Skin Lesion Classification using Class Activation Map
This work addresses skin lesion classification for medical imaging, but it is incremental as it builds on existing class activation map methods with a two-stage refinement.
The authors tackled skin lesion classification by proposing a two-stage framework using a single convolutional network, which first identifies and crops important regions based on maximum activation, then retrains on these regions to improve classification. This approach achieved a mean AUC of 0.857 on the ISIC-2017 validation set, a 0.036 increase over the baseline of 0.821.
We proposed a two stage framework with only one network to analyze skin lesion images, we firstly trained a convolutional network to classify these images, and cropped the import regions which the network has the maximum activation value. In the second stage, we retrained this CNN with the image regions extracted from stage one and output the final probabilities. The two stage framework achieved a mean AUC of 0.857 in ISIC-2017 skin lesion validation set and is 0.04 higher than that of the original inputs, 0.821.