TY - JOUR AU - Brinker, Titus Josef AU - Hekler, Achim AU - Utikal, Jochen Sven AU - Grabe, Niels AU - Schadendorf, Dirk AU - Klode, Joachim AU - Berking, Carola AU - Steeb, Theresa AU - Enk, Alexander H AU - von Kalle, Christof PY - 2018 DA - 2018/10/17 TI - Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review JO - J Med Internet Res SP - e11936 VL - 20 IS - 10 KW - skin cancer KW - convolutional neural networks KW - lesion classification KW - deep learning KW - melanoma classification KW - carcinoma classification AB - Background: State-of-the-art classifiers based on convolutional neural networks (CNNs) were shown to classify images of skin cancer on par with dermatologists and could enable lifesaving and fast diagnoses, even outside the hospital via installation of apps on mobile devices. To our knowledge, at present there is no review of the current work in this research area. Objective: This study presents the first systematic review of the state-of-the-art research on classifying skin lesions with CNNs. We limit our review to skin lesion classifiers. In particular, methods that apply a CNN only for segmentation or for the classification of dermoscopic patterns are not considered here. Furthermore, this study discusses why the comparability of the presented procedures is very difficult and which challenges must be addressed in the future. Methods: We searched the Google Scholar, PubMed, Medline, ScienceDirect, and Web of Science databases for systematic reviews and original research articles published in English. Only papers that reported sufficient scientific proceedings are included in this review. Results: We found 13 papers that classified skin lesions using CNNs. In principle, classification methods can be differentiated according to three principles. Approaches that use a CNN already trained by means of another large dataset and then optimize its parameters to the classification of skin lesions are the most common ones used and they display the best performance with the currently available limited datasets. Conclusions: CNNs display a high performance as state-of-the-art skin lesion classifiers. Unfortunately, it is difficult to compare different classification methods because some approaches use nonpublic datasets for training and/or testing, thereby making reproducibility difficult. Future publications should use publicly available benchmarks and fully disclose methods used for training to allow comparability. SN - 1438-8871 UR - http://www.jmir.org/2018/10/e11936/ UR - https://doi.org/10.2196/11936 UR - http://www.ncbi.nlm.nih.gov/pubmed/30333097 DO - 10.2196/11936 ID - info:doi/10.2196/11936 ER -