Computerized consensus diagnosis: a classification strategy for the robust analysis of MR spectra. I. Application to 1H spectra of thyroid neoplasms
| Autor: | Brion Dolenko, Carolyn E. Mountford, Ray L. Somorjai, Peter Russell, Heather L. Gordon, Gordon B. Scarth, Leigh Delbridge, Ian C. P. Smith, Alexander E. Nikulin, Nic Pizzi, Dick Jackson, Cynthia L. Lean |
|---|---|
| Rok vydání: | 1995 |
| Předmět: |
Adenoma
Magnetic Resonance Spectroscopy Biopsy Thyroid Gland Genetic programming Sensitivity and Specificity Fuzzy Logic Artificial Intelligence Adenocarcinoma Follicular Medicine Humans Radiology Nuclear Medicine and imaging Sensitivity (control systems) Diagnosis Computer-Assisted Thyroid Neoplasms Reliability (statistics) Artificial neural network business.industry Carcinoma Decision Trees Discriminant Analysis Reproducibility of Results Pattern recognition Linear discriminant analysis Proton magnetic resonance Carcinoma Papillary Carcinoma Medullary Artificial intelligence Human thyroid Neural Networks Computer business Nuclear medicine Robust analysis Artifacts Algorithms Hydrogen |
| Zdroj: | Magnetic resonance in medicine. 33(2) |
| ISSN: | 0740-3194 |
| Popis: | We introduce and apply a new classification strategy we call computerized consensus diagnosis (CCD). Its purpose is to provide robust, reliable classification of biomedical data. The strategy involves the cross-validated training of several classifiers of diverse conceptual and methodological origin on the same data, and appropriately combining their outcomes. The strategy is tested on proton magnetic resonance spectra of human thyroid biopsies, which are successfully allocated to normal or carcinoma classes. We used Linear Discriminant Analysis, a Neural Net-based method, and Genetic Programming as independent classifiers on two spectral regions, and chose the median of the six classification outcomes as the consensus. This procedure yielded 100% specificity and 100% sensitivity on the training sets, and 100% specificity and 98% sensitivity on samples of known malignancy in the test sets. We discuss the necessary steps any classification approach must take to guarantee reliability, and stress the importance of fuzziness and undecidability in robust classification. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text