Globally skin cancer is one of the main cause of death in humans. Early diagnosis plays a major role in increasing the prevention of death rate caused due to any kind of cancer. Conventional diagnosis of skin cancer is a tedious and time-consuming process. To overcome this an automated skin lesion classification must develop. Automated skin lesion classification is a challenging task due to the fine-grained variability in the visibility of skin lesions. In this work dermoscopic images are obtained from the International Skin Image Collaboration Archive 2016 (ISIC 2016). In the proposed method the analysis and classification of skin lesions is done with the help of a Convolution Neural Network (CNN) along with the hand crafted features of dermoscopic image using Scattered Wavelet Transform as additional input to the fully connected layer of CNN, which leads to an improvement in the accuracy for identifying Melanoma and different skin lesion classification when compared to the other state of the art methods. When raw dermoscopic image is given as an input to the CNN and feature values of segmented dermoscopic image as input to the fully connected layer as an additional information, the proposed method gives a classification accuracy of 98.13% for identification of Melanoma and the accuracy achieved for classification of skin lesions is 93.14% for Melanoma Vs Nevus, 95.4% for Seborrheic Keratosis (SK) vs Squamous Cell Carcinoma (SCC), 96.87% for Melanoma vs Seborrheic Keratosis (SK), 95.65% for Melanoma vs Basal Cell Carcinoma (BCC), 98.5% for Nevus vs Basal Cell Carcinoma(BCC).
Background: We propose a novel global region based method for segmentation of biomedical images with a fast level set model using Kernel Fuzzy Particles Swarm Optimization (KFPSO) clustering. In the field of medical study, segmentation of biomedical images is one of the most important approaches for the diagnosis of a patient. Segmentation of these images is still a tedious task and cumbersome due to weak contrast and poor resolution of images etc. The automatic segmentation of such images is very difficult. The main reason is a large amount of inhomogeneity present in the background and foreground of real world image. The conventional methods like C-V model and Distance Regularized Level Set (DRLS) method lead to getting improper segmentation with unconvinced results. Methods: We proposed an efficient segmentation method for MRI biomedical images with level set approach using KFPSO clustering. In the pre-processing step, Kernel Fuzzy C- Means (KFCM) clustering is combined with PSO Initialization algorithm called KFPSO clustering for improving the clustering efficiency. In KFCM clustering algorithm, the initial cluster center is chosen randomly, and with the help of PSO, the optimal cluster centers are chosen. Results: The Membership Function (MF) of this algorithm is less sensitive to noise and consideration of the spatial information. In the post processing step, the resulting Kernel fuzzy PSO clustering is modified to the level set model for faster and accurate segmentation. Conclusion: The Proposed segmentation results are effective, superior and accurate compared to conventional methods. This new approach is very helpful for accurate detection of the white matter and gray matter, cancerous cells in brain and bone images.