Peer-Reviewed Publication
Med Image Anal2024;97103257.October 1, 2024Journal Article
The ACROBAT 2022 challenge: Automatic registration of breast cancer tissue.
Philippe Weitz1, Masi Valkonen2, Leslie Solorzano3, Circe Carr2, Kimmo Kartasalo3, Constance Boissin3, Sonja Koivukoski4, Aino Kuusela2, Dusan Rasic5, Yanbo Feng3, Sandra Sinius Pouplier5, Abhinav Sharma3, Kajsa Ledesma Eriksson3, Stephanie Robertson6, Christian Marzahl7, Chandler D Gatenbee8, Alexander R A Anderson8, Marek Wodzinski9, Artur Jurgas9, Niccolò Marini10, Manfredo Atzori11, Henning Müller12, Daniel Budelmann13, Nick Weiss13, Stefan Heldmann13, Johannes Lotz13, Jelmer M Wolterink14, Bruno De Santi15, Abhijeet Patil16, Amit Sethi16, Satoshi Kondo17, Satoshi Kasai18, Kousuke Hirasawa19, Mahtab Farrokh20, Neeraj Kumar20, Russell Greiner21, Leena Latonen4, Anne-Vibeke Laenkholm5, Johan Hartman22, Pekka Ruusuvuori23, Mattias Rantalainen24
1Department of Medical Epidemiology and Biostatistics, Karolinska Insitutet, Stockholm, Sweden. Electronic address: philippe.weitz@ki.se.
2Institute of Biomedicine, University of Turku, Turku, Finland.
3Department of Medical Epidemiology and Biostatistics, Karolinska Insitutet, Stockholm, Sweden.
4Institute of Biomedicine, University of Eastern Finland, Kuopio, Finland.
5Department of Surgical Pathology, Zealand University Hospital, Roskilde, Denmark.
6Department of Oncology and Pathology, Karolinska Institutet, Stockholm, Sweden.
7Gestalt Diagnostics, Spokane, USA.
8Department of Integrated Mathematical Oncology, Moffitt Cancer Center, Tampa, USA.
9Informatics Institute, University of Applied Sciences Western Switzerland, Switzerland; Department of Measurement and Electronics, AGH University of Kraków, Poland.
10Informatics Institute, University of Applied Sciences Western Switzerland, Switzerland; Department of Computer Science, University of Geneva, Geneva, Switzerland.
11Informatics Institute, University of Applied Sciences Western Switzerland, Switzerland; Department of Neuroscience, University of Padova, Italy.
12Informatics Institute, University of Applied Sciences Western Switzerland, Switzerland; Medical Faculty, University of Geneva, Switzerland.
13Fraunhofer Institute for Digital Medicine MEVIS, Lübeck, Germany.
14Department of Applied Mathematics, Technical Medical Centre, University of Twente, Enschede, The Netherlands.
15Multimodality Medical Imaging, Technical Medical Centre, University of Twente, Enschede, The Netherlands.
16Department of Electrical Engineering, Indian Institute of Technology, Bombay, India.
17Graduate School of Engineering, Muroran Institute of Technology, Hokkaido, Japan.
18Faculty of Medical Technology, Niigata University of Health and Welfare, Niigata, Japan.
19FORXAI Business Operations, Konica Minolta, Inc., Osaka, Japan.
20Department of Computing Science, University of Alberta, Edmonton, Alberta.
21Department of Computing Science, University of Alberta, Edmonton, Alberta; Alberta Machine Intelligence Institute, Edmonton, Canada.
22Department of Oncology and Pathology, Karolinska Institutet, Stockholm, Sweden; MedTechLabs, BioClinicum, Karolinska University Hospital, Stockholm, Sweden.
23Institute of Biomedicine, University of Turku, Turku, Finland; Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland.
24Department of Medical Epidemiology and Biostatistics, Karolinska Insitutet, Stockholm, Sweden; MedTechLabs, BioClinicum, Karolinska University Hospital, Stockholm, Sweden. Electronic address: mattias.rantalainen@ki.se.
Abstract
The alignment of tissue between histopathological whole-slide-images (WSI) is crucial for research and clinical applications. Advances in computing, deep learning, and availability of large WSI datasets have revolutionised WSI analysis. Therefore, the current state-of-the-art in WSI registration is unclear. To address this, we conducted the ACROBAT challenge, based on the largest WSI registration…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans