Abstract
BackgroundIn recent months, multiple publications have demonstrated the use of convolutional neural networks (CNN) to classify images of skin cancer as precisely as dermatologists. However, these CNNs failed to outperform the International Symposium on Biomedical Imaging (ISBI) 2016 challenge which ranked the average precision for classification of dermoscopic melanoma images. Accordingly, the technical progress represented by these studies is limited. In addition, the available reports are impossible to reproduce, due to incomplete descriptions of training procedures and the use of proprietary image databases or non-disclosure of used images. These factors prevent the comparison of various CNN classifiers in equal terms.ObjectiveTo demonstrate the training of an image-classifier CNN that outperforms the winner of the ISBI 2016 CNNs challenge by using open source images exclusively.MethodsA detailed description of the training procedure is reported while the used images and test sets are disclosed fully, to insure the reproducibility of our work.ResultsOur CNN classifier outperforms all recent attempts to classify the original ISBI 2016 challenge test data (full set of 379 test images), with an average precision of 0.709 (vs. 0.637 of the ISBI winner) and with an area under the receiver operating curve of 0.85.ConclusionThis work illustrates the potential for improving skin cancer classification with enhanced training procedures for CNNs, while avoiding the use of costly equipment or proprietary image data.
Highlights
Skin cancer is the most common malignancy in fair-skinned populations, and melanoma accounts for the majority of skin cancer-related deaths worldwide[1,2]
We demonstrate the improved training of a convolutional neural network (CNN) classifier that outperforms the winner of the International Symposium on Biomedical Imaging (ISBI) 2016 challenge
The gradient descent can be disturbed by these local minima with sudden increments of the learning rate at specific time steps, which helps to ensure that the training reaches a global minimum of the loss function. This technique is called stochastic gradient descent with restarts (SGDR), and has been shown to be highly effective for improving the classification performance of CNNs over those trained with stochastic gradient descent alone [25][25]
Summary
Multiple publications have demonstrated the use of convolutional neural networks (CNN) to classify images of skin cancer as precisely as dermatologists. These CNNs failed to outperform the International Symposium on Biomedical Imaging (ISBI) 2016 challenge which ranked the average precision for classification of dermoscopic melanoma images. The available reports are impossible to reproduce, due to incomplete descriptions of training procedures and the use of proprietary image databases or non-disclosure of used images. These factors prevent the comparison of various CNN classifiers in equal terms
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 call
