The goal of the Mathematical Biostatistics and Image Analysis Laboratory (MBIAL) is to develop mathematical and biostatistical methods for the analysis of medical images and shapes. Other areas of interest include mixed models, sample size and power calculations, asymptotic hypothesis tests comparison, optimization in statistics, image reconstruction, inverse problems, financial mathematics, partial differential equations and tumor response to treatment. The MBIAL is Directed by Dr. Eugene Demidenko.
Demidenko E, Williams BB, Flood AB, Swartz HM. Standard error of inverse prediction for dose-response relationship: approximate and exact statistical inference.Stat Med. 2013 May 30;32(12):2048-61
Demidenko E. Confidence intervals and bands for the binormal ROC curve revisited. J Appl Stat. 2012 Jan 1;39(1):67-79.
Demidenko E. Three endpoints of in vivo tumour radiobiology and their statistical estimation. Int J Radiat Biol. 2010 Feb;86(2):164-73.
Demidenko E. Statistical Hypothesis Testing for Postreconstructed and Postregistered Medical Images. SIAM J Imaging Sci. 2009 Oct 1;2(4):1049-1067.