DigestPath: A benchmark dataset with challenge review for the pathological detection and segmentation of digestive-system

Qian Da; Xiaodi Huang; Zhongyu Li; Yanfei Zuo; Chenbin Zhang; Jingxin Liu; Wen Chen; Jiahui Li; Dou Xu; Zhiqiang Hu; Hongmei Yi; Yan Guo; Zhe Wang; Ling Chen; Li Zhang; Xianying He; Xiaofan Zhang; Ke Mei; Chuang Zhu; Weizeng Lu; Linlin Shen; Jun Shi; Jun Li; Sreehari S; Ganapathy Krishnamurthi; Jiangcheng Yang; Tiancheng Lin; Qingyu Song; Xuechen Liu; Simon Graham; Raja Muhammad Saad Bashir; Canqian Yang; Shaofei Qin; Xinmei Tian; Baocai Yin; Jie Zhao; Dimitris N. Metaxas; Hongsheng Li; Chaofu Wang; Shaoting Zhang

doi:10.1016/j.media.2022.102485

DigestPath: A benchmark dataset with challenge review for the pathological detection and segmentation of digestive-system

Qian Da
, Xiaodi Huang
, Zhongyu Li
, Yanfei Zuo
, Chenbin Zhang
, Jingxin Liu
, Wen Chen
, Jiahui Li
, Dou Xu
, Zhiqiang Hu
, Hongmei Yi
, Yan Guo
, Zhe Wang
, Ling Chen
, Li Zhang
, Xianying He
, Xiaofan Zhang
, Ke Mei
, Chuang Zhu
, Weizeng Lu

Linlin Shen, Jun Shi, Jun Li, Sreehari S, Ganapathy Krishnamurthi, Jiangcheng Yang, Tiancheng Lin, Qingyu Song, Xuechen Liu, Simon Graham, Raja Muhammad Saad Bashir, Canqian Yang, Shaofei Qin, Xinmei Tian, Baocai Yin, Jie Zhao, Dimitris N. Metaxas, Hongsheng Li, Chaofu Wang, Shaoting Zhang^*

^*Corresponding author for this work

Shanghai Jiao Tong University
SenseTime Group Limited
Xi'an Jiaotong University
Histo Pathology Diagnostic Center
Air Force Medical University
Shanghai Songjiang District Central Hospital
Zhengzhou University
National Engineering Laboratory for Internet Medical Systems and Applications
Shanghai Artificial Intelligence Laboratory
Beijing University of Posts and Telecommunications
Shenzhen University
Hefei University of Technology
Indian Institute of Technology Madras
Shanghai Institute for Advanced Communication and Data Science
Zhejiang University
University of Warwick
University of Science and Technology of China
IFLYTEK Co., Ltd.
Rutgers - The State University of New Jersey, New Brunswick
Chinese University of Hong Kong
Centre for Perceptual and Interactive Intelligence

Research output: Contribution to journal › Article › peer-review

85 Citations (Scopus)

Abstract

Examination of pathological images is the golden standard for diagnosing and screening many kinds of cancers. Multiple datasets, benchmarks, and challenges have been released in recent years, resulting in significant improvements in computer-aided diagnosis (CAD) of related diseases. However, few existing works focus on the digestive system. We released two well-annotated benchmark datasets and organized challenges for the digestive-system pathological cell detection and tissue segmentation, in conjunction with the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). This paper first introduces the two released datasets, i.e., signet ring cell detection and colonoscopy tissue segmentation, with the descriptions of data collection, annotation, and potential uses. We also report the set-up, evaluation metrics, and top-performing methods and results of two challenge tasks for cell detection and tissue segmentation. In particular, the challenge received 234 effective submissions from 32 participating teams, where top-performing teams developed advancing approaches and tools for the CAD of digestive pathology. To the best of our knowledge, these are the first released publicly available datasets with corresponding challenges for the digestive-system pathological detection and segmentation. The related datasets and results provide new opportunities for the research and application of digestive pathology.

