Fuzzy rules to predict degree of malignancy in brain glioma. Export

@article{citeulike:1104798, abstract = {The current pre-operative assessment of the degree of malignancy in brain glioma is based on magnetic resonance imaging (MRI) findings and clinical data. 280 cases were studied, of which 111 were high-grade malignancies and 169 were low-grade, so that regular and interpretable patterns of the relationships between glioma MRI features and the degree of malignancy could be acquired. However, as uncertainties in the data and missing values existed, a fuzzy rule extraction algorithm based on a fuzzy min-max neural network (FMMNN) was used. The performance of a multi-layer perceptron network (MLP) trained with the error back-propagation algorithm (BP), the decision tree algorithm ID3, nearest neighbour and the original fuzzy min-max neural network were also evaluated. The results showed that two fuzzy decision rules on only six features achieved an accuracy of 84.6\% (89.9\% for low-grade and 76.6\% for high-grade cases). Investigations with the proposed algorithm revealed that age, mass effect, oedema, postcontrast enhancement, blood supply, calcification, haemorrhage and the signal intensity of the T1-weighted image were important diagnostic factors.}, address = {Institute of Image Processing \& Pattern Recognition, Shanghai Jiaotong University, China.}, author = {Ye, C. Z. and Yang, J. and Geng, D. Y. and Zhou, Y. and Chen, N. Y.}, citeulike-article-id = {1104798}, citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/12043794}, citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=12043794}, issn = {0140-0118}, journal = {Med Biol Eng Comput}, keywords = {brain, classification}, month = {March}, number = {2}, pages = {145--152}, posted-at = {2007-02-13 10:12:39}, priority = {2}, title = {Fuzzy rules to predict degree of malignancy in brain glioma.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/12043794}, volume = {40}, year = {2002} }

TY - JOUR ID - citeulike:1104798 L3 - citeulike-article-id:1104798 N2 - The current pre-operative assessment of the degree of malignancy in brain glioma is based on magnetic resonance imaging (MRI) findings and clinical data. 280 cases were studied, of which 111 were high-grade malignancies and 169 were low-grade, so that regular and interpretable patterns of the relationships between glioma MRI features and the degree of malignancy could be acquired. However, as uncertainties in the data and missing values existed, a fuzzy rule extraction algorithm based on a fuzzy min-max neural network (FMMNN) was used. The performance of a multi-layer perceptron network (MLP) trained with the error back-propagation algorithm (BP), the decision tree algorithm ID3, nearest neighbour and the original fuzzy min-max neural network were also evaluated. The results showed that two fuzzy decision rules on only six features achieved an accuracy of 84.6% (89.9% for low-grade and 76.6% for high-grade cases). Investigations with the proposed algorithm revealed that age, mass effect, oedema, postcontrast enhancement, blood supply, calcification, haemorrhage and the signal intensity of the T1-weighted image were important diagnostic factors. IS - 2 JF - Med Biol Eng Comput SN - 0140-0118 AD - Institute of Image Processing & Pattern Recognition, Shanghai Jiaotong University, China. EP - 152 TI - Fuzzy rules to predict degree of malignancy in brain glioma. VL - 40 SP - 145 KW - brain KW - classification AU - Ye, CZ AU - Yang, J AU - Geng, DY AU - Zhou, Y AU - Chen, NY PY - 2002/03// UR - http://view.ncbi.nlm.nih.gov/pubmed/12043794 ER -