Neural network and statistical classification methods were applied to derive an objective grading for moderately and poorly differentiated lesions of the prostate, based on characteristics of the nuclear placement patterns. A partly trained multilayer neural network was used as a feature extractor. A hybrid classifier system using a quadratic Bayesian classifier applied to these features allowed grade assignment consensus with visual diagnosis in 96% of fields from a training set of 500 fields and in 77% of 130 fields of a test set.
Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
classifier system
8
neural network
8
hybrid neural
4
neural statistical
4
statistical classifier
4
system histopathologic
4
histopathologic grading
4
grading prostatic
4
prostatic lesions
4
lesions neural
4
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!