Unsupervised Learning-Based Nonrigid Registration of High Resolution Histology Images

Abstract

The use of different dyes during histological sample preparation reveals distinct tissue properties and may improve the diagnosis. Nonetheless, the staining process deforms the tissue slides and registration is necessary before further processing. The importance of this problem led to organizing an open challenge named Automatic Non-rigid Histological Image Registration Challenge (ANHIR), organized jointly with the IEEE ISBI 2019 conference. The challenge organizers provided 481 image pairs and a server-side evaluation platform making it possible to reliably compare the proposed algorithms. The majority of the methods proposed for the challenge were based on the classical, iterative image registration, resulting in high computational load and arguable usefulness in clinical practice due to the long analysis time. In this work, we propose a deep learning-based unsupervised nonrigid registration method, that provides results comparable to the solutions of the best scoring teams, while being significantly faster during the inference. We propose a multilevel, patch-based training and inference scheme that makes it possible to register images of almost any size, up to the highest resolution provided by the challenge organizers. The median target registration error is close to 0.2% of the image diagonal while the average registration time, including the data loading and initial alignment, is below 3 seconds. We freely release both the training and inference code making the results fully reproducible.

Deep Feature based Cross-slide Registration

“…However, the focus has been on monomodal and multi-modal registration of X-ray, CT and MRI images and very few methods have been proposed for histology images. Wodzinski and Muller [19] proposed a deep learning based non-rigid registration method, performing comparably to the winning team of the ANHIR challenge contest and is significantly faster than other iterative methods. Their proposed approach employs UNET like architecture, trained in a multi-level unsupervised manner using negative normalised cross-correlation (NCC) as an objective function.…”

DeepHistReg: Unsupervised Deep Learning Registration Framework for Differently Stained Histology Samples

“…The method is built on our previous contributions [32,33], however, the methods are greatly extended and improved. An additional learning-based background segmentation was introduced, significantly improving the initial alignment.…”

“…Therefore, we propose a pyramid-based, patch-based, group-based, and iterative deep registration solution [32]. The pyramid-based approach means that the images are registered at different resolutions, starting at the coarsest level.…”