Assessment of the performance of advanced classification models applied for concentration of trace elements in healthy and cancerous prostate tissue (Poster)

Abstract

Gleason grade is the most popular system used to classify different stages of prostate cancer. However, this method is highly dependent on experience of the histopathologists as the assessment is based only on microscopic appearance of analysed tissue sections. Complimentary system is needed that integrates tissue architecture and its biochemistry. SRIXE (Synchrotron Radiation Induced X-ray Emission) is powerful, yet not destructive technique used to determine the elemental make-up of a sample. As very often valuable information is hidden in a huge number of variables, that is why dedicated multivariate statistical method has to be applied for straightforward analysis. Comprehensive comparison of classification models based on elemental concentrations in prostate tissue is presented in this poster.

Krzysztof Banas

Principal Research Fellow

I work as beam-line scientist at Singapore Synchrotron Light Source. My research interests include application of advanced statistical methods for hyperspectral data processing (dimension reduction, clustering and identification).