Back to Search
Start Over
Non-melanoma skin lesion classification using colour image data in a hierarchical K-NN classifier
- Source :
- ISBI, Ballerini, L, Fisher, R B, Aldridge, B & Rees, J 2012, Non-melanoma skin lesion classification using colour image data in a hierarchical K-NN classifier . in Biomedical Imaging (ISBI), 2012 9th IEEE International Symposium on . Institute of Electrical and Electronics Engineers (IEEE), pp. 358-361 . https://doi.org/10.1109/ISBI.2012.6235558
- Publication Year :
- 2012
- Publisher :
- IEEE, 2012.
-
Abstract
- This paper presents an algorithm for classification of non-melanoma skin lesions based on a novel hierarchical K-Nearest Neighbors (K-NN) classifier. The K-NN classifier is simple, quick and effective. The hierarchical structure decomposes the classification task into a set of simpler problems, one at each node of the classification. Feature selection is embedded in the hierarchical framework that chooses the most relevant feature subsets at each node of the hierarchy. Colour and texture features are extracted from skin lesions. The accuracy of the proposed hierarchical scheme is higher than 93% in discriminating cancer and pre-malignant lesions from benign lesions, and it reaches an overall classification accuracy of 74% over five common classes of skin lesions, including two non-melanoma cancer types. This is the most extensive published result on non-melanoma skin cancer classification from colour images acquired by a standard camera (non-dermoscopy).
- Subjects :
- Contextual image classification
business.industry
Computer science
Feature extraction
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Cancer
Pattern recognition
Feature selection
medicine.disease
ComputingMethodologies_PATTERNRECOGNITION
Image texture
medicine
Computer vision
Artificial intelligence
Skin cancer
business
Skin lesion
Classifier (UML)
Non melanoma
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI)
- Accession number :
- edsair.doi.dedup.....0990fbd54e9ae9e36532167ac2d851f1