Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics

doi:10.3389/fmolb.2021.614277

科研成果详情

题名	Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics
作者	Kong，Zishang 1; He，Min 2; Luo，Qianjiang 2; Huang，Xiansong 3; Wei，Pengxu 3,4; Cheng，Yalu 1; Chen，Luyang 5; Liang，Yongsheng 6; Lu，Yanchang 7; Li，Xi 2; Chen，Jie 1,3
发表日期	2021-08-19
发表期刊	Frontiers in Molecular Biosciences
卷号	8
摘要	Capsule endoscopy is a leading diagnostic tool for small bowel lesions which faces certain challenges such as time-consuming interpretation and harsh optical environment inside the small intestine. Specialists unavoidably waste lots of time on searching for a high clearness degree image for accurate diagnostics. However, current clearness degree classification methods are based on either traditional attributes or an unexplainable deep neural network. In this paper, we propose a multi-task framework, called the multi-task classification and segmentation network (MTCSN), to achieve joint learning of clearness degree (CD) and tissue semantic segmentation (TSS) for the first time. In the MTCSN, the CD helps to generate better refined TSS, while TSS provides an explicable semantic map to better classify the CD. In addition, we present a new benchmark, named the Capsule-Endoscopy Crohn’s Disease dataset, which introduces the challenges faced in the real world including motion blur, excreta occlusion, reflection, and various complex alimentary scenes that are widely acknowledged in endoscopy examination. Extensive experiments and ablation studies report the significant performance gains of the MTCSN over state-of-the-art methods.
关键词	Auxiliary diagnosis Capsule endoscopy Crohn’s disease Explicable Multi-task learning
DOI	10.3389/fmolb.2021.614277
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-85114348924
引用统计
文献类型	期刊论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/5973
专题	北师香港浸会大学
通讯作者	Chen，Jie
作者单位	1.School of Electonic and Computer Engineering,Peking University,Shenzhen,China 2.Department of Gastroenterology,Peking University Shenzhen Hospital,Shenzhen,China 3.Peng Cheng Laboratory,Shenzhen,China 4.Sun Yat-sen University,Guangzhou,China 5.Pennsylvania State University,Philadelphia,United States 6.Harbin Institute of Technology (Shenzhen),Shenzhen,China 7.Beijing Normal University-Hong Kong Baptist University United International College,Zhuhai,China
推荐引用方式 GB/T 7714	Kong，Zishang,He，Min,Luo，Qianjianget al. Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics[J]. Frontiers in Molecular Biosciences, 2021, 8.
APA	Kong，Zishang., He，Min., Luo，Qianjiang., Huang，Xiansong., Wei，Pengxu., .. & Chen，Jie. (2021). Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics. Frontiers in Molecular Biosciences, 8.
MLA	Kong，Zishang,et al."Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics". Frontiers in Molecular Biosciences 8(2021).