MFSNet: A multi focus segmentation network for skin lesion segmentation

•We propose a deep learning model called MFSNet (Multi-Focus Segmentation Network).•MFSNet uses differently scaled feature maps for skin lesion segmentation.•It has Boundary Attention, Reverse Attention and Parallel Partial Decoder modules.•It uses Res2Net as backbone which is a recently proposed CNN model.•It outperforms past methods when evaluated on PH2, ISIC2017 and HAM10000 datasets.