Semi-supervised Bayesian Source Separation of Scintigraphic Image Sequences

0480504 - ÚTIA 2019 RIV CH eng C - Konferenční příspěvek (zahraniční konf.)
Bódiová, L. - Tichý, Ondřej - Šmídl, Václav
Semi-supervised Bayesian Source Separation of Scintigraphic Image Sequences.
European Congress on Computational Methods in Applied Sciences and Engineering (ECCOMAS 2017: VipIMAGE 2017). Vol. 27. Cham: Springer, 2018, s. 52-61. Lecture Notes in Computational Vision and Biomechanics, 27. ISBN 978-3-319-68195-5. ISSN 2212-9391. E-ISSN 2212-9413.
[VI ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing. Porto (PT), 18.10.2017-20.10.2017]
Institucionální podpora: RVO:67985556
Klíčová slova: Dynamic renal scintigraphy * Regions of interest * Blind source separation * Factor analysis * Variational Bayes method
Obor OECD: Statistics and probability
http://library.utia.cas.cz/separaty/2017/AS/tichy-0480504.pdf

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.
Trvalý link: http://hdl.handle.net/11104/0276748