Title :
A new algorithm for border description of polarized light surface microscopic images of pigmented skin lesions
Author :
Grana, Costantino ; Pellacani, Giovanni ; Cucchiara, Rita ; Seidenari, Stefania
Author_Institution :
Dept. of Comput. Eng., Univ. of Modena & Reggio Emilia, Italy
Abstract :
The aim of the study was to provide mathematical descriptors for the border of pigmented skin lesion images and to assess their efficacy for distinction among different lesion groups. New descriptors such as lesion slope and lesion slope regularity are introduced and mathematically defined. A new algorithm based on the Catmull-Rom spline method and the computation of the gray-level gradient of points extracted by interpolation of normal direction on spline points was employed. The efficacy of these new descriptors was tested on a data set of 510 pigmented skin lesions, composed by 85 melanomas and 425 nevi, by employing statistical methods for discrimination between the two populations.
Keywords :
biomedical optical imaging; cancer; edge detection; interpolation; light polarisation; luminescence; medical image processing; optical microscopy; skin; splines (mathematics); statistical analysis; tumours; Catmull-Rom spline method; border description; epiluminescence; gray-level gradient; image analysis; interpolation; lesion groups; lesion slope regularity; mathematical descriptors; melanomas; nevi; normal direction; pigmented skin lesions; polarized light surface microscopic images; skin tumor; statistical methods; Data mining; Interpolation; Lesions; Malignant tumors; Microscopy; Optical polarization; Pigmentation; Skin; Spline; Testing; Algorithms; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Melanoma; Microscopy, Polarization; Nevus, Pigmented; Reproducibility of Results; Sensitivity and Specificity; Skin Neoplasms;
Journal_Title :
Medical Imaging, IEEE Transactions on
DOI :
10.1109/TMI.2003.815901
