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.

Callegaro, G., Malkoc, K., Corvi, R., Urani, C., Stefanini, F. (2017). A comprehensive statistical classifier of foci in the cell transformation assay for carcinogenicity testing. TOXICOLOGY IN VITRO, 45, 351-358 [10.1016/j.tiv.2017.04.030].

A comprehensive statistical classifier of foci in the cell transformation assay for carcinogenicity testing

Callegaro, G;Urani, C
;
Stefanini, FM
2017

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.
Articolo in rivista - Articolo scientifico
BALB/c 3T3 Cell Transformation Assay; Bayesian Trees; Foci classification; In vitro carcinogenicity testing; Statistical image descriptors;
Cell transformation assay; carcinogenicity, in vitro;
English
2017
45
351
358
none
Callegaro, G., Malkoc, K., Corvi, R., Urani, C., Stefanini, F. (2017). A comprehensive statistical classifier of foci in the cell transformation assay for carcinogenicity testing. TOXICOLOGY IN VITRO, 45, 351-358 [10.1016/j.tiv.2017.04.030].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/179398
Citazioni
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 5
Social impact