CE-Net: Cascade attention and context-aware cross-level fusion network via edge learning guidance for polyp segmentation.

Colorectal polyps are one of the most direct causes of colorectal cancer. Polypectomy can effectively block the process of colorectal cancer, but accurate polyp segmentation methods are required as an auxiliary means. However, there are several challenges associated with achieving accurate polyp segmentation, such as the large semantic gap between the encoder and decoder, the incomplete edges, and the potential confusion between folds in uncertain areas and target objects. To address the aforementioned challenges, an advanced polyp segmentation network (CE-Net) is proposed, leveraging a cascaded attention mechanism and context-aware cross-level fusion guided by edge learning. Firstly, a cascade attention (CA) module is proposed to capture local feature details and increase the receptive field by setting different dilation rates in different convolutional layers, and combines the criss-cross attention mechanism for bridging the semantic gap between codecs. Subsequently, an edge learning guidance (ELG) module is designed that employs parallel axial attention operations to capture complementary edge information with sufficient detail to enrich feature details and edge features. Ultimately, to effectively integrate cross-level features and obtain rich global contextual information, a context-aware cross-level fusion (CCF) module is introduced through a multi-scale channel attention mechanism to minimize potential confusion between folds in uncertain areas and target objects. A plethora of experimental results has shown that CE-Net is superior over the state-of-the-art methods, with average Dice coefficients on five polyp datasets of 94.54 %, 92.23 %, 82.24 %, 79.53 % and 89.84 %.