Abstract | ||
---|---|---|
In this paper, we present a texture analysis based method for diagnosing the Basal Cell Carcinoma (BCC) skin cancer using optical images taken from the suspicious skin regions. We first extracted the Run Length Matrix and Haralick texture features from the images and used a feature selection algorithm to identify the most effective feature set for the diagnosis. We then utilized a Multi-Layer Perceptron (MLP) classifier to classify the images to BCC or normal cases. Experiments showed that detecting BCC cancer based on optical images is feasible. The best sensitivity and specificity we achieved on our data set were 94% and 95%, respectively. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1117/12.878124 | Proceedings of SPIE |
Keywords | Field | DocType |
BCC Skin Cancer,Texture Analysis,Gray Level Run Length Matrix (GLCM),Gray Level Co-occurrence Matrix (GLCM) | Computer vision,Basal cell carcinoma,Feature selection,Skin cancer,Feature set,Artificial intelligence,SKIN REGIONS,Medical diagnostics,Classifier (linguistics),Perceptron,Physics | Conference |
Volume | ISSN | Citations |
7963 | 0277-786X | 0 |
PageRank | References | Authors |
0.34 | 3 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shao-Hui Chuang | 1 | 6 | 2.28 |
Xiaoyan Sun | 2 | 15 | 4.26 |
wenyu chang | 3 | 0 | 0.68 |
Gwo-Shing Chen | 4 | 5 | 0.82 |
adam huang | 5 | 0 | 1.35 |
jiang li | 6 | 23 | 9.88 |
Frederic D Mckenzie | 7 | 75 | 18.51 |