A CNN toolbox for skin cancer classification
This provides a practical tool for researchers and clinicians working on skin cancer classification, though it is incremental as it builds on existing CNN methods.
The authors developed a software toolbox to configure deep neural networks for skin cancer classification, enabling both developers and non-technical users to efficiently set up and explore CNN architectures and hyperparameters. Preliminary results with two CNNs for melanoma detection quantified the impact of image augmentation, resolution, and rescaling filters on detection performance and training time.
We describe a software toolbox for the configuration of deep neural networks in the domain of skin cancer classification. The implemented software architecture allows developers to quickly set up new convolutional neural network (CNN) architectures and hyper-parameter configurations. At the same time, the user interface, manageable as a simple spreadsheet, allows non-technical users to explore different configuration settings that need to be explored when switching to different data sets. In future versions, meta leaning frameworks can be added, or AutoML systems that continuously improve over time. Preliminary results, conducted with two CNNs in the context melanoma detection on dermoscopic images, quantify the impact of image augmentation, image resolution, and rescaling filter on the overall detection performance and training time.