Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification
This work aims to enable practical implementation of DCNN-based skin cancer screening in low-resource settings by improving the efficiency and performance of data augmentation, which is an incremental improvement for the medical imaging domain.
This paper addresses the computational cost and training data limitations of deep convolutional neural networks (DCNNs) for skin lesion classification. They propose a data augmentation strategy that reduces the search space to 60 and achieves a balanced accuracy (BACC) of 0.853 using a single DCNN model on the HAM10000 dataset.
Although deep convolutional neural networks (DCNNs) have achieved significant accuracy in skin lesion classification comparable or even superior to those of dermatologists, practical implementation of these models for skin cancer screening in low resource settings is hindered by their limitations in computational cost and training dataset. To overcome these limitations, we propose a low-cost and high-performance data augmentation strategy that includes two consecutive stages of augmentation search and network search. At the augmentation search stage, the augmentation strategy is optimized in the search space of Low-Cost-Augment (LCA) under the criteria of balanced accuracy (BACC) with 5-fold cross validation. At the network search stage, the DCNNs are fine-tuned with the full training set in order to select the model with the highest BACC. The efficiency of the proposed data augmentation strategy is verified on the HAM10000 dataset using EfficientNets as a baseline. With the proposed strategy, we are able to reduce the search space to 60 and achieve a high BACC of 0.853 by using a single DCNN model without external database, suitable to be implemented in mobile devices for DCNN-based skin lesion detection in low resource settings.