Double Encoder-Decoder Networks for Gastrointestinal Polyp Segmentation

TL;DR

This paper introduces a double encoder-decoder network architecture for gastrointestinal polyp segmentation, significantly improving accuracy over traditional single networks and achieving state-of-the-art results across multiple datasets.

Contribution

The novel double encoder-decoder framework enhances polyp segmentation by using sequential networks with attention mechanisms, outperforming existing methods.

Findings

Outperforms single encoder-decoder models in all tested datasets.

Achieves state-of-the-art segmentation accuracy.

Shows robustness on datasets not used during training.

Abstract

Polyps represent an early sign of the development of Colorectal Cancer. The standard procedure for their detection consists of colonoscopic examination of the gastrointestinal tract. However, the wide range of polyp shapes and visual appearances, as well as the reduced quality of this image modality, turn their automatic identification and segmentation with computational tools into a challenging computer vision task. In this work, we present a new strategy for the delineation of gastrointestinal polyps from endoscopic images based on a direct extension of common encoder-decoder networks for semantic segmentation. In our approach, two pretrained encoder-decoder networks are sequentially stacked: the second network takes as input the concatenation of the original frame and the initial prediction generated by the first network, which acts as an attention mechanism enabling the second network to focus on interesting areas within the image, thereby improving the quality of its predictions. Quantitative evaluation carried out on several polyp segmentation databases shows that double encoder-decoder networks clearly outperform their single encoder-decoder counterparts in all cases. In addition, our best double encoder-decoder combination attains excellent segmentation accuracy and reaches state-of-the-art performance results in all the considered datasets, with a remarkable boost of accuracy on images extracted from datasets not used for training.