Accurate skin cancer diagnosis based on convolutional neural networks

Abstract

<span>Although melanoma is not the most common type of skin cancer, it is supposed to extend to other areas of the body if not early diagnosed. Melanoma is the deadliest form of skin cancer and accounts for about 75% of deaths associated with skin cancer. The present study introduces an automated technique for skin cancer prediction, detection, and diagnosis including trending noninvasive and nonionizing techniques that combines deep learning methods to diagnose melanoma with high accuracy. Computer-aided diagnosis (CAD) using medical images is utilized to distinguish benign and malignant tumors, which can assist physicians in early identification of symptoms, thus lowering the mortality rate. The CAD system consists of four phases; detection of the region of interest (RoI), using data augmentation techniques, processing RoI using convolutional neural network (CNN) to extract the most important features, and finally the extracted CNN features are input to a support vector machine (SVM) classifier to decode the two classes benign (B) and malignant (M). Two datasets, ISIC and CPTAC-CM, were utilized to train the CNNs. GoogleNet, ResNet-50, AlexNet, and VGG19 were investigated and compared. The accuracy of the proposed CAD system has reached 99.8% for ISIC database and 99.9% for CPTAC-CM database.</span>

Enhancing skin cancer classification using a fusion of Densenet and Mobilenet models: a deep learning ensemble approach

“…These outcomes fared better than the method used to classify skin cancer at the moment. Two datasets-ISIC and CPTAC-CM-were used to train the CNNs in the four-layer CAD system that was proposed (Diab et al, 2022) where investigated and contrasted were GoogleNet, ResNet-50, AlexNet, and VGG19. The suggested CAD system has a 99.8% accuracy rate for the ISIC database and a 99.9% accuracy rate for the CPTAC-CM database.…”

Palembang songket fabric motif image detection with data augmentation based on ResNet using dropout

“…Pattern recognition is one of the artificial intelligence technologies supporting this program [13]- [15]. This technology can be incorporated into applications to aid in recognizing woven fabric motif without consulting a cultural expert [16]- [25].…”

Kidney stones detection based on deep learning and discrete wavelet transform

“…The role of artificial intelligence in the medical field as well as in many other fields is shown through deep learning in general and the convolutional neural network in particular, there has been interest in artificial intelligence and deep learning recently due to the large and massive amounts of data that need to be examined and knowledge of the sample being examined [1], [2]. Diab et al [3] deep learning and convolutional neural network training were used to detect brain tumors, especially ResNet50 was used, with an accuracy of 99.8% with an error of 0.005. As for skin cancer, it was detected in [4] by using convolutional neural networks for early disease recognition using the classifier (SVM).…”