Title: A comprehensive statistical classifier of foci in the cell transformation assay for carcinogenicity testing
Citation: TOXICOLOGY IN VITRO vol. 45 p. 351-358
Publication Year: 2017
JRC N°: JRC107082
ISSN: 0887-2333
URI: http://publications.jrc.ec.europa.eu/repository/handle/JRC107082
DOI: 10.1016/j.tiv.2017.04.030
Type: Articles in periodicals and books
Abstract: The identification of the carcinogenic risk of chemicals is currently mainly based on animal studies. The in vitro Cell Transformation Assays (CTAs) are a promising alternative to be considered in an integrated approach. CTAs measure the induction of foci of transformed cells. CTAs model key stages of the in vivo neoplastic process and are able to detect both genotoxic and some non-genotoxic compounds, being the only in vitro method able to deal with the latter. Despite their favorable features, CTAs can be further improved, especially reducing the possible subjectivity arising from the last phase of the protocol, namely visual scoring of foci using coded morphological features. By taking advantage of digital image analysis, the aim of our work is to translate morphological features into statistical descriptors of foci images, and to use them to mimic the classification performances of the visual scorer to discriminate between transformed and non-transformed foci. Here we present a classifier based on five descriptors trained on a dataset of 1364 foci, obtained with different compounds and concentrations. Our classifier showed accuracy, sensitivity and specificity equal to 0.77 and an area under the curve (AUC) of 0.84. The presented classifier outperforms a previously published model.
JRC Directorate:Health, Consumers and Reference Materials

Files in This Item:
There are no files associated with this item.

Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.