Mostrar el registro sencillo del ítem
A two-stage method for microcalcification cluster segmentation in mammography by deformable models
dc.creator | Arikidis, N. | en |
dc.creator | Vassiou, K. | en |
dc.creator | Kazantzi, A. | en |
dc.creator | Skiadopoulos, S. | en |
dc.creator | Karahaliou, A. | en |
dc.creator | Costaridou, L. | en |
dc.date.accessioned | 2015-11-23T10:22:51Z | |
dc.date.available | 2015-11-23T10:22:51Z | |
dc.date.issued | 2015 | |
dc.identifier | 10.1118/1.4930246 | |
dc.identifier.issn | 942405 | |
dc.identifier.uri | http://hdl.handle.net/11615/25812 | |
dc.description.abstract | Purpose: Segmentation of microcalcification (MC) clusters in x-ray mammography is a difficult task for radiologists. Accurate segmentation is prerequisite for quantitative image analysis of MC clusters and subsequent feature extraction and classification in computer-aided diagnosis schemes. Methods: In this study, a two-stage semiautomated segmentation method of MC clusters is investigated. The first stage is targeted to accurate and time efficient segmentation of the majority of the particles of a MC cluster, by means of a level set method. The second stage is targeted to shape refinement of selected individual MCs, by means of an active contour model. Both methods are applied in the framework of a rich scale-space representation, provided by the wavelet transform at integer scales. Segmentation reliability of the proposed method in terms of inter and intraobserver agreements was evaluated in a case sample of 80 MC clusters originating from the digital database for screening mammography, corresponding to 4 morphology types (punctate: 22, fine linear branching: 16, pleomorphic: 18, and amorphous: 24) of MC clusters, assessing radiologist's segmentations quantitatively by two distance metrics (Hausdorff distance - HDISTcluster, average of minimum distance - MINDISTcluster) and the area overlap measure (AOMcluster). The effect of the proposed segmentation method on MC cluster characterization accuracy was evaluated in a case sample of 162 pleomorphic MC clusters (72 malignant and 90 benign). Ten MC cluster features, targeted to capture morphologic properties of individual MCs in a cluster (area, major length, perimeter, compactness and spread), were extracted and a correlation-based feature selection method yielded a feature subset to feed in a support vector machine classifier. Classification performance of the MC cluster features was estimated by means of the area under receiver operating characteristic curve (Az Standard Error) utilizing tenfold cross-validation methodology. A previously developed B-spline active rays segmentation method was also considered for comparison purposes. Results: Interobserver and intraobserver segmentation agreements (median and [25%, 75%] quartile range) were substantial with respect to the distance metrics HDISTcluster (2.3 [1.8, 2.9] and 2.5 [2.1, 3.2] pixels) and AMINDISTcluster (0.8 [0.6, 1.0] and 1.0 [0.8, 1.2] pixels), while moderate with respect to AOMcluster (0.64 [0.55, 0.71] and 0.59 [0.52, 0.66]). The proposed segmentation method outperformed (0.800.04) statistically significantly (Mann-Whitney U-test, p < 0.05) the B-spline active rays segmentation method (0.690.04), suggesting the significance of the proposed semiautomated method. Conclusions: Results indicate a reliable semiautomated segmentation method for MC clusters offered by deformable models, which could be utilized in MC cluster quantitative image analysis. © 2015 American Association of Physicists in Medicine. | en |
dc.source | Medical Physics | en |
dc.source.uri | http://www.scopus.com/inward/record.url?eid=2-s2.0-84941959334&partnerID=40&md5=ce7c90b6aaf73dc069535f69a56cd248 | |
dc.subject | active contours | en |
dc.subject | diagnostic accuracy | en |
dc.subject | level set | en |
dc.subject | mammography | en |
dc.subject | microcalcification cluster segmentation | en |
dc.subject | scale-space representation | en |
dc.subject | segmentation reliability | en |
dc.subject | anatomical concepts | en |
dc.subject | Article | en |
dc.subject | breast calcification | en |
dc.subject | breast density | en |
dc.subject | classification | en |
dc.subject | computer assisted diagnosis | en |
dc.subject | controlled study | en |
dc.subject | human | en |
dc.subject | image analysis | en |
dc.subject | image display | en |
dc.subject | image processing | en |
dc.subject | major clinical study | en |
dc.subject | reliability | en |
dc.subject | support vector machine | en |
dc.title | A two-stage method for microcalcification cluster segmentation in mammography by deformable models | en |
dc.type | journalArticle | en |
Ficheros en el ítem
Ficheros | Tamaño | Formato | Ver |
---|---|---|---|
No hay ficheros asociados a este ítem. |