No abstract

No abstract

No abstract

Skin cancer is one of the major public health concerns among the white population with more than a hundred thousand cases every year. Melanoma is one of the deadliest forms of skin cancer which is responsible for thousands of deaths in US alone in recent years and, therefore, early diagnosis is very important to increase the survival rate of melanoma patients. In last few years’ Deep neural networks have been utilized by researchers to build best models for classifying or diagnosing skin cancer. In this paper Deep neural network-based CNN architectures to classify Melanoma is proposed. The CNN architecture proposed in this work is implemented on CPU, GPU and TPU and the performance of the model is shown on all these platforms. The proposed model is compared to other works done so far for melanoma diagnosis in terms of various performance metrics like prediction accuracy, specifity, sensitivity and it is observed that the proposed models outperformed them. The dataset utilized in training and testing the proposed models is ISIC archive dataset which contains 4750 skin images for two classes i.e. melanoma and benign. The results of our study have proved that utilizing GPU and TPU speeds up the training 38 times faster than CPU and can accelerate the performance of CNN for features extraction, optimization and classification of skin cancer images and the proposed model has outperformed the other models compared with it.

Skin cancer is one of the most common human malignancies, which is generally diagnosed by screening and dermoscopic analysis followed by histopathological assessment and biopsy. Deep-learning-based methods have been proposed for skin lesion classification in the last few years. The major drawback of all methods is that they require a considerable amount of training data, which poses a challenge for classifying medical images as limited datasets are available. The problem can be tackled through transfer learning, in which a model pre-trained on a huge dataset is utilized and fine-tuned as per the problem domain. This paper proposes a new Convolution neural network architecture to classify skin lesions into two classes: benign and malignant. The Google Xception model is used as a base model on top of which new layers are added and then fine-tuned. The model is optimized using various optimizers to achieve the maximum possible performance gain for the classifier output. The results on ISIC archive data for the model achieved the highest training accuracy of 99.78% using Adam and LazyAdam optimizers, validation and test accuracy of 97.94% and 96.8% using RMSProp, and on the HAM10000 dataset utilizing the RMSProp optimizer, the model achieved the highest training and prediction accuracy of 98.81% and 91.54% respectively, when compared to other models.