中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?

文献类型：期刊论文

作者Ma, Jun2; Zhang, Yao3,4; Gu, Song5; Zhu, Cheng6; Ge, Cheng7; Zhang, Yichi8; An, Xingle9; Wang, Congcong10,11; Wang, Qiyuan12; Liu, Xin13
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2022-10-01
卷号44期号:10页码:6695-6714
ISSN号0162-8828
关键词Benchmark testing Liver Image segmentation Biological systems Pancreas Computed tomography Kidney Multi-organ segmentation generalization semi-supervised learning weakly supervised learning continual learning
DOI10.1109/TPAMI.2021.3100536
英文摘要With the unprecedented developments in deep learning, automatic segmentation of main abdominal organs seems to be a solved problem as state-of-the-art (SOTA) methods have achieved comparable results with inter-rater variability on many benchmark datasets. However, most of the existing abdominal datasets only contain single-center, single-phase, single-vendor, or single-disease cases, and it is unclear whether the excellent performance can generalize on diverse datasets. This paper presents a large and diverse abdominal CT organ segmentation dataset, termed AbdomenCT-1K, with more than 1000 (1K) CT scans from 12 medical centers, including multi-phase, multi-vendor, and multi-disease cases. Furthermore, we conduct a large-scale study for liver, kidney, spleen, and pancreas segmentation and reveal the unsolved segmentation problems of the SOTA methods, such as the limited generalization ability on distinct medical centers, phases, and unseen diseases. To advance the unsolved problems, we further build four organ segmentation benchmarks for fully supervised, semi-supervised, weakly supervised, and continual learning, which are currently challenging and active research topics. Accordingly, we develop a simple and effective method for each benchmark, which can be used as out-of-the-box methods and strong baselines. We believe the AbdomenCT-1K dataset will promote future in-depth research towards clinical applicable abdominal organ segmentation methods.
资助项目China's Ministry of Science and Technology[2020YFA0713800] ; National Natural Science Foundation of China[11971229] ; National Natural Science Foundation of China[12090023]
WOS研究方向Computer Science ; Engineering
语种英语
出版者IEEE COMPUTER SOC
WOS记录号WOS:000853875300063
源URL[http://119.78.100.204/handle/2XEOYT63/19412]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Yang, Xiaoping
作者单位1.Nanjing Drum Tower Hosp, Dept Nucl Med, Nanjing 210008, Peoples R China
2.Nanjing Univ Sci & Technol, Dept Math, Nanjing 210094, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, Beijing 100864, Peoples R China
4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
5.Nanjing Univ Informat Sci & Technol, Sch Automat, Nanjing 210044, Peoples R China
6.Shenzhen Haichuang Med CO LTD, Shenzhen 518000, Peoples R China
7.Jiangsu Univ Technol, Inst Bioinformat & Med Engn, Changzhou 213001, Peoples R China
8.Beihang Univ, Sch Biol Sci & Med Engn, Beijing 100191, Peoples R China
9.Beijing Infervis Technol CO LTD, Beijing 100089, Peoples R China
10.Tianjin Univ Technol, Sch Comp Sci & Engn, Tianjin 300222, Peoples R China
推荐引用方式
GB/T 7714		 Ma, Jun,Zhang, Yao,Gu, Song,et al. AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2022,44(10):6695-6714.
APA Ma, Jun.,Zhang, Yao.,Gu, Song.,Zhu, Cheng.,Ge, Cheng.,...&Yang, Xiaoping.(2022).AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,44(10),6695-6714.
MLA Ma, Jun,et al."AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 44.10(2022):6695-6714.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。