ANHIR: Automatic Non-Rigid Histological Image Registration Challenge

Jiri Borovec, Jan Kybic, Ignacio Arganda-Carreras, Dmitry V. Sorokin, Gloria Bueno, Alexander V. Khvostikov, Spyridon Bakas, Eric I.Chao Chang, Stefan Heldmann, Kimmo Kartasalo, Leena Latonen, Johannes Lotz, Michelle Noga, Sarthak Pati, Kumaradevan Punithakumar, Pekka Ruusuvuori, Andrzej Skalski, Nazanin Tahmasebi, Masi Valkonen, Ludovic VenetYizhe Wang, Nick Weiss, Marek Wodzinski, Yu Xiang, Yan Xu, Yan Yan, Paul Yushkevich, Shengyu Zhao, Arrate Munoz-Barrutia

5 Citations (Scopus)


Automatic Non-rigid Histological Image Registration (ANHIR) challenge was organized to compare the performance of image registration algorithms on several kinds of microscopy histology images in a fair and independent manner. We have assembled 8 datasets, containing 355 images with 18 different stains, resulting in 481 image pairs to be registered. Registration accuracy was evaluated using manually placed landmarks. In total, 256 teams registered for the challenge, 10 submitted the results, and 6 participated in the workshop. Here, we present the results of 7 well-performing methods from the challenge together with 6 well-known existing methods. The best methods used coarse but robust initial alignment, followed by non-rigid registration, used multiresolution, and were carefully tuned for the data at hand. They outperformed off-the-shelf methods, mostly by being more robust. The best methods could successfully register over 98% of all landmarks and their mean landmark registration accuracy (TRE) was 0.44% of the image diagonal. The challenge remains open to submissions and all images are available for download.

Original languageEnglish
JournalIEEE Transactions on Medical Imaging
Issue number10
Pages (from-to)3042-3052
Number of pages11
Publication statusPublished - 01.10.2020


Dive into the research topics of 'ANHIR: Automatic Non-Rigid Histological Image Registration Challenge'. Together they form a unique fingerprint.

Cite this