FCN-Based DenseNet Framework for Automated Detection and Classification of Skin Lesions in Dermoscopy Images

Abstract

Skin Lesion detection and classification are very critical in diagnosing skin malignancy. Existing Deep learning-based Computer-aided diagnosis (CAD) methods still perform poorly on challenging skin lesions with complex features such as fuzzy boundaries, artifacts presence, low contrast with the background and, limited training datasets. They also rely heavily on a suitable turning of millions of parameters which often leads to over-fitting, poor generalization, and heavy consumption of computing resources. This study proposes a new framework that performs both segmentation and classification of skin lesions for automated detection of skin cancer. The proposed framework consists of two stages: the first stage leverages on an encoder-decoder Fully Convolutional Network (FCN) to learn the complex and inhomogeneous skin lesion features with the encoder stage learning the coarse appearance and the decoder learning the lesion borders details. Our FCN is designed with the sub-networks connected through a series of skip pathways that incorporate long skip and shortcut connections unlike, the only long skip connections commonly used in the traditional FCN, for residual learning strategy and effective training. The network also integrates the Conditional Random Field (CRF) module which employs a linear combination of Gaussian kernels for its pairwise edge potentials for contour refinement and lesion boundaries localization. The second stage proposes a novel FCN-based DenseNet framework that is composed of dense blocks that are merged and connected via the concatenation strategy and transition layer. The system also employs hyperparameters optimization techniques to reduce network complexity and improve computing efficiency. This approach encourages feature reuse and thus requires a small number of parameters and effective with limited data. The proposed model was evaluated on publicly available HAM10000 dataset of over 10000 images consisting of 7 different categories of diseases with 98% accuracy, 98.5% recall, and 99% of AUC score respectively.

Dermoscopy Image Classification Based on StyleGAN and DenseNet201

“…Experiment results and analyses showed the effectiveness of the proposed framework, which achieved better accuracy than many existing works in skin disease tasks. Adegun, Adekanmi A et al [33] proposed a new framework that performed both segmentation and classification of skin lesions for automated detection of skin cancer, The proposed model was evaluated on a publicly available HAM10000 dataset and achieved excellent results.…”

A Probabilistic-Based Deep Learning Model for Skin Lesion Segmentation

“…The probability model is a conditional model that employs Gibbs distribution [23,24] in which the probability P(y|x) is modeled as:…”

Cancer-Net SCa: Tailored Deep Neural Network Designs for Detection of Skin Cancer from Dermoscopy Images

“…Motivated by the tremendous advances in the field of deep learning [22] and the great potential it has shown in a wide range of clinical decision support applications [23,24,25,26,27,19,28,29], a number of recent studies have explored the efficacy of deep neural networks for the purpose of skin cancer detection [19,28,30,31,32,33,34,35,36,37]. In a recent study by Budhiman et al [19,21], a comprehensive exploration of different residual network architectures was conducted for the purpose of melanoma detection, with the best quantitative results found when leveraging a ResNet-50 [38] architecture.…”