Advancing X-ray microcomputed tomography image processing of avian eggshells: An improved registration metric for multiscale 3D images and resolution-enhanced segmentation of eggshell pores using edge-attentive neural networks.
Authors
Affiliations (4)
Affiliations (4)
- Department of Bioengineering, McGill University, Montreal, H3A 0E9, QC, Canada.
- Dragonfly, Comet Group, Montreal, H3B 1A7, QC, Canada.
- Faculty of Dental Medicine and Oral Health Sciences, McGill University, Montreal, H3A 1G1, QC, Canada; Department of Anatomy and Cell Biology, McGill University, Montreal, H3A 0C7, QC, Canada.
- Department of Bioengineering, McGill University, Montreal, H3A 0E9, QC, Canada; Faculty of Dental Medicine and Oral Health Sciences, McGill University, Montreal, H3A 1G1, QC, Canada; Department of Anatomy and Cell Biology, McGill University, Montreal, H3A 0C7, QC, Canada. Electronic address: [email protected].
Abstract
Avian eggs exhibit a variety of shapes and sizes, reflecting different reproductive strategies. The eggshell not only protects the egg contents, but also regulates gas and water vapor exchange vital for embryonic development. While many studies have explored eggshell ultrastructure, the distribution of pores across the entire shell is less well understood because of a trade-off between resolution and field-of-view in imaging. To overcome this, a neural network was developed for resolution enhancement of low-resolution 3D tomographic data, while performing voxel-wise labeling. Trained on X-ray microcomputed tomography images of ostrich, guillemot and crow eggshells from a natural history museum collection, the model used stepwise magnification to create low- and high-resolution training sets. Registration performance was validated with a novel metric based on local grayscale gradients. An edge-attentive loss function prevented bias towards the dominant background class (95% of all voxels), ensuring accurate labeling of eggshell (5%) and pore (0.1%) voxels. The results indicate that besides edge-attention and class balancing, 3D context preservation and 3D convolution are of paramount importance for extrapolating subvoxel features.