, Ιωάννης	el
dc.date.accessioned	2015-06-10T16:31:11Z
dc.date.available	2015-06-10T16:31:11Z
dc.date.issued	2015-06-10
dc.identifier.uri	http://hdl.handle.net/11400/15647
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://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1814330	en
dc.subject	όγκος του εγκεφάλου
dc.subject	όγκος του μαστού
dc.subject	Μονάδα επεξεργασίας γραφικών
dc.subject	Πιθανοτικά Νευρωνικά Δίκτυα
dc.subject	brain tumours
dc.subject	breast tumours
dc.subject	Graphics Processing Unit
dc.subject	Probabilistic Neural Network
dc.title	A GPU-based computer-assisted microscopy system for assessing the importance of different families of histological characteristics in cancer diagnosis	en
heal.type	conferenceItem
heal.classification	Πληροφορική
heal.classification	Καρκίνος
heal.classification	Computer science
heal.classification	Cancer
heal.classificationURI	N/A-Πληροφορική
heal.classificationURI	N/A-Καρκίνος
heal.classificationURI	http://skos.um.es/unescothes/C00750
heal.classificationURI	http://zbw.eu/stw/descriptor/18899-3
heal.contributorName	Ασβεστάς, Παντελής	el
heal.contributorName	Κάβουρας, Διονύσης Α.	el
heal.identifier.secondary	DOI: 10.1117/12.2054186
heal.language	en
heal.access	campus
heal.recordProvider	Τεχνολογικό Εκπαιδευτικό Ίδρυμα Αθήνας. Σχολή Τεχνολογικών Εφαρμογών. Τμήμα Μηχανικών Βιοϊατρικής Τεχνολογίας Τ.Ε.	el
heal.publicationDate	2013-10-26
heal.bibliographicCitation	Glotsos, D., Kostopoulos, S., Sidiropoulos, K., Ravazoula, P., Kalatzis, I. et al. (2013) A GPU-based computer-assisted microscopy system for assessing the importance of different families of histological characteristics in cancer diagnosis. Proceedings of SPIE - The International Society for Optical Engineering. 5th International Conference on Graphic and Image Processing, ICGIP 2013. 9069, 2014, 90691I. Hong Kong, China: SPIE	en
heal.abstract	In this study a Computer-Aided Microscopy (CAM) system is proposed for investigating the importance of the histological criteria involved in diagnosing of cancers in microscopy in order to suggest the more informative features for discriminating low from high-grade brain tumours. Four families of criteria have been examined, involving the greylevel variations (i.e. texture), the morphology (i.e. roundness), the architecture (i.e. cellularity) and the overall tumour qualities (expert's ordinal scale). The proposed CAM system was constructed using a modified Seeded Region Growing algorithm for image segmentation, and the Probabilistic Neural Network classifier for image classification. The implementation was designed on a commercial Graphics Processing Unit card using parallel programming. The system's performance using textural, morphological, architectural and ordinal information was 90.8%, 87.0%, 81.2% and 88.9% respectively. Results indicate that nuclei texture is the most important family of features regarding the degree of malignancy, and, thus, may guide more accurate predictions for discriminating low from high grade gliomas. Considering that nuclei texture is almost impractical to be encoded by visual observation, the need to incorporate computer-aided diagnostic tools as second opinion in daily clinical practice of diagnosing rare brain tumours may be justified.	en
heal.sponsor	The Hong Kong Polytechnic University,Wuhan University,Nanyang Technological University,Southern Polytechnic State University,International Association of Computer Science,and Information Technology (IACSIT)	en
heal.publisher	SPIE	en
heal.fullTextAvailability	false
heal.conferenceName	Proceedings of SPIE - The International Society for Optical Engineering	en
heal.conferenceItemType	short paper