- Tytuł:
- Feature selection for breast cancer malignancy classification problem
- Autorzy:
-
Filipczuk, P.
Kowal, M.
Marciniak, A. - Powiązania:
- https://bibliotekanauki.pl/articles/333614.pdf
- Data publikacji:
- 2010
- Wydawca:
- Uniwersytet Śląski. Wydział Informatyki i Nauki o Materiałach. Instytut Informatyki. Zakład Systemów Komputerowych
- Tematy:
-
wybór funkcji
klasyfikacja
rak piersi
feature selection
classification
breast cancer - Opis:
- The paper provides a preview of some work in progress on the computer system to support breast cancer diagnosis. Diagnosis approach is based on microscope images of the FNB (Fine Needle Biopsy) and assumes distinguishing malignant from benign cases. Studies conducted focus on two different problems, the first concern the extraction of morphometric parameters of nuclei present in cytological images and the other concentrate on breast cancer nature classification using selected features. Studies in both areas are conducted in parallel. This work is devoted to the problem of feature selection from the set of determined features in order to maximize the accuracy of classification. Morphometric features are derived directly from a digital scans of breast fine needle biopsy slides and are computed for segmented nuclei. The quality of feature space is measured with four different classification methods. In order to illustrate the effectiveness of the approach, the automatic system of malignancy classification was applied on a set of medical images with promising results.
- Źródło:
-
Journal of Medical Informatics & Technologies; 2010, 15; 193-199
1642-6037 - Pojawia się w:
- Journal of Medical Informatics & Technologies
- Dostawca treści:
- Biblioteka Nauki