Channel Attention Separable Convolution Network for Skin Lesion Segmentation

TL;DR

This paper introduces CASCN, a novel neural network leveraging channel attention and separable convolution for accurate, automated skin lesion segmentation, achieving state-of-the-art results on the PH2 dataset.

Contribution

The paper proposes a new network architecture, CASCN, combining channel attention and separable convolution for improved skin lesion segmentation accuracy.

Findings

Achieves Dice coefficient of 0.9461 on PH2 dataset.

Attains accuracy of 0.9645 without extensive pre/post-processing.

Outperforms existing methods on the same dataset.

Abstract

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.