J. Iglesias et al., Diagnosis of human oligodendrogliomas with the help of the NeuroShell EasyClassifier (TM) neural network, ANAL QUAN C, 22(5), 2000, pp. 383-392
Citations number
63
Categorie Soggetti
Medical Research Diagnosis & Treatment
Journal title
ANALYTICAL AND QUANTITATIVE CYTOLOGY AND HISTOLOGY
OBJECTIVE: To examine whether a suitable solution can be found concerning t
he ability to reproduce the histologic classification of human oligodendrog
liomas with the assistance of the NeuroShell Easy Classifier(TM) neural net
work.
STUDY DESIGN: Histologic sections of 449 human oligodendrogliomas were sele
cted. The diagnostic task was given by differentiation of three oligodendro
glioma types: 121 low grade oligodendrogliomas, World Health Organization g
rade 2; 180 low grade oligoastrocytomas; and 148 anaplastic oligodendroglio
mas, grade 3. Age, sex and 50 histologic characteristics were examined in e
ach case, describing the presence of a specific histologic feature on a sca
le of four (zero, absence of the feature; three, abundant presence). From e
ach group, two-thirds of randomly selected tumors were available for the tr
aining set and one-third for the testing set.
RESULTS: In the three-class problem, 98.88% of the tumors were correctly cl
assified (testing set). Ninety-nine percent of new testing tumors were corr
ectly classified with Easy Classifier(TM) as low grade and anaplastic oligo
dendrogliomas. In the case of low grade oligodendrogliomas versus low grade
oligoastrocytomas, 99% of new tumors were correctly classified.
CONCLUSION: The main conclusion from this study is that Easy Classifier(TM)
was able to differentiate, with high accuracy, sensitivity and specificity
, among the three types of oligodendrogliomas.