CASIA OpenIR  > 学术期刊  > Machine Intelligence Research
Video Polyp Segmentation: A Deep Learning Perspective
Ge-Peng Ji1; Guobao Xiao2; Yu-Cheng Chou3; Deng-Ping Fan4; Kai Zhao5; Geng Chen6; Luc Van Gool4
Source PublicationMachine Intelligence Research
ISSN2731-538X
2022
Volume19Issue:6Pages:531-549
Abstract

We present the first comprehensive video polyp segmentation (VPS) study in the deep learning era. Over the years, devel- opments in VPS are not moving forward with ease due to the lack of a large-scale dataset with fine-grained segmentation annotations. To address this issue, we first introduce a high-quality frame-by-frame annotated VPS dataset, named SUN-SEG, which contains 158 690 colonoscopy video frames from the well-known SUN-database. We provide additional annotation covering diverse types, i.e., attribute, object mask, boundary, scribble, and polygon. Second, we design a simple but efficient baseline, named PNS+, which consists of a global encoder, a local encoder, and normalized self-attention (NS) blocks. The global and local encoders receive an anchor frame and multiple successive frames to extract long-term and short-term spatial-temporal representations, which are then progressively refined by two NS blocks. Extensive experiments show that PNS+ achieves the best performance and real-time inference speed (170fps), making it a prom- ising solution for the VPS task. Third, we extensively evaluate 13 representative polyp/object segmentation models on our SUN-SEG dataset and provide attribute-based comparisons. Finally, we discuss several open issues and suggest possible research directions for the VPS community. Our project and dataset are publicly available at https://github.com/GewelsJI/VPS.

KeywordVideo polyp segmentation (VPS) dataset self-attention colonoscopy abdomen
DOI10.1007/s11633-022-1371-y
Sub direction classification其他
planning direction of the national heavy laboratory其他
Paper associated data
Chinese guidehttps://mp.weixin.qq.com/s/wp0MdDxJpZzXyrLzbLhP1w
Video parsinghttps://www.bilibili.com/video/BV1Lj411D719/
Citation statistics
Cited Times:32[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/55960
Collection学术期刊_Machine Intelligence Research
Affiliation1.Research School of Engineering, Australian National University, Canberra 2601, Australia
2.College of Computer and Control Engineering, Minjiang University, Fuzhou 350108, China
3.Department of Computer Science, Johns Hopkins University, Baltimore 21218, USA
4.Computer Vision Laboratory, ETH Zòrich, Zòrich 8092, Switzerland
5.Department of Radiological Sciences, University of California, Los Angeles 90095, USA
6.School of Computer Science and Engineering, Northwestern Polytechnical University, Xi/an 710072, China
Recommended Citation
GB/T 7714
Ge-Peng Ji,Guobao Xiao,Yu-Cheng Chou,et al. Video Polyp Segmentation: A Deep Learning Perspective[J]. Machine Intelligence Research,2022,19(6):531-549.
APA Ge-Peng Ji.,Guobao Xiao.,Yu-Cheng Chou.,Deng-Ping Fan.,Kai Zhao.,...&Luc Van Gool.(2022).Video Polyp Segmentation: A Deep Learning Perspective.Machine Intelligence Research,19(6),531-549.
MLA Ge-Peng Ji,et al."Video Polyp Segmentation: A Deep Learning Perspective".Machine Intelligence Research 19.6(2022):531-549.
Files in This Item: Download All
File Name/Size DocType Version Access License
MIR-2022-07-215.pdf(9520KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Ge-Peng Ji]'s Articles
[Guobao Xiao]'s Articles
[Yu-Cheng Chou]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ge-Peng Ji]'s Articles
[Guobao Xiao]'s Articles
[Yu-Cheng Chou]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ge-Peng Ji]'s Articles
[Guobao Xiao]'s Articles
[Yu-Cheng Chou]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: MIR-2022-07-215.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.