Your browser doesn't support javascript.
loading
A comprehensive statistical classifier of foci in the cell transformation assay for carcinogenicity testing.
Callegaro, Giulia; Malkoc, Kasja; Corvi, Raffaella; Urani, Chiara; Stefanini, Federico M.
Afiliação
  • Callegaro G; Department of Earth and Environmental Sciences, University of Milan Bicocca, Piazza della Scienza, 1, 20126 Milan, Italy.
  • Malkoc K; Department of Statistics, Computer Science, Applications, University of Florence, Viale Morgagni 59, 50134 Florence, Italy.
  • Corvi R; European Union Reference Laboratory for Alternatives to Animal Testing (EURL ECVAM), Chemical Safety and Alternative Methods Unit, Directorate F, European Commission Joint Research Centre, TP 126, Via E. Fermi 2749, I-21027 Ispra, VA, Italy.
  • Urani C; Department of Earth and Environmental Sciences, University of Milan Bicocca, Piazza della Scienza, 1, 20126 Milan, Italy. Electronic address: chiara.urani@unimib.it.
  • Stefanini FM; Department of Statistics, Computer Science, Applications, University of Florence, Viale Morgagni 59, 50134 Florence, Italy. Electronic address: stefanini@disia.unifi.it.
Toxicol In Vitro ; 45(Pt 3): 351-358, 2017 Dec.
Article em En | MEDLINE | ID: mdl-28461232
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.
Assuntos
Palavras-chave

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Testes de Carcinogenicidade / Transformação Celular Neoplásica Idioma: En Ano de publicação: 2017 Tipo de documento: Article País de afiliação: Itália

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Testes de Carcinogenicidade / Transformação Celular Neoplásica Idioma: En Ano de publicação: 2017 Tipo de documento: Article País de afiliação: Itália