Multi-spectral image analysis and classification of melanoma using fuzzy membership based partitions
| Autor: | Sachin V. Patwardhan, Atam P. Dhawan, Shuangshuang Dai |
|---|---|
| Rok vydání: | 2005 |
| Předmět: |
Skin Neoplasms
Fuzzy classification Channel (digital image) Feature vector Gaussian ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Health Informatics Fuzzy logic Diagnosis Differential symbols.namesake Fuzzy Logic Image Interpretation Computer-Assisted Humans Radiology Nuclear Medicine and imaging Sensitivity (control systems) Melanoma Mathematics Radiological and Ultrasound Technology business.industry Wavelet transform Pattern recognition Computer Graphics and Computer-Aided Design United States ComputingMethodologies_PATTERNRECOGNITION symbols Computer Vision and Pattern Recognition Artificial intelligence business Dysplastic Nevus Syndrome Energy (signal processing) |
| Zdroj: | Computerized Medical Imaging and Graphics. 29:287-296 |
| ISSN: | 0895-6111 |
| DOI: | 10.1016/j.compmedimag.2004.11.001 |
| Popis: | The sensitivity and specificity of melanoma diagnosis can be improved by adding the lesion depth and structure information obtained from the multi-spectral, trans-illumination images to the surface characteristic information obtained from the epi-illumination images. Wavelet transform based bi-modal channel energy features obtained from the images are used in the analysis. Methods using both crisp and fuzzy membership based partitioning of the feature space are evaluated. For this purpose, the ADWAT classification method that uses crisp partitioning is extended to handle multi-spectral image data. Also, multi-dimensional fuzzy membership functions with Gaussian and Bell profiles are proposed for classification. Results show that the fuzzy membership functions with Bell profile are more effective than the extended ADWAT method in discriminating melanoma from dysplastic nevus. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect