학술논문
The ACROBAT 2022 Challenge: Automatic Registration Of Breast Cancer Tissue
Document Type
Working Paper
Author
Weitz, Philippe; Valkonen, Masi; Solorzano, Leslie; Carr, Circe; Kartasalo, Kimmo; Boissin, Constance; Koivukoski, Sonja; Kuusela, Aino; Rasic, Dusan; Feng, Yanbo; Pouplier, Sandra Sinius; Sharma, Abhinav; Eriksson, Kajsa Ledesma; Robertson, Stephanie; Marzahl, Christian; Gatenbee, Chandler D.; Anderson, Alexander R. A.; Wodzinski, Marek; Jurgas, Artur; Marini, Niccolò; Atzori, Manfredo; Müller, Henning; Budelmann, Daniel; Weiss, Nick; Heldmann, Stefan; Lotz, Johannes; Wolterink, Jelmer M.; De Santi, Bruno; Patil, Abhijeet; Sethi, Amit; Kondo, Satoshi; Kasai, Satoshi; Hirasawa, Kousuke; Farrokh, Mahtab; Kumar, Neeraj; Greiner, Russell; Latonen, Leena; Laenkholm, Anne-Vibeke; Hartman, Johan; Ruusuvuori, Pekka; Rantalainen, Mattias
Source
Subject
Language
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 dataset to date, including 4,212 WSIs from 1,152 breast cancer patients. The challenge objective was to align WSIs of tissue that was stained with routine diagnostic immunohistochemistry to its H&E-stained counterpart. We compare the performance of eight WSI registration algorithms, including an investigation of the impact of different WSI properties and clinical covariates. We find that conceptually distinct WSI registration methods can lead to highly accurate registration performances and identify covariates that impact performances across methods. These results establish the current state-of-the-art in WSI registration and guide researchers in selecting and developing methods.