A computer-aided diagnosis system for malignant melanomas

作者：Razmjooy N; Mousavi B Somayeh; Soleymani Fazlollah^*; Khotbesara M Hosseini

来源：Neural Computing & Applications, 2013, 23(7-8): 2059-2071.

DOI：10.1007/s00521-012-1149-1

• Malignant melanoma
• Support vector machine
• Segmentation
• Feature extraction
• Texture
• ABCD rule
• Sequential minimal optimization

The aim of this study is to provide an efficient way to segment the malignant melanoma images. This method first eliminates extra hair and scales using edge detection; afterward, it deduces a color image into an intensity image and approximately segments the image by intensity thresholding. Some morphological operations are used to focus on an image area where a melanoma boundary potentially exists and then used to localize the boundary in that area. The distributions of texture and a new feature known as AIBQ features in the next step provide a good discrimination of skin lesions to feature extraction. Finally, we rely on quantitative image analysis to measure a series of candidate attributes hoped to contain enough information to differentiate malignant from benign melanomas. The selected features are applied to a support vector machine to classify the melanomas as malignant or benign. By our approach, we obtained 95 % correct classification of malignant or benign melanoma on real melanoma images.

• 出版日期2013-12