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.
@article{arxiv.2305.18033,
title = {The ACROBAT 2022 Challenge: Automatic Registration Of Breast Cancer Tissue},
author = {Philippe Weitz and Masi Valkonen and Leslie Solorzano and Circe Carr and Kimmo Kartasalo and Constance Boissin and Sonja Koivukoski and Aino Kuusela and Dusan Rasic and Yanbo Feng and Sandra Sinius Pouplier and Abhinav Sharma and Kajsa Ledesma Eriksson and Stephanie Robertson and Christian Marzahl and Chandler D. Gatenbee and Alexander R. A. Anderson and Marek Wodzinski and Artur Jurgas and Niccolò Marini and Manfredo Atzori and Henning Müller and Daniel Budelmann and Nick Weiss and Stefan Heldmann and Johannes Lotz and Jelmer M. Wolterink and Bruno De Santi and Abhijeet Patil and Amit Sethi and Satoshi Kondo and Satoshi Kasai and Kousuke Hirasawa and Mahtab Farrokh and Neeraj Kumar and Russell Greiner and Leena Latonen and Anne-Vibeke Laenkholm and Johan Hartman and Pekka Ruusuvuori and Mattias Rantalainen},
journal= {arXiv preprint arXiv:2305.18033},
year = {2023}
}