Regional Registration of Whole Slide Image Stacks Containing Highly Deformed Artefacts

Abstract

Motivation High resolution 2D whole slide imaging provides rich information about the tissue structure. This information can be a lot richer if these 2D images can be stacked into a 3D tissue volume. A 3D analysis, however, requires accurate reconstruction of the tissue volume from the 2D image stack. This task is not trivial due to the distortions that each individual tissue slice experiences while cutting and mounting the tissue on the glass slide. Performing registration for the whole tissue slices may be adversely affected by the deformed tissue regions. Consequently, regional registration is found to be more effective. In this paper, we propose an accurate and robust regional registration algorithm for whole slide images which incrementally focuses registration on the area around the region of interest. Results Using mean similarity index as the metric, the proposed algorithm (mean ± std: 0.84 ± 0.11) followed by a fine registration algorithm (0.86 ± 0.08) outperformed the state-of-the-art linear whole tissue registration algorithm (0.74±0.19) and the regional version of this algorithm (0.81±0.15). The proposed algorithm also outperforms the state-of-the-art nonlinear registration algorithm (original: 0.82 ± 0.12, regional: 0.77 ± 0.22) for whole slide images and a recently proposed patch-based registration algorithm (patch size 256: 0.79 ± 0.16 , patch size 512: 0.77 ± 0.16) for medical images. Availability The C++ implementation code is available online at the github repository: https://github.com/MahsaPaknezhad/WSIRegistration

PathFlow-MixMatch for Whole Slide Image Registration: An Investigation of a Segment-Based Scalable Image Registration Method

“…In this study, we did not seek to compare solely the differential accuracies of the underlying registration algorithms, but also to highlight the advantages of dividing WSI into discrete tissue segments prior to registration with an eye toward computational efficiency. The finetuning alignment technique employed by MixMatch utilized the Airlab registration library; however, it may be fruitful to investigate other tools such as HistoReg, 18 Recursive Cascaded Networks, 34 and other approaches 35,36 as means to better align individual segment pairs as it applies to their specific domain. Additionally, there are many registration loss functions that can be utilized to improve registration quality, such as cross-correlational, structural similarity, and mutual information losses, which may warrant further study.…”