DPE-Net: Dual-Parallel Encoder Based Network for Semantic Segmentation of Polyps

TL;DR

DPE-Net introduces a dual-encoder network with parallel branches for improved polyp segmentation, achieving state-of-the-art results on medical datasets by combining diverse feature extraction methods.

Contribution

The paper presents a novel dual-parallel encoder architecture with dual convolution blocks and feature diversity, enhancing segmentation accuracy in medical imaging.

Findings

Achieved Dice scores of 0.919 and 0.931 on two datasets.

Surpassed several established deep-learning models in segmentation performance.

Demonstrated robustness and effectiveness in medical image segmentation tasks.

Abstract

In medical imaging, efficient segmentation of colon polyps plays a pivotal role in minimally invasive solutions for colorectal cancer. This study introduces a novel approach employing two parallel encoder branches within a network for polyp segmentation. One branch of the encoder incorporates the dual convolution blocks that have the capability to maintain feature information over increased depths, and the other block embraces the single convolution block with the addition of the previous layer's feature, offering diversity in feature extraction within the encoder, combining them before transpose layers with a depth-wise concatenation operation. Our model demonstrated superior performance, surpassing several established deep-learning architectures on the Kvasir and CVC-ClinicDB datasets, achieved a Dice score of 0.919, a mIoU of 0.866 for the Kvasir dataset, and a Dice score of 0.931 and a mIoU of 0.891 for the CVC-ClinicDB. The visual and quantitative results highlight the efficacy of our model, potentially setting a new model in medical image segmentation.