ColonNet: A novel polyp segmentation framework based on LK-RFB and GPPD

Dong Sui; Weifeng Liu; Yue Zhang; Yang Li; Gongning Luo; Kuanquan Wang; Maozu Guo

doi:10.1016/j.compbiomed.2023.107541

ColonNet: A novel polyp segmentation framework based on LK-RFB and GPPD

Comput Biol Med. 2023 Sep 30:166:107541. doi: 10.1016/j.compbiomed.2023.107541. Online ahead of print.

Authors

Dong Sui¹, Weifeng Liu², Yue Zhang³, Yang Li², Gongning Luo⁴, Kuanquan Wang⁴, Maozu Guo²

Affiliations

¹ School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, China. Electronic address: suidongcs2016@gmail.com.
² School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, China.
³ College of Computer Science and Technology, Harbin Engineering University, Harbin, China. Electronic address: yuezhang@hrbeu.edu.cn.
⁴ Perceptual Computing Research Center, Harbin Institute of Technology, Harbin, China.

PMID: 37804779
DOI: 10.1016/j.compbiomed.2023.107541

Abstract

Colorectal cancer (CRC) holds the distinction of being the most prevalent malignant tumor affecting the digestive system. It is a formidable global health challenge, as it ranks as the fourth leading cause of cancer-related fatalities around the world. Despite considerable advancements in comprehending and addressing colorectal cancer (CRC), the likelihood of recurring tumors and metastasis remains a major cause of high morbidity and mortality rates during treatment. Currently, colonoscopy is the predominant method for CRC screening. Artificial intelligence has emerged as a promising tool in aiding the diagnosis of polyps, which have demonstrated significant potential. Unfortunately, most segmentation methods face challenges in terms of limited accuracy and generalization to different datasets, especially the slow processing and analysis speed has become a major obstacle. In this study, we propose a fast and efficient polyp segmentation framework based on the Large-Kernel Receptive Field Block (LK-RFB) and Global Parallel Partial Decoder(GPPD). Our proposed ColonNet has been extensively tested and proven effective, achieving a DICE coefficient of over 0.910 and an FPS of over 102 on the CVC-300 dataset. In comparison to the state-of-the-art (SOTA) methods, ColonNet outperforms or achieves comparable performance on five publicly available datasets, establishing a new SOTA. Compared to state-of-the-art methods, ColonNet achieves the highest FPS (over 102 FPS) while maintaining excellent segmentation results, achieving the best or comparable performance on the five public datasets. The code will be released at: https://github.com/SPECTRELWF/ColonNet.

Keywords: ConvNeXt; Global Parallel Partial Decoder; Large-Kernel Receptive Field Block; Polyp segmentation.