1
|
Yang K, Musio F, Ma Y, Juchler N, Paetzold JC, Al-Maskari R, Höher L, Li HB, Hamamci IE, Sekuboyina A, Shit S, Huang H, Prabhakar C, de la Rosa E, Waldmannstetter D, Kofler F, Navarro F, Menten M, Ezhov I, Rueckert D, Vos I, Ruigrok Y, Velthuis B, Kuijf H, Hämmerli J, Wurster C, Bijlenga P, Westphal L, Bisschop J, Colombo E, Baazaoui H, Makmur A, Hallinan J, Wiestler B, Kirschke JS, Wiest R, Montagnon E, Letourneau-Guillon L, Galdran A, Galati F, Falcetta D, Zuluaga MA, Lin C, Zhao H, Zhang Z, Ra S, Hwang J, Park H, Chen J, Wodzinski M, Müller H, Shi P, Liu W, Ma T, Yalçin C, Hamadache RE, Salvi J, Llado X, Lal-Trehan Estrada UM, Abramova V, Giancardo L, Oliver A, Liu J, Huang H, Cui Y, Lin Z, Liu Y, Zhu S, Patel TR, Tutino VM, Orouskhani M, Wang H, Mossa-Basha M, Zhu C, Rokuss MR, Kirchhoff Y, Disch N, Holzschuh J, Isensee F, Maier-Hein K, Sato Y, Hirsch S, Wegener S, Menze B. Benchmarking the CoW with the TopCoW Challenge: Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA. ArXiv 2024:arXiv:2312.17670v3. [PMID: 38235066 PMCID: PMC10793481] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Download PDF] [Subscribe] [Scholar Register] [Indexed: 01/19/2024]
Abstract
The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited public datasets with annotations on CoW anatomy, especially for CTA. Therefore we organized the TopCoW Challenge in 2023 with the release of an annotated CoW dataset. The TopCoW dataset was the first public dataset with voxel-level annotations for thirteen possible CoW vessel components, enabled by virtual-reality (VR) technology. It was also the first large dataset with paired MRA and CTA from the same patients. TopCoW challenge formalized the CoW characterization problem as a multiclass anatomical segmentation task with an emphasis on topological metrics. We invited submissions worldwide for the CoW segmentation task, which attracted over 140 registered participants from four continents. The top performing teams managed to segment many CoW components to Dice scores around 90%, but with lower scores for communicating arteries and rare variants. There were also topological mistakes for predictions with high Dice scores. Additional topological analysis revealed further areas for improvement in detecting certain CoW components and matching CoW variant topology accurately. TopCoW represented a first attempt at benchmarking the CoW anatomical segmentation task for MRA and CTA, both morphologically and topologically.
Collapse
Affiliation(s)
- Kaiyuan Yang
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
| | - Fabio Musio
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
- Center for Computational Health, Zurich University of Applied Sciences, Zurich, Switzerland
| | - Yihui Ma
- Department of Neuroradiology, University Hospital of Zurich, Zurich, Switzerland
- Department of Neurosurgery, Zhongnan Hospital of Wuhan University, Wuhan, China
| | - Norman Juchler
- Center for Computational Health, Zurich University of Applied Sciences, Zurich, Switzerland
| | - Johannes C. Paetzold
- Department of Computing, Imperial College London, London, UK
- Institute for Tissue Engineering and Regenerative Medicine (iTERM), Helmholtz Center, Munich, Germany
| | - Rami Al-Maskari
- Institute for Tissue Engineering and Regenerative Medicine (iTERM), Helmholtz Center, Munich, Germany
| | - Luciano Höher
- Institute for Tissue Engineering and Regenerative Medicine (iTERM), Helmholtz Center, Munich, Germany
| | - Hongwei Bran Li
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
- Athinoula A. Martinos Center for Biomedical Imaging, Harvard Medical School, Boston, USA
| | | | - Anjany Sekuboyina
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
| | - Suprosanna Shit
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
- School of Medicine, Technical University of Munich, Munich, Germany
| | - Houjing Huang
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
| | - Chinmay Prabhakar
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
| | - Ezequiel de la Rosa
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
| | - Diana Waldmannstetter
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
- Department of Informatics, Technical University of Munich, Munich, Germany
| | - Florian Kofler
- School of Medicine, Technical University of Munich, Munich, Germany
- Department of Informatics, Technical University of Munich, Munich, Germany
- Helmholtz AI, Helmholtz Munich, Munich, Germany
| | - Fernando Navarro
- School of Medicine, Technical University of Munich, Munich, Germany
- Department of Informatics, Technical University of Munich, Munich, Germany
| | - Martin Menten
- Department of Computing, Imperial College London, London, UK
- Department of Informatics, Technical University of Munich, Munich, Germany
| | - Ivan Ezhov
