Dermoscopic Image Analysis for ISIC Challenge 2018
This work addresses skin lesion analysis for medical imaging, but it is incremental as it uses existing methods on a specific challenge dataset.
The authors tackled the ISIC Challenge 2018 by applying modified PSPNet for lesion segmentation and attribute detection, and DenseNet-169 for disease classification, reporting evaluation performances for all tasks.
This short paper reports the algorithms we used and the evaluation performances for ISIC Challenge 2018. Our team participates in all the tasks in this challenge. In lesion segmentation task, the pyramid scene parsing network (PSPNet) is modified to segment the lesions. In lesion attribute detection task, the modified PSPNet is also adopted in a multi-label way. In disease classification task, the DenseNet-169 is adopted for multi-class classification.