A two-level classifier for automatic medical objects classification
Przemysław Wiktor Pardel, Jan G. Bazan, Jacek Zarychta, Stanisława Bazan-Socha
DOI: http://dx.doi.org/10.15439/2015F407
Citation: Proceedings of the 2015 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 5, pages 139–143 (2015)
Abstract. The goal of this paper is to describe the approach for image and a decision returned by the lower-level classifier, and automatic identifying human organs from a medical CT images the output returns confirmation or negation for the suggestion and discuss results of its comparison to different classification generated by the lower-level classifier. It consists in the fact, methods. The main premise of this approach is the use of data that in a situation where the decision taken by the lower-level sets together with the relevant domain knowledge. We test our classifier, is clearly incompatible with domain knowledge, the approach on multiple CT images of chest organs (trachea, lungs, bronchus) and demonstrate usefulness and effectiveness of the adviser suggests to refrain from taking a decision. Thanks to resulting classifications. The presented approach can be used to this, increases the accuracy of such the two-level classifier, assist in solving more complex medical problems.