个人中心| | 帮助
高级检索
当前位置： 首页 > 详情页

Mitosis domain generalization in histopathology images - The MIDOG challenge

| 认领 | 导出 | |

文献详情

资源类型：
Pubmed体系：
作者：
Marc Aubreville [1] ; Nikolas Stathonikos [2] ; Christof A. Bertram [3] ; Robert Klopfleisch [4] ; Natalie ter Hoeve [2] ; Francesco Ciompi [5] ; Frauke Wilm [6,28] ; Christian Marzahl [6] ; Taryn A. Donovan [7] ; Andreas Maier [6] ; Jack Breen [8] ; Nishant Ravikumar [8] ; Youjin Chung [9] ; Jinah Park [9] ; Ramin Nateghi [10] ; Fattaneh Pourakpour [11] ; Rutger H.J. Fick [12] ; Saima Ben Hadj [12] ; Mostafa Jahanifar [13] ; Adam Shephard [13] ; Jakob Dexl [14] ; Thomas Wittenberg [14] ; Satoshi Kondo [15] ; Maxime W. Lafarge [16] ; Viktor H. Koelzer [16] ; Jingtang Liang [17] ; Yubo Wang [17] ; Xi Long [18] ; Jingxin Liu [19] ; Salar Razavi [20] ; April Khademi [20] ; Sen Yang [21] ; Xiyue Wang [22] ; Ramona Erber [23] ; Andrea Klang [3] ; Karoline Lipnik [3] ; Pompei Bolfa [24] ; Michael J. Dark [25] ; Gabriel Wasinger [26] ; Mitko Veta [27] ; Katharina Breininger [28] ;
机构： [1]Technische Hochschule Ingolstadt, Ingolstadt, Germany [2]Pathology Department, UMC Utrecht, Utrecht, The Netherlands [3]Institute of Pathology, University of Veterinary Medicine, Vienna, Austria [4]Institute of Veterinary Pathology, Freie Universität Berlin, Berlin, Germany [5]Computational Pathology Group, Radboud UMC, Nijmegen, The Netherlands [6]Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany [7]Department of Anatomic Pathology, Schwarzman Animal Medical Center, NY, USA [8]CISTIB Center for Computational Imaging and Simulation Technologies in Biomedicine, School of Computing, University of Leeds, Leeds, UK [9]Korea Advanced Institute of Science and Technology, Daejeon, South Korea [10]Electrical and Electronics Engineering Department, Shiraz University of Technology, Shiraz, Iran [11]Iranian Brain Mapping Biobank (IBMB), National Brain Mapping Laboratory (NBML), Tehran, Iran [12]Tribun Health, Paris, France [13]Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, Warwick, UK [14]Fraunhofer-Institute for Integrated Circuits IIS, Erlangen, Germany [15]Muroran Institute of Technology, Hokkaido, Japan [16]Department of Pathology and Molecular Pathology, University Hospital and University of Zurich, Zurich, Switzerland [17]School of Life Science and Technology, Xidian University, Shannxi, China [18]Histo Pathology Diagnostic Center, Shanghai, China [19]Xi’an Jiaotong-Liverpool University, Suzhou, China [20]Image Analysis in Medicine Lab (IAMLAB), Electrical, Computer and Biomedical Engineering, Ryerson University, Toronto, ON, Canada [21]Tencent AI Lab, Shenzhen 518057, China [22]College of Computer Science, Sichuan University, Chengdu 610065, China [23]Institute of Pathology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany [24]Ross University School of Veterinary Medicine, Basseterre, Saint Kitts and Nevis [25]College of Veterinary Medicine, University of Florida, Gainesville, FL, USA [26]Department of Pathology, General Hospital of Vienna, Medical University of Vienna, Vienna, Austria [27]Medical Image Analysis Group, TU Eindhoven, Eindhoven, The Netherlands [28]Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
出处：
DOI： 10.1016/j.media.2022.102699
ISSN：

关键词： Domain generalization Histopathology Challenge Deep Learning Mitosis

摘要：
The density of mitotic figures (MF) within tumor tissue is known to be highly correlated with tumor proliferation and thus is an important marker in tumor grading. Recognition of MF by pathologists is subject to a strong inter-rater bias, limiting its prognostic value. State-of-the-art deep learning methods can support experts but have been observed to strongly deteriorate when applied in a different clinical environment. The variability caused by using different whole slide scanners has been identified as one decisive component in the underlying domain shift. The goal of the MICCAI MIDOG 2021 challenge was the creation of scanner-agnostic MF detection algorithms. The challenge used a training set of 200 cases, split across four scanning systems. As test set, an additional 100 cases split across four scanning systems, including two previously unseen scanners, were provided. In this paper, we evaluate and compare the approaches that were submitted to the challenge and identify methodological factors contributing to better performance. The winning algorithm yielded an F1 score of 0.748 (CI95: 0.704-0.781), exceeding the performance of six experts on the same task.Copyright © 2022 Elsevier B.V. All rights reserved.

语种：
外文
PubmedID：
中科院(CAS)分区：
出版当年[2022]版：
大类 | 1 区 工程技术
小类 | 1 区 工程：生物医学 1 区 核医学 1 区 计算机：人工智能 1 区 计算机：跨学科应用
最新[2023]版：
大类 | 1 区 医学
小类 | 1 区 计算机：人工智能 1 区 计算机：跨学科应用 1 区 工程：生物医学 1 区 核医学
第一作者：
第一作者机构： [1]Technische Hochschule Ingolstadt, Ingolstadt, Germany
通讯作者：
推荐引用方式(GB/T 7714)：
Marc Aubreville,Nikolas Stathonikos,Christof A. Bertram,et al.Mitosis domain generalization in histopathology images - The MIDOG challenge[J].Medical image analysis.2022,84:102699.doi:10.1016/j.media.2022.102699.
APA：
Marc Aubreville,Nikolas Stathonikos,Christof A. Bertram,Robert Klopfleisch,Natalie ter Hoeve...&Katharina Breininger.(2022).Mitosis domain generalization in histopathology images - The MIDOG challenge.Medical image analysis,84,
MLA：
Marc Aubreville,et al."Mitosis domain generalization in histopathology images - The MIDOG challenge".Medical image analysis 84.(2022):102699

相关文献

[1]Domain generalization across tumor types, laboratories, and species - Insights from the 2022 edition of the Mitosis Domain Generalization Challenge [2]CoNIC Challenge: Pushing the frontiers of nuclear detection, segmentation, classification and counting [3]CDDSA: Contrastive domain disentanglement and style augmentation for generalizable medical image segmentation [4]A Deep Learning-Based Radiomics Model for Prediction of Survival in Glioblastoma Multiforme [5]Predicting cutaneous malignant melanoma patients' survival using deep learning: a retrospective cohort study [6]Efficient application of deep learning-based elective lymph node regions delineation for pelvic malignancies [7]Deep learning based clinical target volumes contouring for prostate cancer: Easy and efficient application [8]A novel deep learning segmentation model for organoid-based drug screening [9]Domain composition and attention network trained with synthesized unlabeled images for generalizable medical image segmentation [10]Using deep learning to classify pediatric posttraumatic stress disorder at the individual level.

资源点击量：43377 今日访问量：0 总访问量：3120 更新日期：2024-09-01 建议使用谷歌、火狐浏览器 常见问题

版权所有©2020 四川省肿瘤医院 技术支持：重庆聚合科技有限公司 地址：成都市人民南路四段55号