Title :
On knowledge-based improvement of biomedical pattern recognition-a case study
Author :
Wu, Q. ; Suetens, P. ; Oosterlinck, A.
Author_Institution :
Dept. of Electr. Eng., Leuven Univ., Belgium
Abstract :
Most biomedical pattern recognition (BPR) systems use the classical statistical pattern recognition strategy in which a feature hyperspace is constructed for the problem followed by a statistical discriminant analysis procedure. It is shown that there are several essential drawbacks with this conventional approach. These limitations often lead to highly erroneous classification results subject to time-consuming interactive corrections in existing systems. To overcome such limitations, a pilot study on applying knowledge-based techniques to chromosome classification has been carried out. The scheme developed as a result of this case study is described in detail. The system has been implemented and tested on metaphase imagery in preliminary experiments, the results of which are also presented
Keywords :
cellular biophysics; computerised pattern recognition; knowledge based systems; medical computing; BPR systems; automated cytogenetics; biomedical pattern recognition; chromosome classification; classical statistical pattern recognition strategy; erroneous classification results; feature hyperspace; interactive corrections; knowledge-based improvement; knowledge-based techniques; metaphase imagery; pilot study; statistical discriminant analysis procedure; Artificial intelligence; Automatic testing; Biological cells; Business process re-engineering; Computer aided software engineering; Image analysis; Knowledge based systems; Pattern analysis; Pattern recognition; System testing;
Conference_Titel :
Artificial Intelligence Applications, 1989. Proceedings., Fifth Conference on
Conference_Location :
Miami, FL
Print_ISBN :
0-8186-1902-3
DOI :
10.1109/CAIA.1989.49159
