Show simple item record

dc.contributor.authorNeofytou, Marios S.en
dc.contributor.authorPattichis, Marios S.en
dc.contributor.authorPattichis, Constantinos S.en
dc.contributor.authorTanos, Vasiliosen
dc.contributor.authorKyriacou, Efthyvoulos C.en
dc.contributor.authorKoutsouris, Demetrios Dionysiosen
dc.creatorNeofytou, Marios S.en
dc.creatorPattichis, Marios S.en
dc.creatorPattichis, Constantinos S.en
dc.creatorTanos, Vasiliosen
dc.creatorKyriacou, Efthyvoulos C.en
dc.creatorKoutsouris, Demetrios Dionysiosen
dc.description.abstractThe objective of this study was to classify hysteroscopy images of the endometrium based on texture analysis for the early detection of gynaecological cancer. A total of 418 Regions of Interest (ROIs) were extracted (209 normal and 209 abnormal) from 40 subjects. Images were gamma corrected and were converted to gray scale. The following texture features were extracted: (i) Statistical Features, (ii) Spatial Gray Level Dependence Matrices (SGLDM), and (iii) Gray level difference statistics (GLDS). The PNN and SVM neural network classifiers were also investigated for classifying normal and abnormal ROIs. Results show that there is significant difference (using Wilcoxon Rank Sum Test at a=0.05) between the texture features of normal and abnormal ROIs for both the gamma corrected and uncorrected images. Abnormal ROIs had lower gray scale median and homogeneity values, and higher entropy and contrast values when compared to the normal ROIs. The highest percentage of correct classifications score was 77% and was achieved for the SVM models trained with the SF and GLDS features. Concluding, texture features provide useful information differentiating between normal and abnormal ROIs of the endometrium. © 2006 IEEE.en
dc.sourceAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedingsen
dc.source28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06en
dc.subjectStatistical methodsen
dc.subjectFeature extractionen
dc.subjectNeural networksen
dc.subjectImage analysisen
dc.subjectSupport vector machinesen
dc.subjectTexture analysisen
dc.subjectHysteroscopy imagesen
dc.subjectTexture based classificationen
dc.titleTexture-based classification of hysteroscopy images of the endometriumen
dc.description.endingpage3008 Σχολή Θετικών και Εφαρμοσμένων Επιστημών / Faculty of Pure and Applied SciencesΤμήμα Πληροφορικής / Department of Computer Science
dc.type.uhtypeConference Objecten
dc.description.notes<p>Conference code: 69200en
dc.description.notesCited By :6</p>en
dc.contributor.orcidPattichis, Constantinos S. [0000-0003-1271-8151]
dc.contributor.orcidPattichis, Marios S. [0000-0002-1574-1827]
dc.contributor.orcidKyriacou, Efthyvoulos C. [0000-0002-4589-519X]

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record