In this paper, a methodological approach to the classification of tumour skin lesions in dermoscopy images is presented. Melanomas are the most malignant skin tumours. They grow in melanocytes, the cells responsible for pigmentation. This type of cancer is increasing rapidly; its related mortality rate is increasing more modestly, and inversely proportional to the thickness of the tumour. The mortality rate can be decreased by earlier detection of suspicious lesions and better prevention. Using skin tumour features such as colour, symmetry and border regularity, an attempt is made to determine if the skin tumour is a melanoma or a benign tumour. In this work, we are interested in extracting specific attributes which can be used for computer-aided diagnosis of melanoma, especially among general practitioners. In the first step, we eliminate surrounding hair in order to eliminate the residual noise. In the second step, an automatic segmentation is applied to the image of the skin tumour. This method reduces a colour image into an intensity image and approximately segments the image by intensity thresholding. Then, it refines the segmentation using the image edges, which are used to localize the boundary in that area of the skin. This step is essential to characterize the shape of the lesion and also to locate the tumour for analysis. Then, a sequences of transformations is applied to the image to measure a set of attributes (A: asymmetry, B: border, C: colour and D: diameter) which contain sufficient information to differentiate a melanoma from benign lesions. Finally, the various signs of specific lesion (ABCD) are provided to an artificial neural network to differentiate between malignant tumours and benign lesions.

Automated analysis and interpretation of retinal images has become an incontournable diagnostic step in ophthalmology. Retinal blood vessels morphology can be an important indicator for diseases such as diabetic retinopathy; and their detection also serves for image registration. This paper presents a method based on mathematical morphology for extraction of vascular tree in color retinal image with low contrast. It consists in contrast enhancement and application of watershed transformation in order to segment blood vessels in digital fundus images.

No abstract

Our objective in this paper is to introduce the efficacies of texture in the interpretation of color skin images. Melanoma is the most malignant skin tumor, growing in melanocytes, the cells responsible for pigmentation. This type of cancer is nowadays increasing rapidly; its related mortality rate increases by more modest and inversely proportional to the thickness of the tumor. This rate can be decreased by an earlier detection and better prevention. Using the features of skin tumors, such as color, symmetry, and border regularity, an attempt is made to determinate if the skin tumor is a melanoma or a benign tumor. In this work, we are interested by adding to form parameters such as the asymmetry (A) and the shape irregularities of skin tumors (B), the textural parameters to estimate colors in dermatoscopic images. In this case, the images are analyzed using textural parameters computed in several directions. These parameters and the form parameters are added to obtain a better classification results. A statistical analysis is performed over these ratios to select the most highly discriminating textural parameters. The method has been tested successfully on 144 images and we found significant differences between the lesions (melanoma and benign). Finally, these parameters (form and parameters of texture selected) are only use to classify the benign and malignancy of the skin lesion. A multilayer neural network is employed to differentiate between malignant tumors and benign lesions.

In this paper, a methodological approach to the segmentation of tumours skin lesions in dermoscopy images is presented. Melanoma is the most malignant skin tumor, growing in melanocytes, the cells responsible for pigmentation. This type of cancer is nowadays increasing rapidly, its related mortality rate increases by more modest and inversely proportional to the thickness of the tumor. This rate can be decreased by an earlier detection and better prevention. In dermatoscopic images, the segmentation is essential to characterize the information shape of the lesion and also to locate the tumor for analysis. In this domain, we have evaluated several techniques for the segmentation of dermatoscopic images. All these methods do not exactly separate the lesion from the background. In this work a fast approach in border detection of dermoscopy pigmented skin lesions images based on the region growing algorithm is presented. This method is tested on a set of 60 dermoscopy images. The obtained results show that the presented method achieves both fast and accurate border detection.