A new feature descriptor derived from Hilbert space-filling curve to assist breast cancer classification
2010 IEEE 23rd International Symposium on Computer-Based Medical Systems (CBMS) (2010)
Oct. 12, 2010 to Oct. 15, 2010
D. Guliato , Fac. de Comput., Univ. Fed. de Uberlandia, Uberlandia, Brazil
W. A. A. de Oliveira , Fac. de Comput., Univ. Fed. de Uberlandia, Uberlandia, Brazil
C. Traina , ICMC - Inst. de Cienc., Mat. e de Comput., Univ. de Sao Paulo, Sao Carlos, Brazil
Malignant breast tumors and benign masses appear in mammograms with different shape characteristics: the former usually have rough, spiculated, or microlobulated contours, whereas the latter commonly have smooth, round, oval, or macrolobulated contours. Visual features that characterize shape roughness can assist in distinguishing between malignant tumors and benign masses in mammo-grams. Here we propose a new approach based on Hilbert curves to classify breast masses as benign or malignant. The feature extraction is performed in linear time, and is amenable to parallel processing, whereas the classification phase can be performed by a classical neural networks structure. We evaluated our method using a set of 111 contours from 65 benign masses and 46 malignant tumors. As the experimental evaluations show, we achieved an accuracy of 0.99 in terms of the area under the receiver operating characteristics curve, a very high classification result.
receiver operating characteristics curve, feature descriptor, Hilbert space-filling curve, breast cancer classification, malignant breast tumors, benign mass, mammogram, visual features, feature extraction, parallel processing, neural networks structure
C. Traina, D. Guliato and W. A. de Oliveira, "A new feature descriptor derived from Hilbert space-filling curve to assist breast cancer classification," 2010 IEEE 23rd International Symposium on Computer-Based Medical Systems (CBMS), Perth, WA, 2010, pp. 303-308.