MCE-Net: polyp segmentation with multiple branch series-parallel attention and channel interaction via edge distribution guidance

Objective.Accurate polyp segmentation is vital for diagnosing colorectal cancer. However, it is still challenging for accurate polyp segmentation and several bottlenecks exist, such as incomplete boundary, localization bias and lack of micro blocks along with large fragmented boundaries in uncertain regions.Approach.To address the above issues, a novel polyp segmentation network with multiple branch series-parallel attention (MBSA) and channel interaction via edge distribution guidance is proposed. Initially, the edge distribution guidance strategy is proposed to generate the edge distribution following Cauchy distribution to capture complementary edges with sufficient details. Subsequently, a MBSA module is put forward to extract features from various receptive fields to pinpoint tiny polyps by a multiple kernel dilated convolution block, while combining semantics of different dimensions to filter out noise and refining the details of micro target. Ultimately, the channel interaction model is proposed to improve the segmentation accuracy of the polyps in uncertain area by splitting channels into groups and conducts group-wise interaction to excavate subtle clues contained in different channels.Main results.Extensive experimental results demonstrate that the proposed method is superior over the state-of-the-art methods with the mean dice of 0.8972, 0.9420, 0.8312, 0.8064 and 0.9214 on five public polyp datasets.Significance.The proposed method improves the integrity of the margins and internal details for polyp segmentation, which will provide a powerful aid for doctors to achieve accurate judgments, reducing the likelihood of colorectal cancer and improving the survival chances of patients.