BDG-Net: boundary distribution guided network for accurate polyp segmentation (2022-01-03T00:00:00.000000Z)

TL;DR

A Boundary Distribution Guided Network (BDG-Net) is designed for accurate polyp segmentation and outperforms state-of-the-art models remarkably and maintains low computational complexity.

Abstract

Colorectal cancer (CRC) is one of the most common fatal cancer in the world. Polypectomy can effectively interrupt the progression of adenoma to adenocarcinoma. Colonoscopy is the primary method to find colonic polyps. However, due to the different sizes and the unclear boundary of polyps, it is challenging to segment polyps accurately. To this end, we design a Boundary Distribution Guided Network (BDG-Net) for accurate polyp segmentation. Specifically, Boundary Distribution Generate Module (BDGM) aggregates high-level features to generate Boundary Distribution Map (BDM), which is sent to the Boundary Distribution Guided Decoder (BDGD) as complementary spatial information to guide the polyp segmentation. Moreover, a multi-scale feature interaction strategy is adopted in BDGD to improve the polyp segmentation of different sizes. Extensive experiments demonstrate that BDG-Net outperforms state-of-the-art models remarkably and maintains low computational complexity.

Authors

Zihuan Qiu

1 papers

Zhichuan Wang

1 papers

Miaomiao Zhang

1 papers

BDG-Net: boundary distribution guided network for accurate polyp segmentation

TL;DR

Abstract

Authors

References20 items

PraNet: Parallel Reverse Attention Network for Polyp Segmentation

Kvasir-SEG: A Segmented Polyp Dataset

ResUNet++: An Advanced Architecture for Medical Image Segmentation

Selective Feature Aggregation Network with Area-Boundary Constraints for Polyp Segmentation

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

Enhanced-alignment Measure for Binary Foreground Map Evaluation

Attention U-Net: Learning Where to Look for the Pancreas

Road Extraction by Deep Residual U-Net

Receptive Field Block Net for Accurate and Fast Object Detection

Structure-Measure: A New Way to Evaluate Foreground Maps

A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images

Automated Polyp Detection in Colonoscopy Videos Using Shape and Context Information

WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians

U-Net: Convolutional Networks for Biomedical Image Segmentation

How to Evaluate Foreground Maps

Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancer

Saliency filters: Contrast based filtering for salient region detection

We design BDGM to generate BDM, which can be used as complementary spatial information to guide the accurate polyp segmentation

BDGD, which fuses multi-scales features to improve polyp segmentation on diﬀerent sizes

Field of Study