Knowledge Transfer for Melanoma Screening with Deep Learning
This work addresses the challenge of limited training data in medical imaging by optimizing transfer learning for melanoma detection, though it is incremental as it builds on existing methods.
The study systematically evaluated transfer learning for melanoma screening, finding that deeper models pre-trained on ImageNet with fine-tuning achieved AUCs of 80.7% and 84.5% on two skin-lesion datasets.
Knowledge transfer impacts the performance of deep learning -- the state of the art for image classification tasks, including automated melanoma screening. Deep learning's greed for large amounts of training data poses a challenge for medical tasks, which we can alleviate by recycling knowledge from models trained on different tasks, in a scheme called transfer learning. Although much of the best art on automated melanoma screening employs some form of transfer learning, a systematic evaluation was missing. Here we investigate the presence of transfer, from which task the transfer is sourced, and the application of fine tuning (i.e., retraining of the deep learning model after transfer). We also test the impact of picking deeper (and more expensive) models. Our results favor deeper models, pre-trained over ImageNet, with fine-tuning, reaching an AUC of 80.7% and 84.5% for the two skin-lesion datasets evaluated.