Regional registration of whole slide image stacks containing major histological artifacts
- PDF / 2,857,388 Bytes
- 20 Pages / 595.276 x 790.866 pts Page_size
- 45 Downloads / 126 Views
METHODOLOGY ARTICLE
Open Access
Regional registration of whole slide image stacks containing major histological artifacts Mahsa Paknezhad1*† , Sheng Yang Michael Loh1, Yukti Choudhury3,4, Valerie Koh Cui Koh5, Timothy Tay Kwang Yong7, Hui Shan Tan8, Ravindran Kanesvaran7, Puay Hoon Tan5, John Yuen Shyi Peng5, Weimiao Yu6, Yongcheng Benjamin Tan7, Yong Zhen Loy5, Min‑Han Tan3,4,7 and Hwee Kuan Lee1,2,8,9 *Correspondence: [email protected]‑star.edu.sg † Mahsa Paknezhad and Sheng Yang Michael Loh have equal contributor 1 Imaging Informatics Division, Bioinformatics Institute (BII), Agency for Science, Technology and Research (A*STAR), 30 Biopolis Street, 07‑01, Matrix, 138671 Singapore, Singapore Full list of author information is available at the end of the article
Abstract Background: 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 reconstruc‑ tion of the tissue volume from the 2D image stack. This task is not trivial due to the distortions such as tissue tearing, folding and missing at each slide. Performing registra‑ tion for the whole tissue slices may be adversely affected by distorted tissue regions. Consequently, regional registration is found to be more effective. In this paper, we propose a new approach to an accurate and robust registration of regions of interest for whole slide images. We introduce the idea of multi-scale attention for registration. Results: Using mean similarity index as the metric, the proposed algorithm (mean ± SD 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 out‑ performs 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 reg‑ istration algorithm (patch size 256: 0.79 ± 0.16 , patch size 512: 0.77 ± 0.16 ) for medical images. Conclusion: Using multi-scale attention mechanism leads to a more robust and accu‑ rate solution to the problem of regional registration of whole slide images corrupted in some parts by major histological artifacts in the imaged tissue. Keywords: Whole slide images, Immunohistochemistry images, Rigid registration, Blood vessel 3D reconstruction, Multi-scale attention
Background This section presents the motivation for proposing a regional registration algorithm for whole slides images (WSIs). It also provides the objectives in this paper, literature review of the previously proposed registration algorithms for WSIs, and the innovation in the proposed algorithm compared to existing registration methods.
© The Author(s) 2020. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distri
Data Loading...
