Regional registration of whole slide image stacks containing major histological artifacts

BMC Bioinformatics

Hui Shan Tan¹  Sheng Yang Michael Loh²  Mahsa Paknezhad²  Hwee Kuan Lee²  Yongcheng Benjamin Tan³  Timothy Tay Kwang Yong³  Ravindran Kanesvaran³  Yukti Choudhury⁴  Min-Han Tan⁴  Weimiao Yu⁵  Yong Zhen Loy⁶  John Yuen Shyi Peng⁶  Puay Hoon Tan⁶  Valerie Koh Cui Koh⁶ 

[1] Image and Pervasive Access Lab (IPAL), CNRS UMI 2955;Imaging Informatics Division, Bioinformatics Institute (BII), Agency for Science, Technology and Research (A*STAR);Institute of Molecular and Cell Biology;Lucence Diagnostics;National Cancer Centre Singapore;Singapore General Hospital;

关键词: Whole slide images;    Immunohistochemistry images;    Rigid registration;    Blood vessel 3D reconstruction;    Multi-scale attention;   

DOI  :  10.1186/s12859-020-03907-6

来源: DOAJ

【 摘 要 】

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 reconstruction 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 registration 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 $$0.84 \pm 0.11$$ 0.84 ± 0.11 ) followed by a fine registration algorithm ( $$0.86 \pm 0.08$$ 0.86 ± 0.08 ) outperformed the state-of-the-art linear whole tissue registration algorithm ( $$0.74 \pm 0.19$$ 0.74 ± 0.19 ) and the regional version of this algorithm ( $$0.81 \pm 0.15$$ 0.81 ± 0.15 ). The proposed algorithm also outperforms the state-of-the-art nonlinear registration algorithm (original: $$0.82 \pm 0.12$$ 0.82 ± 0.12 , regional: $$0.77 \pm 0.22$$ 0.77 ± 0.22 ) for whole slide images and a recently proposed patch-based registration algorithm (patch size 256: $$0.79 \pm 0.16$$ 0.79 ± 0.16 , patch size 512: $$0.77 \pm 0.16$$ 0.77 ± 0.16 ) for medical images. Conclusion Using multi-scale attention mechanism leads to a more robust and accurate solution to the problem of regional registration of whole slide images corrupted in some parts by major histological artifacts in the imaged tissue.

【 授权许可】

Unknown