High-throughput micro-CT scanning and deep learning segmentation workflow for analyses of shelly invertebrates and their fossils: Examples from marine Bivalvia

Abstract

The largest source of empirical data on the history of life largely derives from the marine invertebrates. Their rich fossil record is an important testing ground for macroecological and macroevolutionary theory, but much of this historical biodiversity remains locked away in consolidated sediments. Manually preparing invertebrate fossils out of their matrix can require weeks to months of careful excavation and cannot guarantee the recovery of important features on specimens. Micro-CT is greatly improving our access to the morphologies of these fossils, but it remains difficult to digitally separate specimens from sediments of similar compositions, e.g., calcareous shells in a carbonate rich matrix. Here we provide a workflow for using deep learning—a subset of machine learning based on artificial neural networks—to augment the segmentation of these difficult fossils. We also provide a guide for bulk scanning fossil and Recent shells, with sizes ranging from 1 mm to 20 cm, enabling the rapid acquisition of large-scale 3D datasets for macroevolutionary and macroecological analyses (300–500 shells in 8 hours of scanning). We then illustrate how these approaches have been used to access new dimensions of morphology, allowing rigorous statistical testing of spatial and temporal patterns in morphological evolution, which open novel research directions in the history of life.

Automatic Segmentation of Early Triassic Vertebrate Fossil CT Scans: Reducing Human Annotation Time through Deep Learning

“…Edie et al 10 showed that using the built-in deep learning "Segmentation Wizard" in Object Research Systems (ORS) Dragonfly Inc. (2022), they could achieve model's accuracy score of up to 0.97 (Dice 0.13) using fewer than five training slides and 2.5D (3 slices) input dimensions (effectively 15 slices but still only 5 manually segmented ROIs) for fossil bivalve material. However, the morphology of bivalves is significantly less complex than that of a vertebrate skull.…”

“…With the introduction of Deep Learning 9 , palaeontologists have started experimenting with methodologies for automatic image segmentation as a way to cut back on processing times for these large datasets. Recent studies on fossil invertebrate and vertebrate material suggest that much time can be saved using these new technologies 7,10 , but indicate that they currently require a significant amount of training input (manually segmented entire CT datasets) to accurately predict ROIs in more complex material, such as dinosaur skulls 7 .…”

Deep learning approaches to the phylogenetic placement of extinct pollen morphotypes

“…Significant morphological convergence would confound the analysis, so the best candidates would be taxa for which the relationship between morphology and phylogeny are well established. This includes both plant and animal clades with existing image databases, including foraminifera ( 56 ), bivalves ( 57 ), and plant phytoliths ( 58 ).…”

Automatic identification and morphological comparison of bivalve and brachiopod fossils based on deep learning

“…In the future, it may be possible to use this feature to find similar classification boundaries relying on models to perceive more detailed information about fossils ( e.g. , ornamental features and 3D-morphology), which in turn could allow for quantitative differentiation of gradual features ( Klinkenbußet al, 2020 ; Edie, Collins & Jablonski, 2023 ). That could not only provide new possible perspectives for exploring fossil classification and biomorphological evolution, but also try to explore whether there are important features that have been overlooked by experts.…”