Joint Dermatological Lesion Classification and Confidence Modeling with Uncertainty Estimation
This work addresses the need for more reliable deep learning solutions in dermatology by providing uncertainty estimates to prevent overconfident predictions, though it is incremental as it builds on existing methods.
The paper tackles the problem of improving dermatological lesion classification by jointly modeling uncertainty estimation to quantify model confidence and focus on confident features, resulting in improved accuracy on ISIC 2018 and ISIC 2019 datasets.
Deep learning has played a major role in the interpretation of dermoscopic images for detecting skin defects and abnormalities. However, current deep learning solutions for dermatological lesion analysis are typically limited in providing probabilistic predictions which highlights the importance of concerning uncertainties. This concept of uncertainty can provide a confidence level for each feature which prevents overconfident predictions with poor generalization on unseen data. In this paper, we propose an overall framework that jointly considers dermatological classification and uncertainty estimation together. The estimated confidence of each feature to avoid uncertain feature and undesirable shift, which are caused by environmental difference of input image, in the latent space is pooled from confidence network. Our qualitative results show that modeling uncertainties not only helps to quantify model confidence for each prediction but also helps classification layers to focus on confident features, therefore, improving the accuracy for dermatological lesion classification. We demonstrate the potential of the proposed approach in two state-of-the-art dermoscopic datasets (ISIC 2018 and ISIC 2019).