Transfer Learning for Melanoma Detection: Participation in ISIC 2017 Skin Lesion Classification Challenge
This work addresses melanoma detection for medical imaging, but it is incremental as it applies existing methods to a specific competition dataset.
The authors tackled the ISIC 2017 skin lesion classification challenge by using transfer learning with a pre-trained Inception V3 network, achieving an average AUC of 0.80 on binary classification tasks.
This manuscript describes our participation in the International Skin Imaging Collaboration's 2017 Skin Lesion Analysis Towards Melanoma Detection competition. We participated in Part 3: Lesion Classification. The two stated goals of this binary image classification challenge were to distinguish between (a) melanoma and (b) nevus and seborrheic keratosis, followed by distinguishing between (a) seborrheic keratosis and (b) nevus and melanoma. We chose a deep neural network approach with a transfer learning strategy, using a pre-trained Inception V3 network as both a feature extractor to provide input for a multi-layer perceptron as well as fine-tuning an augmented Inception network. This approach yielded validation set AUC's of 0.84 on the second task and 0.76 on the first task, for an average AUC of 0.80. We joined the competition unfortunately late, and we look forward to improving on these results.