Comparison of different Neuro-Fuzzy classification systems for the detection of prostate cancer in ultrasonic images

The authors selected five trainable Neuro-Fuzzy classification algorithms in order to investigate their ability to differentiate areas of malign tissue in ultrasonic prostate images. The algorithms were compared with results from two commonly used classifiers, the K-nearest neighbor (KNN) classifier and the Bayes classifier. The best Neuro-Fuzzy classification system, which is based on a mountain clustering algorithm published by Yager et al. (1994) and refined by Chiu (1994) reached recognition rates above 86% in comparison to the Bayes classifier (79%) and the KNN classifier (78%). The authors' results suggest that Neuro-Fuzzy classification algorithms have the potential to significantly improve common classification methods for the use in ultrasonic tissue characterization.