An automatic classification system of urine bladder tumors employing morphological and textural nuclear features

The performance of three classifiers is evaluated in an attempt to achieve a more objective grading of urinary bladder tumors. 95 cases were classified according to the World Health Organization (WHO) grading system by pathologists in three classes: grade I, grade II, and grade III. Each case was represented by 36 nuclear features. The minimum distance, the least mean square, and the Bayes classifier were implemented in a two stage hierarchical tree. The classification accuracy of each hierarchical tree was also tested in relation to direct tumor grading. The Bayes classifier provided the best overall system accuracy of 74.5%, employing a four-feature vector and the leave one out method. Grade I and grade III tumors were recognized as two distinct entities, whereas tumors of grade II, were poorly discriminated from tumors of grade I and II. Nuclear features could be of value in a more objective grading of urine bladder cancer