FIB-SEM Datasets of Anaeramoeba flamelloides Symbiosome with Deep Learning Segmentation

FIB-SEM datasets of the Anaeramoeba flamelloides BUSSELTON2 symbiosome contain two 3D cellular volumes acquired via focused ion beam scanning electron microscopy. The volumes, with resolutions of 8.43 nm x 8.43 nm x 8.0 nm (1,725 slices) and 6.744 nm x 6.744 nm x 7.0 nm (1,300 slices), were segmented using a combination of manual annotation and deep learning. The dataset was created by Jon Jerlström-Hultqvist and is available on figshare under a CC-BY-4.0 license.

Use Cases

• Train and validate 3D semantic segmentation models based on manually annotated structures like symbionts, hydrogenosomes, and the endoplasmic reticulum.
• Benchmark interactive segmentation tools using the Segment Anything Model 2 (SAM 2) approach described for the nucleus.
• Study the ultrastructure and spatial relationships of organelles within a symbiotic microbial eukaryote.
• Develop image registration and processing pipelines for FIB-SEM volumes based on the described Linear alignment by SIFT and Multistackreg methods.

Strengths

• Provides two high-resolution 3D FIB-SEM volumes with precise voxel dimensions (e.g., 8.43 nm x 8.43 nm x 8.0 nm).
• Includes segmentation masks for multiple cellular structures (e.g., symbiosome, nucleus, hydrogenosomes) created via a detailed deep learning and manual refinement pipeline.
• Dataset is openly available under a permissive CC-BY-4.0 license.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The description is highly technical and focused on sample preparation; data accessibility for non-specialists may be limited.

Provenance

Source

Jon Jerlström-Hultqvist via figshare.

Collection Method

Cells were high-pressure frozen, freeze-substituted, embedded, and imaged using a Scios dualbeam FIB-SEM. Volumes were registered and processed in ImageJ, then segmented manually and with deep learning in Microscopy Image Browser.

Freshness

Last updated 2026-04-14 04:01:17; freshness should be verified.