Original language	English
Article number	102485
Journal	Medical Image Analysis
Volume	80
DOIs	https://doi.org/10.1016/j.media.2022.102485
Publication status	Published - Aug 2022
Externally published	Yes

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Benchmark dataset
Cell detection
Digestive system cancer
Grand challenge
Tissue segmentation

Access to Document

10.1016/j.media.2022.102485

Cite this

Da, Q., Huang, X., Li, Z., Zuo, Y., Zhang, C., Liu, J., Chen, W., Li, J., Xu, D., Hu, Z., Yi, H., Guo, Y., Wang, Z., Chen, L., Zhang, L., He, X., Zhang, X., Mei, K., Zhu, C., ... Zhang, S. (2022). DigestPath: A benchmark dataset with challenge review for the pathological detection and segmentation of digestive-system. Medical Image Analysis, 80, Article 102485. https://doi.org/10.1016/j.media.2022.102485

@article{5c92cc99ec2642458da4a575e5f15ffc,

title = "DigestPath: A benchmark dataset with challenge review for the pathological detection and segmentation of digestive-system",

abstract = "Examination of pathological images is the golden standard for diagnosing and screening many kinds of cancers. Multiple datasets, benchmarks, and challenges have been released in recent years, resulting in significant improvements in computer-aided diagnosis (CAD) of related diseases. However, few existing works focus on the digestive system. We released two well-annotated benchmark datasets and organized challenges for the digestive-system pathological cell detection and tissue segmentation, in conjunction with the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). This paper first introduces the two released datasets, i.e., signet ring cell detection and colonoscopy tissue segmentation, with the descriptions of data collection, annotation, and potential uses. We also report the set-up, evaluation metrics, and top-performing methods and results of two challenge tasks for cell detection and tissue segmentation. In particular, the challenge received 234 effective submissions from 32 participating teams, where top-performing teams developed advancing approaches and tools for the CAD of digestive pathology. To the best of our knowledge, these are the first released publicly available datasets with corresponding challenges for the digestive-system pathological detection and segmentation. The related datasets and results provide new opportunities for the research and application of digestive pathology.",

keywords = "Benchmark dataset, Cell detection, Digestive system cancer, Grand challenge, Tissue segmentation",

author = "Qian Da and Xiaodi Huang and Zhongyu Li and Yanfei Zuo and Chenbin Zhang and Jingxin Liu and Wen Chen and Jiahui Li and Dou Xu and Zhiqiang Hu and Hongmei Yi and Yan Guo and Zhe Wang and Ling Chen and Li Zhang and Xianying He and Xiaofan Zhang and Ke Mei and Chuang Zhu and Weizeng Lu and Linlin Shen and Jun Shi and Jun Li and Sreehari S and Ganapathy Krishnamurthi and Jiangcheng Yang and Tiancheng Lin and Qingyu Song and Xuechen Liu and Simon Graham and Bashir, \{Raja Muhammad Saad\} and Canqian Yang and Shaofei Qin and Xinmei Tian and Baocai Yin and Jie Zhao and Metaxas, \{Dimitris N.\} and Hongsheng Li and Chaofu Wang and Shaoting Zhang",

note = "Funding Information: This study was supported by the funding of the Science and Technology Commission Shanghai Municipality ( 19511121400 ), the National Key Research and Development Project of China ( 2020YFC2004800 ), the Science and Technology Project for Innovation Ecosystem Construction of Zhengzhou National Supercomputing Center (201400210400), and the Central Guidance on Local Science and Technology Development Fund of Henan Province. The authors would like to thank the Intel{\textregistered} student Ambassador Program for AI, which provided the necessary computational resources on the Intel{\textregistered} AI DevCloud for running the WSI inference pipeline. The authors are also grateful to the NVIDIA GPU Grant Program for donating Titan-V GPU used in this research. The authors would like to thank Qi Duan, and Shuang Yang from SenseTime Research for their great help in challenging organizations. The authors are thankful to Xiao Mu, Bo Xu, Bin Gu, Zhaoyu Wang, Qiang Li from Shanghai Histo Pathology Diagnostic Center, Weiwei Sun, Minmin Gu, Caijuan Li, Yanqiong Zhang from Shanghai Songjiang District Central Hospital for their work in preparation of the data set. Funding Information: This study was supported by the funding of the Science and Technology Commission Shanghai Municipality (19511121400), the National Key Research and Development Project of China (2020YFC2004800), the Science and Technology Project for Innovation Ecosystem Construction of Zhengzhou National Supercomputing Center (201400210400), and the Central Guidance on Local Science and Technology Development Fund of Henan Province. The authors would like to thank the Intel{\textregistered} student Ambassador Program for AI, which provided the necessary computational resources on the Intel{\textregistered} AI DevCloud for running the WSI inference pipeline. The authors are also grateful to the NVIDIA GPU Grant Program for donating Titan-V GPU used in this research. The authors would like to thank Qi Duan, and Shuang Yang from SenseTime Research for their great help in challenging organizations. The authors are thankful to Xiao Mu, Bo Xu, Bin Gu, Zhaoyu Wang, Qiang Li from Shanghai Histo Pathology Diagnostic Center, Weiwei Sun, Minmin Gu, Caijuan Li, Yanqiong Zhang from Shanghai Songjiang District Central Hospital for their work in preparation of the data set. Publisher Copyright: {\textcopyright} 2022 Elsevier B.V.",

year = "2022",

month = aug,

doi = "10.1016/j.media.2022.102485",

language = "English",

volume = "80",

journal = "Medical Image Analysis",

issn = "1361-8415",

}

Da, Q, Huang, X, Li, Z, Zuo, Y, Zhang, C, Liu, J, Chen, W, Li, J, Xu, D, Hu, Z, Yi, H, Guo, Y, Wang, Z, Chen, L, Zhang, L, He, X, Zhang, X, Mei, K, Zhu, C, Lu, W, Shen, L, Shi, J, Li, J, S, S, Krishnamurthi, G, Yang, J, Lin, T, Song, Q, Liu, X, Graham, S, Bashir, RMS, Yang, C, Qin, S, Tian, X, Yin, B, Zhao, J, Metaxas, DN, Li, H, Wang, C & Zhang, S 2022, 'DigestPath: A benchmark dataset with challenge review for the pathological detection and segmentation of digestive-system', Medical Image Analysis, vol. 80, 102485. https://doi.org/10.1016/j.media.2022.102485

TY - JOUR

T1 - DigestPath

T2 - A benchmark dataset with challenge review for the pathological detection and segmentation of digestive-system

AU - Da, Qian

AU - Huang, Xiaodi

AU - Li, Zhongyu

AU - Zuo, Yanfei

AU - Zhang, Chenbin

AU - Liu, Jingxin

AU - Chen, Wen

AU - Li, Jiahui

AU - Xu, Dou

AU - Hu, Zhiqiang

AU - Yi, Hongmei

AU - Guo, Yan

AU - Wang, Zhe

AU - Chen, Ling

AU - Zhang, Li

AU - He, Xianying

AU - Zhang, Xiaofan

AU - Mei, Ke

AU - Zhu, Chuang

AU - Lu, Weizeng

AU - Shen, Linlin

AU - Shi, Jun

AU - Li, Jun

AU - S, Sreehari

AU - Krishnamurthi, Ganapathy

AU - Yang, Jiangcheng

AU - Lin, Tiancheng

AU - Song, Qingyu

AU - Liu, Xuechen

AU - Graham, Simon

AU - Bashir, Raja Muhammad Saad

AU - Yang, Canqian

AU - Qin, Shaofei

AU - Tian, Xinmei

AU - Yin, Baocai

AU - Zhao, Jie

AU - Metaxas, Dimitris N.

AU - Li, Hongsheng

AU - Wang, Chaofu

AU - Zhang, Shaoting

N1 - Funding Information: This study was supported by the funding of the Science and Technology Commission Shanghai Municipality ( 19511121400 ), the National Key Research and Development Project of China ( 2020YFC2004800 ), the Science and Technology Project for Innovation Ecosystem Construction of Zhengzhou National Supercomputing Center (201400210400), and the Central Guidance on Local Science and Technology Development Fund of Henan Province. The authors would like to thank the Intel® student Ambassador Program for AI, which provided the necessary computational resources on the Intel® AI DevCloud for running the WSI inference pipeline. The authors are also grateful to the NVIDIA GPU Grant Program for donating Titan-V GPU used in this research. The authors would like to thank Qi Duan, and Shuang Yang from SenseTime Research for their great help in challenging organizations. The authors are thankful to Xiao Mu, Bo Xu, Bin Gu, Zhaoyu Wang, Qiang Li from Shanghai Histo Pathology Diagnostic Center, Weiwei Sun, Minmin Gu, Caijuan Li, Yanqiong Zhang from Shanghai Songjiang District Central Hospital for their work in preparation of the data set. Funding Information: This study was supported by the funding of the Science and Technology Commission Shanghai Municipality (19511121400), the National Key Research and Development Project of China (2020YFC2004800), the Science and Technology Project for Innovation Ecosystem Construction of Zhengzhou National Supercomputing Center (201400210400), and the Central Guidance on Local Science and Technology Development Fund of Henan Province. The authors would like to thank the Intel® student Ambassador Program for AI, which provided the necessary computational resources on the Intel® AI DevCloud for running the WSI inference pipeline. The authors are also grateful to the NVIDIA GPU Grant Program for donating Titan-V GPU used in this research. The authors would like to thank Qi Duan, and Shuang Yang from SenseTime Research for their great help in challenging organizations. The authors are thankful to Xiao Mu, Bo Xu, Bin Gu, Zhaoyu Wang, Qiang Li from Shanghai Histo Pathology Diagnostic Center, Weiwei Sun, Minmin Gu, Caijuan Li, Yanqiong Zhang from Shanghai Songjiang District Central Hospital for their work in preparation of the data set. Publisher Copyright: © 2022 Elsevier B.V.

PY - 2022/8

Y1 - 2022/8

N2 - Examination of pathological images is the golden standard for diagnosing and screening many kinds of cancers. Multiple datasets, benchmarks, and challenges have been released in recent years, resulting in significant improvements in computer-aided diagnosis (CAD) of related diseases. However, few existing works focus on the digestive system. We released two well-annotated benchmark datasets and organized challenges for the digestive-system pathological cell detection and tissue segmentation, in conjunction with the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). This paper first introduces the two released datasets, i.e., signet ring cell detection and colonoscopy tissue segmentation, with the descriptions of data collection, annotation, and potential uses. We also report the set-up, evaluation metrics, and top-performing methods and results of two challenge tasks for cell detection and tissue segmentation. In particular, the challenge received 234 effective submissions from 32 participating teams, where top-performing teams developed advancing approaches and tools for the CAD of digestive pathology. To the best of our knowledge, these are the first released publicly available datasets with corresponding challenges for the digestive-system pathological detection and segmentation. The related datasets and results provide new opportunities for the research and application of digestive pathology.

AB - Examination of pathological images is the golden standard for diagnosing and screening many kinds of cancers. Multiple datasets, benchmarks, and challenges have been released in recent years, resulting in significant improvements in computer-aided diagnosis (CAD) of related diseases. However, few existing works focus on the digestive system. We released two well-annotated benchmark datasets and organized challenges for the digestive-system pathological cell detection and tissue segmentation, in conjunction with the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). This paper first introduces the two released datasets, i.e., signet ring cell detection and colonoscopy tissue segmentation, with the descriptions of data collection, annotation, and potential uses. We also report the set-up, evaluation metrics, and top-performing methods and results of two challenge tasks for cell detection and tissue segmentation. In particular, the challenge received 234 effective submissions from 32 participating teams, where top-performing teams developed advancing approaches and tools for the CAD of digestive pathology. To the best of our knowledge, these are the first released publicly available datasets with corresponding challenges for the digestive-system pathological detection and segmentation. The related datasets and results provide new opportunities for the research and application of digestive pathology.

KW - Benchmark dataset

KW - Cell detection

KW - Digestive system cancer

KW - Grand challenge

KW - Tissue segmentation

UR - https://www.scopus.com/pages/publications/85134035713

U2 - 10.1016/j.media.2022.102485

DO - 10.1016/j.media.2022.102485

M3 - Article

C2 - 35679692

AN - SCOPUS:85134035713

SN - 1361-8415

VL - 80

JO - Medical Image Analysis

JF - Medical Image Analysis

M1 - 102485

ER -

DigestPath: A benchmark dataset with challenge review for the pathological detection and segmentation of digestive-system

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this