- Department of Informatics, Technical University of Munich, Munich, Germany
| | - Daniel Rueckert
- Department of Computing, Imperial College London, London, UK
- Department of Informatics, Technical University of Munich, Munich, Germany
| | - Iris Vos
- Image Sciences Institute, UMC Utrecht, Utrecht, the Netherlands
| | - Ynte Ruigrok
- Department of Neurology, UMC Utrecht, Utrecht, the Netherlands
| | | | - Hugo Kuijf
- Image Sciences Institute, UMC Utrecht, Utrecht, the Netherlands
| | - Julien Hämmerli
- Department of Clinical Neurosciences, Division of Neurosurgery, Geneva University Hospitals, Geneva, Switzerland
| | - Catherine Wurster
- Department of Clinical Neurosciences, Division of Neurosurgery, Geneva University Hospitals, Geneva, Switzerland
| | - Philippe Bijlenga
- Department of Clinical Neurosciences, Division of Neurosurgery, Geneva University Hospitals, Geneva, Switzerland
| | - Laura Westphal
- Department of Neurology, University Hospital of Zurich, Zurich, Switzerland
| | - Jeroen Bisschop
- Department of Physiology, University of Toronto, Toronto, Canada
| | - Elisa Colombo
- Department of Neurosurgery, University Hospital of Zurich, Zurich, Switzerland
| | - Hakim Baazaoui
- Department of Neurology, University Hospital of Zurich, Zurich, Switzerland
| | - Andrew Makmur
- Department of Diagnostic Imaging, National University Hospital, Singapore
| | - James Hallinan
- Department of Diagnostic Imaging, National University Hospital, Singapore
| | - Bene Wiestler
- School of Medicine, Technical University of Munich, Munich, Germany
| | - Jan S. Kirschke
- School of Medicine, Technical University of Munich, Munich, Germany
| | - Roland Wiest
- Department of Diagnostic and Interventional Neuroradiology, University Hospital Berne and University of Berne, Berne, Switzerland
| | - Emmanuel Montagnon
- Centre de Recherche du Centre Hospitalier de l’Université de Montreal (CRCHUM), Montreal, Canada
| | | | | | | | | | | | - Chaolong Lin
- Institute of Medical Technology, Peking University Health Science Center, Beijing, China
| | - Haoran Zhao
- Institute of Medical Technology, Peking University Health Science Center, Beijing, China
| | - Zehan Zhang
- Hangzhou Genlight Medtech Co. Ltd., Hangzhou, China
| | - Sinyoung Ra
- Department of Artificial Intelligence, Sungkyunkwan University, Seoul, Korea
| | - Jongyun Hwang
- Department of Artificial Intelligence, Sungkyunkwan University, Seoul, Korea
| | - Hyunjin Park
- Department of Electrical and Computer Engineering, Sungkyunkwan University, Seoul, Korea
| | - Junqiang Chen
- Shanghai MediWorks Precision Instruments Co.,Ltd, Shanghai, China
| | - Marek Wodzinski
- Institute of Informatics, HES-SO Valais-Wallis, Switzerland
- Department of Measurement and Electronics, AGH University of Krakow, Poland
| | - Henning Müller
- Institute of Informatics, HES-SO Valais-Wallis, Switzerland
| | - Pengcheng Shi
- Electronic & Information Engineering School, Harbin Institute of Technology (Shenzhen), Shenzhen, China
| | - Wei Liu
- Electronic & Information Engineering School, Harbin Institute of Technology (Shenzhen), Shenzhen, China
| | - Ting Ma
- Electronic & Information Engineering School, Harbin Institute of Technology (Shenzhen), Shenzhen, China
- Peng Cheng Laboratory, Shenzhen, China
| | - Cansu Yalçin
- Research Institute of Computer Vision and Robotics (ViCOROB), Universitat de Girona, Catalonia, Spain
| | - Rachika E. Hamadache
- Research Institute of Computer Vision and Robotics (ViCOROB), Universitat de Girona, Catalonia, Spain
| | - Joaquim Salvi
- Research Institute of Computer Vision and Robotics (ViCOROB), Universitat de Girona, Catalonia, Spain
| | - Xavier Llado
- Research Institute of Computer Vision and Robotics (ViCOROB), Universitat de Girona, Catalonia, Spain
| | | | - Valeriia Abramova
- Research Institute of Computer Vision and Robotics (ViCOROB), Universitat de Girona, Catalonia, Spain
| | - Luca Giancardo
- Center for Precision Health, McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, USA
| | - Arnau Oliver
- Research Institute of Computer Vision and Robotics (ViCOROB), Universitat de Girona, Catalonia, Spain
| | - Jialu Liu
- Laboratory of Brain Atlas and Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Haibin Huang
- Laboratory of Brain Atlas and Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Yue Cui
- Laboratory of Brain Atlas and Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Zehang Lin
- School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China
| | - Yusheng Liu
- Department of Automation, Shanghai Jiao Tong University, Shanghai, China
| | - Shunzhi Zhu
- School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China
| | - Tatsat R. Patel
- Canon Stroke and Vascular Research Center, Buffalo, USA
- Department of Pathology and Anatomical Sciences, University at Buffalo, Buffalo, USA
