Hierarchical modelling for unsupervised tumour segmentation in PET

Ziming Zeng, Tony Shepherd, Reyer Zwiggelaar

Allbwn ymchwil: Pennod mewn Llyfr/Adroddiad/Trafodion CynhadleddTrafodion Cynhadledd (Nid-Cyfnodolyn fathau)

3 Dyfyniadau (Scopus)

Crynodeb

This paper presents a fully automated and unsupervised method for the segmentation of tumours in PET images. The segmentation technique incorporates a pre-processing stage and a hierarchical approach based on an improved region-scalable energy fitting model. The advantages of the approach lie in its multi-level processing. It first considers the whole range of grey levels in the image volume, which is able to avoid local maxima. Subsequently, the local grey levels range is utilized to refine the segmentation which effectively avoids false negative segmentations. We validate our method using real PET images of head-and-neck cancer patients as well as custom-designed phantom PET images. Compared with other popular approaches, the experimental results on both data sets show that our method can accurately segment tumours in PET images.
Iaith wreiddiolSaesneg
TeitlProceedings - IEEE-EMBS International Conference on Biomedical and Health Informatics
Is-deitlGlobal Grand Challenge of Health Informatics, BHI 2012
CyhoeddwrIEEE Press
Tudalennau439-443
Nifer y tudalennau5
ISBN (Electronig)978-1-4577-2177-9
ISBN (Argraffiad)9781457721779
Dynodwyr Gwrthrych Digidol (DOIs)
StatwsCyhoeddwyd - 05 Ion 2012

Cyfres gyhoeddiadau

EnwProceedings - IEEE-EMBS International Conference on Biomedical and Health Informatics: Global Grand Challenge of Health Informatics, BHI 2012

Ôl bys

Gweld gwybodaeth am bynciau ymchwil 'Hierarchical modelling for unsupervised tumour segmentation in PET'. Gyda’i gilydd, maen nhw’n ffurfio ôl bys unigryw.

Dyfynnu hyn