论文信息 - Automated skin lesion segmentation with kernel density estimation

Automated skin lesion segmentation with kernel density estimation

Skin lesion segmentation is a complex step for dermoscopy pathological diagnosis. Kernel density estimation is proposed as a segmentation technique based on the statistic distribution of color intensities in the lesion and non-lesion regions.

[1] Brian W. Pogue,et al. Directional Kernel Density Estimation for Classification of Breast Tissue Spectra , 2017, IEEE Transactions on Medical Imaging.

[2] N. Otsu. A threshold selection method from gray level histograms , 1979 .

[3] Nilkamal S. Ramteke,et al. ABCD rule based automatic computer-aided skin cancer detection using MATLAB ® , 2013 .

[4] C. D. Kemp,et al. Density Estimation for Statistics and Data Analysis , 1987 .

[5] Giovanni Pellacani,et al. Validity and Reliability of Dermoscopic Criteria Used to Differentiate Nevi From Melanoma: A Web-Based International Dermoscopy Society Study. , 2016, JAMA dermatology.

[6] E. Parzen. On Estimation of a Probability Density Function and Mode , 1962 .

[7] Pedro M. Ferreira,et al. PH2 - A dermoscopic image database for research and benchmarking , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).