Scale-based normalization of spectral data

Issue title: Quantitative Methods for Biomarker Discovery and Validation

Guest editors: Ziding Feng

Article type: Research Article

Authors: Randolph, Timothy W.^{; *}

Affiliations: Department of Biostatistics, University of Washington, Seattle, WA, 98195, USA | Biostatistics Program, Fred Hutchinson Cancer Research Center, Seattle, WA 98109, USA

Correspondence: [*] Corresponding author. Tel.: +1 206 667 1079; Fax: +1 206 667 7998; E-mail: trandolp@u.washington.edu.

Abstract: Classification of data that arise as signals or images often requires a standardization step so that information extracted from biologically equivalent signals can be quantified for comparison across classes. Differences in global trend, total energy, high-frequency noise and/or local background can arise from variabilities due to instrumentation or conditions during data collection. This article considers some common ways in which such variation is adjusted for and introduces a generalization of the popular “standard normal variate” transformation. Based on a wavelet decomposition this generalization provides increased flexibility for normalizing spectral data affected by local background noise. Examples from three types of spectroscopy data illustrate the method and its properties.

Keywords: Normalization, spectroscopy, preprocessing, standard normal variate, wavelet

DOI: 10.3233/CBM-2006-23-405

Journal: Cancer Biomarkers, vol. 2, no. 3-4, pp. 135-144, 2006