Department of Information Technology, Faculty of Computers and Informatics, Zagazig University, Zagazig, Egypt.
Department of Robotics and Intelligent Machines, Director of the Quality Assurance Unit, Faculty of Artificial Intelligence, Kafrelsheikh University, Kafr el-Sheikh, Egypt.
J Digit Imaging. 2022 Apr;35(2):258-280. doi: 10.1007/s10278-021-00552-0. Epub 2022 Jan 11.
Skin cancer is the most common type of cancer that affects humans and is usually diagnosed by initial clinical screening, which is followed by dermoscopic analysis. Automated classification of skin lesions is still a challenging task because of the high visual similarity between melanoma and benign lesions. This paper proposes a new residual deep convolutional neural network (RDCNN) for skin lesions diagnosis. The proposed neural network is trained and tested using six well-known skin cancer datasets, PH2, DermIS and Quest, MED-NODE, ISIC2016, ISIC2017, and ISIC2018. Three different experiments are carried out to measure the performance of the proposed RDCNN. In the first experiment, the proposed RDCNN is trained and tested using the original dataset images without any pre-processing or segmentation. In the second experiment, the proposed RDCNN is tested using segmented images. Finally, the utilized trained model in the second experiment is saved and reused in the third experiment as a pre-trained model. Then, it is trained again using a different dataset. The proposed RDCNN shows significant high performance and outperforms the existing deep convolutional networks.
皮肤癌是最常见的影响人类的癌症类型，通常通过初步临床筛查进行诊断，然后进行皮肤镜分析。由于黑色素瘤和良性病变之间具有很高的视觉相似性，因此自动对皮肤病变进行分类仍然是一项具有挑战性的任务。本文提出了一种用于皮肤病变诊断的新的残差深度卷积神经网络（RDCNN）。所提出的神经网络使用六个著名的皮肤癌数据集 PH2、DermIS 和 Quest、MED-NODE、ISIC2016、ISIC2017 和 ISIC2018 进行训练和测试。进行了三个不同的实验来衡量所提出的 RDCNN 的性能。在第一个实验中，使用原始数据集图像对所提出的 RDCNN 进行训练和测试，而无需进行任何预处理或分割。在第二个实验中，使用分割后的图像对所提出的 RDCNN 进行测试。最后，在第三个实验中，将在第二个实验中使用的经过训练的模型保存并重新用作预训练模型。然后，使用不同的数据集再次对其进行训练。所提出的 RDCNN 表现出显著的高性能，优于现有的深度卷积网络。
