Skin Cancer Semantic Segmentation

Image segmentation is an important segment of medical image diagnosis. Due to recent advancements in the field of deep learning, image segmentation can be possible without human involvement. Applications of CNN and transformer-based models are being used in every field nowadays. CNN-based models can learn local features efficiently, whereas transformer-based models can learn global features, which makes combining these two a great tool for medical image segmentation. Again, converting the Cartesian image to a polar image reduces the dimension of the elliptical and complex decision boundaries of medical images to a more simple one. In this study, we will try to compare the scores of CNN and transformer-based models on the ISIC-2018 dataset for semantic segmentation of medical images. For the CNN-based model, we will use UNET architecture. We will also use TransUNET, which takes advantage of both CNNs and the transformer. We will also compare the scores obtained from both Cartesian and polar images.