A comparison of machine learning methods for the diagnosis of pigmented skin lesions

Journal of Biomedical Informatics

Volumn 34, Issue 1, 2001, Pages 28-36

  Dreiseitl, Stephan ^a,b   Ohno Machado, Lucila ^a   Kittler, Harald ^c   Vinterbo, Staal ^a   Billhardt, Holger ^a   Binder, Michael ^a,c  

^a BRIGHAM AND WOMEN S HOSPITAL   (United States)

^b UNIVERSITY OF APPLIED SCIENCES UPPER AUSTRIA   (Austria)

^c Universitatsklinik fur Dermatologie   (Austria)

Author keywords

Decision support; Image classification; Machine learning; Neural networks; Support vector machines

Indexed keywords

ANALYTIC METHOD; ARTICLE; ARTIFICIAL NEURAL NETWORK; DECISION THEORY; DISCRIMINANT ANALYSIS; DISEASE CLASSIFICATION; DYSPLASTIC NEVUS; HUMAN; IMAGE ANALYSIS; LEARNING; MACHINE; MELANOMA; NEVUS; PRIORITY JOURNAL; REGRESSION ANALYSIS;

EID: 0034981810     PISSN: 15320464     EISSN: None     Source Type: Journal    
DOI: 10.1006/jbin.2001.1004     Document Type: Article

References (26)

1. Accuracy in the clinical diagnosis of malignant melanoma
2. Epiluminescence microscopy. A useful tool for the diagnosis of pigmented skin lesions for formally trained dermatologists
3. Nearest-neighbor classification for identification of aggressive versus nonaggressive low-grade astrocytic tumors by means of image cytometry-generated variables
4. Detection of suspected malignant patterns in three-dimensional magnetic resonance breast images
5. Feature selection algorithm for optimized skin tumor recognition using genetic algorithms
6. Regression modelling strategies for improved prognostic prediction
7. Probabilistic prediction in patient management and clinical trials
8. Artificial neural networks for cancer research: Outcome prediction
9. Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithm
10. The limitations of decision trees and automatic learning in real world medical decision making
11. Computational methods for probabilistic decision trees
12. Constructing a minimal diagnostic decision tree
13. Knowledge discovery and knowledge validation in intensive care
14. Three-way ROCs
15. Comparing three-class diagnostic tests by three-way ROC analysis
16. The meaning and use of the area under the receiver operating characteristic (ROC) curve
17. A method of comparing the areas under receiver operating characteristic curves derived from the same cases
18. Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach
19. Multicategory classification by support vector machines
20. Evaluating the yield of medical tests