Number of the records: 1
Semi-supervised Bayesian Source Separation of Scintigraphic Image Sequences
- 1.
SYSNO ASEP 0480504 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Semi-supervised Bayesian Source Separation of Scintigraphic Image Sequences Author(s) Bódiová, L. (CZ)
Tichý, Ondřej (UTIA-B) RID, ORCID
Šmídl, Václav (UTIA-B) RID, ORCIDNumber of authors 3 Source Title European Congress on Computational Methods in Applied Sciences and Engineering (ECCOMAS 2017: VipIMAGE 2017), 27. - Cham : Springer, 2018 - ISSN 2212-9391 - ISBN 978-3-319-68195-5 Pages s. 52-61 Number of pages 10 s. Publication form Print - P Action VI ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing Event date 18.10.2017 - 20.10.2017 VEvent location Porto Country PT - Portugal Event type WRD Language eng - English Country CH - Switzerland Keywords Dynamic renal scintigraphy ; Regions of interest ; Blind source separation ; Factor analysis ; Variational Bayes method Subject RIV BB - Applied Statistics, Operational Research OECD category Statistics and probability Institutional support UTIA-B - RVO:67985556 UT WOS 000437032100006 EID SCOPUS 85032330126 DOI 10.1007/978-3-319-68195-5_6 Annotation Many diagnostic methods using scintigraphic image sequence require decomposition of the sequence into tissue images and their time-activity curves. Standard procedure for this task is still manual selection of regions of interest (ROIs) which can be highly subjective due to their overlaps and poor signal-to-noise ratio. This can be overcome by automatic decomposition, however, the results may not have good physiological meaning. In this contribution, we aim to combine these approaches in semi-supervised procedure which is based on Bayesian blind source separation with the possibility of manual interaction after each run until an acceptable solution is obtained. The manual interaction is based on manual ROI placement and using its position to modify the corresponding prior parameters of the model. Performance of the proposed method is studied on real scintigraphic image sequence as well as on estimation of the specific diagnostic parameter on representative dataset of 10 scintigraphic sequences. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2019
Number of the records: 1