Defining Keypoints to Align H&E Images and Xenium DAPI-Stained Images Automatically

Abstract

10X Xenium is an in situ spatial transcriptomics platform that enables single-cell and subcellular-level gene expression analysis. In Xenium data analysis, defining matched keypoints to align H&E and spatial transcriptomic images is critical for cross-referencing sequencing and histology. Currently, it is labor-intensive for domain experts to manually place keypoints to perform image registration in the Xenium Explorer software. We present Xenium-Align, a keypoint identification method that automatically generates keypoint files for image registration in Xenium Explorer. We validated our proposed method on 14 human kidney samples and one human skin Xenium sample representing healthy and diseased states, with expert manually marked results. These results show that Xenium-Align could generate accurate keypoints for automatically implementing image alignment in the Xenium Explorer software for spatial transcriptomics studies. Our future research aims to optimize the method's runtime efficiency and usability for image alignment applications.

Keywords: H&E image; Xenium technology; graph matching; image alignment; nucleus segmentation; spatial transcriptomics.

Figure 1

The workflow of our proposed keypoint identification method, named Xenium-Align, automatically generates the keypoint file for the Xenium Explorer software. The image alignment details of the five experimental parts are as follows: (A) shows the image processing on the imported H&E image and the extracted DAPI-stained image. Nucleus patches are cropped with the same radius size from the segmented H&E image (by Cellpose or StarDist models) and the extracted DAPI-stained image to locate nucleus positions. (B) Details of the multi-directional enhanced image assessment involving five aspects (center, up, down, left, and right moving directions). The image quality evaluation index of PSNR is used to measure the similarity between the H&E patch and the DAPI-stained patch. (C) Shows the Delaunay triangulation graph matching process used to filter out the outliers due to the mistaken placement of the initially matched keypoints. (D) Shows nucleus polygon matching by evaluating the overlap degree between the cell nuclei from the DAPI-stained and H&E images to further remove mismatched keypoints. (E) Illustrates the output of placement points with spatial coordinates kept in a CSV format file, which can be used as the input for image alignment in Xenium Explorer software. This figure was prepared using Adobe Illustrator CC Software (version 2017; Adobe Inc., San Jose, CA, USA).

Figure 2

Visualization results of image alignment in good and poor cases using our proposed keypoint identification method on the same tissue region on sample F59. (A) Shows an example of good image alignment; (B) shows an example of poor image alignment.

Figure 3

Visualization results of the keypoint placements across the whole tissue between the H&E image and the DAPI-stained image using our proposed identification method in Xenium Explorer, from sample F59. (A) Shows the keyponit placement of the DAPI-stained image; (B) shows the keypoint placement of the H&E image.

Figure 4

Visualization results of the accurate keypoint placements of a certain pair of keypoints between the H&E image and the DAPI-stained image using our proposed identification method in Xenium Explorer, from sample F59. (A) Shows the keypoint placement of the DAPI-stained image; (B) shows the keypoint placement of the H&E image. The number “2” in the figure indicates the corresponding spots in Figure 3.

Figure 5

Comparison results between the H&E image and its nucleus segmentation image for sample F59; (A) shows the original H&E image; (B) shows the nucleus segmentation image.

Figure 6

Comparison results of cropped patches from the (1) H&E image, (2) H&E segmentation, and (3) DAPI-stained image in five moving directions, that is, (A) center, (B) up, (C) down, (D) left, and (E) right for a selected pair of cell nuclei on sample F59. The radius size of the cropped patch is 400 pixels, and the moving distance from the center points is 300 pixels. The central cell in the Xenium data from the DAPI-stained image is identified by barcode gggbgpij-1; (scale bar, 10 μm).