Classification of cell colonies images by ART2 classifier

Abstract

Counting of cell colonies is a high demanded procedure in cytometry. An ability to automatically parameterize biomedical samples highly influences on cytometry and therefore medical research results. The article extends previously by the authors developed cell colonies image parameterization technique with new results based on the use of another - ART2 (Adaptive Resonance Theory 2), classifier. Experimental investigation is carried out in order to check reliability of cell colony count and efficiency of cell colony image classification. Results of the experimental verification confirms that ART2 classifier brings up similar results to Heuristic classifier in terms of F1 score, accuracy and precision, yet DOR value is increased more than two times. Moreover the use of ART2 classifier in terms of true positives manifests better performance than the use of other considered classifiers: Support Vector Machine - by 14%, ART1 - by 4% and Heuristic - by 2%.