A neural network based workstation for automated cell proliferation analysis

Abstract

Abstract-In this paper is reported the development of a neural network (NN) based workstation for automated cell proliferation analysis, of cytological microscope images. The software of the system assists the expert biotechnologist during cell proliferation and chromosome aberration studies by automatically identifying metaphase spreads and stimulated nuclei on each digital image. After manual edition of metaphase false positives, the system automatically calculates the mitotic index (MI) i.e. the ratio of metaphases to stimulated nuclei of a given tissue sample. The system reported has been able to classify correctly approximately 91% of the metaphases and stimulated nuclei, in a test set of 191 mitosis, 331 nuclei, and 387 artefacts, obtained from 30 different microscope slides. Manual edition of false positives from the metaphase classification results allows the calculation of the MI with an error of 6.5%.

A study of machine learning techniques for Automated Karyotyping System

“…Chromosomes that are touching, overlapping or curved can also be treated with it. Its only flaw is the process’s high computing cost of assessing all of the metaphase chromosomal images [18].…”