Okapi-EM: A napari plugin for processing and analyzing cryogenic serial focused ion beam/scanning electron microscopy images

Abstract

An emergent volume electron microscopy technique called cryogenic serial plasma focused ion beam milling scanning electron microscopy (pFIB/SEM) can decipher complex biological structures by building a three-dimensional picture of biological samples at mesoscale resolution. This is achieved by collecting consecutive SEM images after successive rounds of FIB milling that expose a new surface after each milling step. Due to instrumental limitations, some image processing is necessary before 3D visualization and analysis of the data is possible. SEM images are affected by noise, drift, and charging effects, that can make precise 3D reconstruction of biological features difficult. This article presents Okapi-EM, an open-source napari plugin developed to process and analyze cryogenic serial pFIB/SEM images. Okapi-EM enables automated image registration of slices, evaluation of image quality metrics specific to pFIB-SEM imaging, and mitigation of charging artifacts. Implementation of Okapi-EM within the napari framework ensures that the tools are both user- and developer-friendly, through provision of a graphical user interface and access to Python programming.

Keywords: 3D imaging; Cryogenic; image processing; napari; serial FIB/SEM; software.

Figure 1.

View of the napari application highlighting the Okapi-EM plugin (green rectangle at right), and the currently available tools (pink rectangle at right). Each Okapi-EM plugin has its own tab with appropriate options for its use displayed. See Supplementary Figure S1 for a detailed view and description of the options available in each plugin.

Figure 2.

Nonphysical distortion in the alignment process if the modes of transformation are not appropriately limited. (a) Original SEM image of yeast cells. (b) Artificially distorted image after a shearing transformation was applied to the original image. A shear factor of 0.15 was selected for visibility. (c) Feature points found in (b) using SIFT, with two feature-dense regions highlighted with circle and triangle markers. (d) Possible alignment result when the modes of transformation are not restrained, where even though the feature-rich regions are well-aligned, a nonphysical rotation is introduced. Data is FIB-SEM of yeast, available at EMPIAR with ID 11416.

Figure 3.

Alignment results and comparison between Okapi-EM, TrakEM2, and Fiji Linear Stack Alignment with SIFT (a) Cross-sectional views of SEM image stack of yeast cells (109 slices along z direction, slice size 20.7 × 13.8 μm²) are obtained. (b–i) Cross-sectional view of a 11.2 × 3.7 μm² area at y = 2 μm of the unaligned stack and the aligned stacks using Okapi-EM alignment with RANSAC and {translate, shear x, stretch y} selected, Fiji plugin TrakEM2 with rigid transformation, similarity transformation, or affine transformation selected, respectively, and Fiji plugin Linear Stack Alignment with rigid transformation, similarity transformation, or affine transformation selected respectively. (j–q), Cross-sectional view of a 15.0 × 3.7 μm² area at y = 11 μm of the aligned stacks using the three aforementioned alignment methods and settings respectively. Data is EMPIAR-11416. In both Fiji plugins, rigid transformation allows translation and rotation. Similarity transformation allows translation, rotation, and scaling. Affine transformation is defined as shown in Supplementary Figure S2. Details about the rendering of the cross-section images is detailed in Supplementary Figure S8.

Figure 4.

(a–f) SEM images and plots illustrating the charge artifact removal algorithm on a lipid droplet from a yeast dataset. Data is EMPIAR-11416. (a) SEM image of a lipid droplet within a yeast cell (image size 6.75 × 1.35 μm²). Arrows indicate a scanning line of interest, with its signal profile in (c–e) as blue line. Red rectangle represents data region where signal was averaged (width set by the nlinesavaerage parameter) resulting in signal profile in (c) as orange line. (b) Annotation image of the charge center, corresponding to the charging artifact in Figure (a). Green line in plot (c) is the line profile of the annotation along the row of interest (arbitrary units). (d) Line profiles describing the background corrected signal (blue line) and the optimized functions and , (red and purple) respectively. (e) Line profiles of the uncorrected signal (blue line) and corrected signal (brown line). (g–i) SEM images illustrating charge artifact suppression on myelinated sheaths found in mouse brain (image size 20.7 × 10.3 μm²). Data is EMPIAR-11415. (g) Original SEM image displaying copious amounts of charging. (h) SEM image with overlaid segmentation of charging centers and extending to complete rings of myelin sheaths. (i) Result after applying filter with default parameters.

Figure 5.

Calibration dataset of polystyrene beads used to calculate the gold-standard two-image FRC. These images were taken at 90° SEM angle. A region-of-interest (blue box) covering 2 × 2 μm² was used for the calibration, where the average one-image FRC and two-image FRC were calculated for these regions at all pixel sizes. Scale bars represent 2 μm.

Figure 6.

Calibration of the one-image FRC measurement to the gold-standard two-image FRC. (a) Two-image FRC curve and one-image FRC curves before and after calibration for the image pair at 4.5 nm pixel size at 52° SEM angle. (b) versus scatter plot (blue dots) and calibration curve , where is the average resolution measured from the one-image FRC for the image pair (Figure a, normalized frequency value at the location the curve crosses the correlation cutoff line of 1/7), and is the resolution from the gold-standard two-image FRC measured from the image pair. Calibration shifted the uncalibrated one-image FRC curves along the frequency axis to match the two-image FRC curves, ensuring that the resolution measurement for the one-image FRC matches the gold standard.

Figure 7.

Validation of Quoll resolution measurements compared to physical features of known sizes in HeLa cells. Images were taken with 6.745 nm pixel size at 52° SEM angle. Nuclear pore complexes (a,b) of 120 nm diameter were clearly resolved in the images, as indicated by the arrows in (b), and the resolution in this region was estimated as better than the resolvable features. Similarly, in (c) and (d), centrosomes of 200 nm diameter could be resolved from the images (indicated by the arrow in d), and resolution was better than the size of the centrosomes. (a,c) A resolution heatmap is overlaid onto regions of the image showing nuclear pore complexes and centrosomes respectively, where the colors represent the resolution values of that local region and numbers are the local resolution values in nm calculated on the respective rectangular regions. (b,d) are the zoomed-in regions indicated in (a) and (c) with a red square, with arrows indicating the position of the nuclear pore complexes and centrosomes, respectively. Data is EMPIAR-11419.