- Department of Neurosurgery, University at Buffalo, Buffalo, USA
| | - Vincent M. Tutino
- Canon Stroke and Vascular Research Center, Buffalo, USA
- Department of Pathology and Anatomical Sciences, University at Buffalo, Buffalo, USA
- Department of Neurosurgery, University at Buffalo, Buffalo, USA
- Department of Biomedical Engineering, University at Buffalo, Buffalo, USA
| | | | - Huayu Wang
- Department of Radiology, University of Washington, Seattle, USA
| | | | - Chengcheng Zhu
- Department of Radiology, University of Washington, Seattle, USA
| | - Maximilian R. Rokuss
- German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Germany
- Faculty of Mathematics and Computer Science, Heidelberg University, Germany
| | - Yannick Kirchhoff
- German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Germany
- Faculty of Mathematics and Computer Science, Heidelberg University, Germany
- HIDSS4Health - Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany
| | - Nico Disch
- German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Germany
- Faculty of Mathematics and Computer Science, Heidelberg University, Germany
- HIDSS4Health - Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany
| | - Julius Holzschuh
- German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Germany
| | - Fabian Isensee
- German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Germany
- Helmholtz Imaging, German Cancer Research Center, Heidelberg, Germany
| | - Klaus Maier-Hein
- German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Germany
- Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital
| | | | - Sven Hirsch
- Center for Computational Health, Zurich University of Applied Sciences, Zurich, Switzerland
| | - Susanne Wegener
- Department of Neurology, University Hospital of Zurich, Zurich, Switzerland
| | - Bjoern Menze
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
| |
Collapse
|
3
|
Molton JS, Thomas BA, Pang Y, Khor LK, Hallinan J, Naftalin CM, Totman JJ, Townsend DW, Lim TK, Chee CBE, Wang YT, Paton NI. Sub-clinical abnormalities detected by PET/MRI in household tuberculosis contacts. BMC Infect Dis 2019; 19:83. [PMID: 30678651 PMCID: PMC6346497 DOI: 10.1186/s12879-019-3705-0] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2017] [Accepted: 01/10/2019] [Indexed: 11/21/2022] Open
Abstract
Background The understanding of early events following TB exposure is limited by traditional tests that rely on detection of an immune response to infection, which is delayed, or on imaging tests with low sensitivity for early disease. We investigated for evidence of lung abnormalities in heavily exposed TB contacts using PET/MRI. Methods 30 household contacts of 20 index patients underwent clinical assessment, IGRA testing, chest x-ray and PET/MRI scan using 18-F-FDG. MRI images were examined by a radiology/nuclear medicine dual-qualified physician using a standardised report form, while PET/MRI images were examined independently by another radiology/nuclear medicine dual-qualified physician using a similar form. Standardised uptake value (SUV) was quantified for each abnormal lesion. Results IGRA was positive in 40%. PET/MRI scan was abnormal in 30%, predominantly FDG uptake in hilar or mediastinal lymph nodes and lung apices. We did not identify any relationship between PET/MRI findings and degree of exposure or IGRA status. Conclusion PET-based imaging may provide important insights into the natural history following exposure to TB that may not be available from traditional tests of TB immune response or imaging. The clinical significance of the abnormalities is uncertain and merits further investigation in longitudinal studies.
Collapse
Affiliation(s)
- James S Molton
- University Medicine Cluster, National University Health System, Singapore, Singapore.,Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | | | - Yan Pang
- University Medicine Cluster, National University Health System, Singapore, Singapore
| | - Lih Kin Khor
- Department of Diagnostic Imaging, National University Health System, Singapore, Singapore
| | - James Hallinan
- Department of Diagnostic Imaging, National University Health System, Singapore, Singapore
| | - Claire M Naftalin
- Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | - John J Totman
- A*STAR-NUS Clinical Imaging Research Centre, Singapore, Singapore
| | - David W Townsend
- A*STAR-NUS Clinical Imaging Research Centre, Singapore, Singapore
| | - Tow Keang Lim
- University Medicine Cluster, National University Health System, Singapore, Singapore.,Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | | | - Yee Tang Wang
- Tuberculosis Control Unit, Tan Tock Seng Hospital, Singapore, Singapore
| | - Nicholas I Paton
- University Medicine Cluster, National University Health System, Singapore, Singapore. .,Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
| |
Collapse
|