THE USE OF THE DECISION TREE TECHNIQUE AND IMAGE CYTOMETRY TO CHARACTERIZE AGGRESSIVENESS IN WORLD-HEALTH-ORGANIZATION (WHO) GRADE-II SUPERFICIAL TRANSITIONAL-CELL CARCINOMAS OF THE BLADDER

The aggressiveness of human bladder tumours can be assessed by means o f various classification systems, including the one proposed by the Wo rld Health Organization (WHO). According to the WHO classification, th ree levels of malignancy are identified as grades I (low), II (interme diate), and III (high), This classification system operates satisfacto rily for two of the three grades in forecasting clinical progression, most grade I tumours being associated with good prognoses and most gra de III with bad, In contrast, the grade II group is very heterogeneous in terms of their clinical behaviour, The present study used two comp uter-assisted methods to investigate whether it is possible to sub-cla ssify grade II tumours: computer-assisted microscope analysis (image c ytometry) of Feulgen-stained nuclei and the Decision Tree Technique, T his latter technique belongs to the Supervised Learning Algorithm and enables an objective assessment to be made of the diagnostic value ass ociated with a given parameter. The combined use of these two methods in a series of 292 superficial transitional cell carcinomas shows that it is possible to identify one subgroup of grade II tumours which beh ave clinically like grade I tumours and a second subgroup which behave s clinically like grade III tumours, Of the nine ploidy-related parame ters computed by means of image cytometry [the DNA index (DI), DNA his togram type (DHT), and the percentages of diploid, hyperdiploid, tripl oid, hypertriploid, tetraploid, hypertetraploid, and polyploid cell nu clei], it was the percentage of hyperdiploid and hypertetraploid cell nuclei which enabled identification, rather than conventional paramete rs such as the DI or the DHT.