Channel Attention Separable Convolution Network for Skin Lesion Segmentation
This work addresses the problem of automating precise segmentation of skin lesions to assist doctors in early diagnosis, but it is incremental as it builds on existing mechanisms like U-Net and DenseNet.
The paper tackles skin lesion segmentation for early cancer diagnosis by proposing a novel network called CASCN, which achieves state-of-the-art performance on the PH2 dataset with a Dice similarity coefficient of 0.9461 and accuracy of 0.9645.
Skin cancer is a frequently occurring cancer in the human population, and it is very important to be able to diagnose malignant tumors in the body early. Lesion segmentation is crucial for monitoring the morphological changes of skin lesions, extracting features to localize and identify diseases to assist doctors in early diagnosis. Manual de-segmentation of dermoscopic images is error-prone and time-consuming, thus there is a pressing demand for precise and automated segmentation algorithms. Inspired by advanced mechanisms such as U-Net, DenseNet, Separable Convolution, Channel Attention, and Atrous Spatial Pyramid Pooling (ASPP), we propose a novel network called Channel Attention Separable Convolution Network (CASCN) for skin lesions segmentation. The proposed CASCN is evaluated on the PH2 dataset with limited images. Without excessive pre-/post-processing of images, CASCN achieves state-of-the-art performance on the PH2 dataset with Dice similarity coefficient of 0.9461 and accuracy of 0.9645.