Melanoma Classification from Dermoscopy Images Using Ensemble of Convolutional Neural Networks

Abstract

Human skin is the most exposed part of the human body that needs constant protection and care from heat, light, dust, and direct exposure to other harmful radiation, such as UV rays. Skin cancer is one of the dangerous diseases found in humans. Melanoma is a form of skin cancer that begins in the cells (melanocytes) that control the pigment in human skin. Early detection and diagnosis of skin cancer, such as melanoma, is necessary to reduce the death rate due to skin cancer. In this paper, the classification of acral lentiginous melanoma, a type of melanoma with benign nevi, is being carried out. The proposed stacked ensemble method for melanoma classification uses different pre-trained models, such as Xception, Inceptionv3, InceptionResNet-V2, DenseNet121, and DenseNet201, by employing the concept of transfer learning and fine-tuning. The selection of pre-trained CNN architectures for transfer learning is based on models having the highest top-1 and top-5 accuracies on ImageNet. A novel stacked ensemble-based framework is presented to improve the generalizability and increase robustness by fusing fine-tuned pre-trained CNN models for acral lentiginous melanoma classification. The performance of the proposed method is evaluated by experimenting on a Figshare benchmark dataset. The impact of applying different augmentation techniques has also been analyzed through extensive experimentations. The results confirm that the proposed method outperforms state-of-the-art techniques and achieves an accuracy of 97.93%.

Dermatopathology of Malignant Melanoma in the Era of Artificial Intelligence: A Single Institutional Experience

“…The main motivation is in the novel approach adopted for the algorithm training. Other studies use a traditional approach based on the discrimination of the training model and of the testing model, which are performed by adopting different images [ 21 ]. In the proposed approach, it adopts the same image both for the training and for the testing: each image is converted into grayscale images, and in the same image [ 12 ] the classes training the model are identified (classes of similar features, including those of the Spitz nevi).…”

Privacy Preserving Image Encryption with Optimal Deep Transfer Learning Based Accident Severity Classification Model

“…At this stage, the features involved in the RoI are extracted by the Xception model. For effective feature extraction, the Xception architecture was introduced to extract feature vectors [ 29 ]. Initially, a pretrained Xception network model is selected named Inception.…”

Multiclass Skin Less Ions Classification Based on Deep Neural Networks

“…Extensive systems use images of different birthmarks, each of the diseases is marked as a class. The review of the multiclass classification was carried out in many works [2,4,21,36,38,47]. Table 1 presents a list of works that achieved a high ACC score for the classification of skin birthmarks based on CNN.…”