Neural Networks for Classification of Image Data in Quantitative Pathology
| Autor: | D. D. Komitowski, C. P. Janson |
|---|---|
| Rok vydání: | 1997 |
| Předmět: |
Decision support system
Artificial neural network Computer science business.industry Quadratic classifier Linear discriminant analysis Machine learning computer.software_genre Statistical classification ComputingMethodologies_PATTERNRECOGNITION Tumor Grading Artificial intelligence Quantitative pathology business Classifier (UML) computer |
| Zdroj: | Classification and Knowledge Organization ISBN: 9783540629818 |
| DOI: | 10.1007/978-3-642-59051-1_47 |
| Popis: | Computerized image analysis in tumor grading offers new possibilities for the decision support in diagnosis. But one of the major problems remains the selection of the optimal classifier for the quantitative data. From this point of view artificial neural networks were examined, particularly after architecture selection. Optimized nets were tested on several data sets and compared to statistical classification methods. Concerning generalization ability, neural nets did not surpass statistical procedures. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|