Segmentation of skin lesions using active contour s initialized by region growing

Image processing methods allied to medical imaging systems have been extensively developed, and several solutions have been accomplished to assist medical professionals in the diagnosis and follow up of diseases from images, in a fast and accurate way. For example, the processing and analysis of images of skin lesions have been gained an increasing attention due to the extremely high importance of an adequate precocious diagnosis of such lesions. Some characteristics commonly considered by dermatologists in the analysis of skin lesions are: contour’ irregularity, shape’ asymmetry, color variation along inner areas and lesion’ dimensions [1]. In this sense, techniques of image processing and analyses can be used to help dermatologists on their diagnosis by extracting lesion contours from images and characterizing the lesions involved.

[1]  Jim R. Parker,et al.  Algorithms for image processing and computer vision , 1996 .

[2]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[3]  Zhen Ma,et al.  A review of algorithms for medical image segmentation and their applications to the female pelvic cavity , 2010, Computer methods in biomechanics and biomedical engineering.