0465945 - ÚTIA 2017 RIV US eng J - Journal Article
Habart, D. - Švihlík, J. - Schier, Jan - Cahová, M. - Girman, P. - Zacharovová, K. - Berková, Z. - Kříž, J. - Fabryová, E. - Kosinová, L. - Papáčková, Z. - Kybic, J. - Saudek, F.
Automated Analysis of Microscopic Images of Isolated Pancreatic Islets.
Cell Transplantation. Roč. 25, č. 12 (2016), s. 2145-2156. ISSN 0963-6897. E-ISSN 1555-3892
Grant - others:GA ČR(CZ) GA14-10440S
Institutional support: RVO:67985556
Keywords : enumeration of islets * image processing * image segmentation * islet transplantation * machine-learning * quality control
Subject RIV: IN - Informatics, Computer Science
Impact factor: 3.006, year: 2016 ; AIS: 0.769, rok: 2016
Result website:
http://library.utia.cas.cz/separaty/2016/ZOI/schier-0465945.pdf

DOI: https://doi.org/10.3727/096368916X692005

Clinical islet transplantation programs rely on the capacities of individual centers to quantify isolated islets. We describe two machine learning algorithms for islet quantification, the trainable islet algorithm (TIA) and the non-trainable purity algorithm (NPA). These algorithms automatically segment pancreatic islets and exocrine tissue on microscopic images in order to count individual islets, and calculate islet volume and purity. References for islet counts and volumes were generated by the fully manual segmentation (FMS) method, which was validated against the internal DNA standard. References for islet purity were generated via the expert visual assessment (EVA) method, which was validated against the FMS method.
Permanent Link: http://hdl.handle.net/11104/0265686