Conditional Random Fields and Supervised Learning in Automated Skin Lesion Diagnosis
Figure 1
Typical computer aided diagnosis (CAD) pipeline usually adopted for automated skin lesion diagnosis (ASLD). Our goal is to (1) generalize the artifact detection, segmentation as well as a portion of the feature extraction stage into a single mathematical framework and (2) propose and evaluate probabilistic models which employ supervised learning to quickly and automatically “learn” to perform these tasks.