Computer assisted characterization of liver tissue using image texture analysis techniques on B-scan images

Kyriacou, E; Pavlopoulos, S; Koutsouris, D; Zoumpoulis, P; Theotokas, I

dc.contributor.author	Kyriacou, E	en
dc.contributor.author	Pavlopoulos, S	en
dc.contributor.author	Koutsouris, D	en
dc.contributor.author	Zoumpoulis, P	en
dc.contributor.author	Theotokas, I	en
dc.date.accessioned	2014-03-01T01:12:43Z
dc.date.available	2014-03-01T01:12:43Z
dc.date.issued	1997	en
dc.identifier.issn	05891019	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/12210
dc.subject	Fractal Dimension	en
dc.subject	Image Texture Analysis	en
dc.subject	K Nearest Neighbor	en
dc.subject	Texture Analysis	en
dc.subject	Tissue Characterization	en
dc.subject	Ultrasound	en
dc.subject	Region of Interest	en
dc.subject.other	Algorithms	en
dc.subject.other	Computer aided analysis	en
dc.subject.other	Image analysis	en
dc.subject.other	Tissue	en
dc.subject.other	Ultrasonic imaging	en
dc.subject.other	Fractal dimension texture analysis	en
dc.subject.other	Gray level difference statistics	en
dc.subject.other	Gray level run length statistics	en
dc.subject.other	Spatial gray level dependence matrices	en
dc.subject.other	Medical imaging	en
dc.title	Computer assisted characterization of liver tissue using image texture analysis techniques on B-scan images	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/IEMBS.1997.757766	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IEMBS.1997.757766	en
heal.publicationDate	1997	en
heal.abstract	In this study, the classification of B-scan ultrasonic liver images using image texture analysis techniques is investigated. The texture analysis algorithms used were the Gray Level Difference Statistics (GLDS), the Gray Level Run Length Statistics (RUNL), the Spatial Gray Level Dependence Matrices (SGLDM) and the Fractal Dimension Texture Analysis (FDTA). All four techniques were applied on four sets of ultrasonic liver images: normal, fatty, cirrhosis and hepatoma. A total of 120 cases were investigated (30 from each class), with all abnormal cases being histologically proven. In each image, a 32×32 pixel rectangular region-of-interest was selected by an expert physician. Results were classified using the K-nearest neighbor (K-NN) classifier. The FDTA and SGLDM algorithms were able to classify the four sets with an overall accuracy of 78,3% and 77,5% respectively while the RUNL algorithm achieved 74,2% and the GLDS algorithm 70,8% overall accuracy. Combination of RUNL, SGLDM and FDTA improved the overall accuracy to 80%.	en
heal.publisher	IEEE, Piscataway, NJ, United States	en
heal.journalName	Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings	en
dc.identifier.doi	10.1109/IEMBS.1997.757766	en
dc.identifier.volume	2	en
dc.identifier.spage	806	en
dc.identifier.epage	809	en