Affiliations: [a] Biomedical Engineering Unit, Division of Maternal and Fetal Medicine, Department of Obstetrics and Gynecology, Hacettepe University, 06100, Ankara, Turkey | [b] Department of Electrical and Electronics Engineering, Middle East Technical University, 06531, Ankara, Turkey | [c] Department of Histology and Embryology, Hacettepe University, 06100, Ankara, Turkey | [d] Section of Clinical Genetics, Rigshospitalet, 4032, Copenhagen (2), Denmark
Correspondence:
[*]
Corresponding author, Biomedical Engineering Unit, Division of Maternal and Fetal Medicine, Department of Obstetrics and Gynecology, Hacettepe University, 06100 Ankara, Turkey. Tel: 00-90-312-3101011. Fax: 00-90-312-3105552.
Abstract: In this study, we introduce an expert system for intelligent chromosome recognition and classification based on artificial neural networks (ANN) and features obtained by automated image analysis techniques. A microscope equipped with a CCTV camera, integrated with an IBM-PC compatible computerÂů environment including a frame grabber, is used for image data acquisition. Features of the chromosomes are obtained directly from the digital chromosome images. Two new algorithms for automated object detection and object skeletonizing constitute the basis of the feature extraction phase which constructs the components of the input vector to the ANN part of the system. This first version of our intelligent diagnostic system uses a trained unsupervised neural network structure and an original rule-based classification algorithm to find a karyotyped form of randomly distributed chromosomes over a complete metaphase. We investigate the effects of network parameters on the classification performance and discuss the adaptability and flexibility of the neural system in order to reach a structure giving an output including information about both structural and numerical abnormalities. Moreover, the classification performances of neural and rule-based system are compared for each class of chromosome.
