Abstract
Basal Cell Carcinoma (BCC) is the most frequent skin cancer and its increasing incidence is producing a high overload in dermatology services. In this sense, it is convenient to aid physicians in detecting it soon. Thus, in this paper, we propose a tool for the detection of BCC to provide a prioritization in the teledermatology consultation. Firstly, we analyze if a previous segmentation of the lesion improves the ulterior classification of the lesion. Secondly, we analyze three deep neural networks and ensemble architectures to distinguish between BCC and nevus, and BCC and other skin lesions. The best segmentation results are obtained with a SegNet deep neural network. A 98% accuracy for distinguishing BCC from nevus and a 95% accuracy classifying BCC vs. all lesions have been obtained. The proposed algorithm outperforms the winner of the challenge ISIC 2019 in almost all the metrics. Finally, we can conclude that when deep neural networks are used to classify, a previous segmentation of the lesion does not improve the classification results. Likewise, the ensemble of different neural network configurations improves the classification performance compared with individual neural network classifiers. Regarding the segmentation step, supervised deep learning-based methods outperform unsupervised ones.
Highlights
Skin cancer is the most common cancer in the United States and worldwide [1]
The majority of the works in the literature are focused on melanoma detection, the most common malign skin lesion is the non-melanoma skin cancer (NMSC)
To the best of our knowledge, there are no previous works that evaluate the influence of a previous segmentation in the classification of skin lesions with a deep neural network
Summary
Skin cancer is the most common cancer in the United States and worldwide [1]. the majority of the works in the literature are focused on melanoma detection, the most common malign skin lesion is the non-melanoma skin cancer (NMSC). In Han et al, 12 skin diseases were classified, employing a deep learning algorithm They used three databases and concluded that the tested algorithm performance is comparable to that obtained by 16 dermatologists. One of these skin diseases is BCC [15]. Sies et al [18] tested two market-approved tools, one employed a Machine Learning (ML) technique and one is based on Convolutional Neural Networks (CNN). They tested 1981 skin lesions, only 28 lesions were BCC. To the best of our knowledge, there are no previous works that evaluate the influence of a previous segmentation in the classification of skin lesions with a deep neural network
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
