Skin lesion can be benign or skin cancer. Skin cancer is one of the most dangerous cancersrnkilling so many people all over the world. Skin cancer is the most curable cancer if skin lesionsrnare diagnosed at early stage. Skin lesion segmentation is a crucial phase in automated skin lesionrndetection towards skin cancer. Segmentation of skin lesion is the most challenging task forrndermatologists. The rest phases of computer analysis diagnosis of skin cancer mainly depend onrnthe segmentation result. Due to this, many methods of skin lesion segmentation have beenrnproposed to improve the segmentation technique performance in computer aided diagnosis. rnIn this work, skin lesion segmentation using convolution de-convolution neural network andrncontour level set method is used to segment dermoscopic skin lesion images. Convolution deconvolutionrnneuralrnnetworkrnisrntrainedrnpixelrnwisernforrnsemanticrnsegmentationrnofrnpixelsrnintornlesionrnrnandrnrnbackground. Level set is used to find the exact edges of detected lesion boundary byrnconvolution de-convolution neural network method. In addition to the two main proposedrntechniques, preprocessing of the input images is applied to remove unwanted artifacts such asrnhair over the skin lesion image using vector filters and data augmentation to overcome the overrnfitting problem of proposed deep learning network. 2017 International Skin ImagingrnCollaboration (ISIC) archive dataset hosted by International Society of Biomedical Imagingrn(ISBI) for skin lesion analysis towards melanoma detection is used. rnThe performance evaluations on the proposed skin lesion segmentation method is pixel wisernaverage measurements validated against ground truth for test data set are 94.8% intersection overrnunion, 98.80% specificity, 94.84% sensitivity, 97.84% positive predicted value and 95.58%rnnegative predicted value. The proposed method out performs segmentation using convolution deconvolutionrnrnneural network and level set method by more than 2% and 30% respectively. rnTherefore, using convolution de-convolution neural network with level set segmentation methodrnof skin lesion results better than convolution de-convolution neural network segmentation andrnlevel set segmentation.