Illumination-based Transformations Improve Skin Lesion Segmentation in Dermoscopic Images
This work addresses segmentation challenges for computer-aided diagnosis in dermatology, but it is incremental as it builds on existing deep learning methods with new data transformations.
The paper tackled the problem of improving skin lesion segmentation in dermoscopic images by incorporating physics-based illumination transformations, resulting in Jaccard index improvements of 12.02%, 4.30%, and 8.86% over a baseline on three datasets.
The semantic segmentation of skin lesions is an important and common initial task in the computer aided diagnosis of dermoscopic images. Although deep learning-based approaches have considerably improved the segmentation accuracy, there is still room for improvement by addressing the major challenges, such as variations in lesion shape, size, color and varying levels of contrast. In this work, we propose the first deep semantic segmentation framework for dermoscopic images which incorporates, along with the original RGB images, information extracted using the physics of skin illumination and imaging. In particular, we incorporate information from specific color bands, illumination invariant grayscale images, and shading-attenuated images. We evaluate our method on three datasets: the ISBI ISIC 2017 Skin Lesion Segmentation Challenge dataset, the DermoFit Image Library, and the PH2 dataset and observe improvements of 12.02%, 4.30%, and 8.86% respectively in the mean Jaccard index over a baseline model trained only with RGB images.