Vert-NSM: neural shape models for shape completion, classification, and landmark-free morphometrics of vertebrate specimens
Year: 2026
Type: preprint
Abstract: Natural history museums are building digital 3D archives at a scale that enables geometric morphometric analysis across thousands of specimens. Landmark-based analyses depend on anatomical priors and often exclude unidentified and incomplete specimens, which are abundant in collections and the fossil record. Continuous shape representations offer a landmark-free alternative that can be combined with neural networks to perform shape completion and classification. It is unknown how their morphospaces compare with landmarks or how accurately they perform. We present Vert-NSM, neural shape models for vertebrate biodiversity specimens, and apply them to squamate vertebrae, a well-represented, but challenging test case. Models were trained on 2,896 vertebral meshes from 95 specimens across 40 families, produced in part by the oVert digitization initiative. We evaluated shape completion, classification, and morphometrics of sparse landmarks, dense correspondences, and Vert-NSM latents. Shape completion accuracy reached 0.375% of a vertebral radius. Classification exceeded frequency-weighted chance at nearly every level tested, reaching 80% accuracy for the cervical spine and 90% for Cordylidae. Vert-NSM shared the dominant axes of variation recovered by landmarks, and identified shape differences that did not depend on anatomical priors. In downsampling experiments, models performed well when trained with at least 30 specimens. Vert-NSM has the potential to unlock discoveries from vertebrate collections at scale and in deep time.
DOI: 10.32942/x2nt3x
Institutions: Florida Museum of Natural History, University of Florida
Language: English
Domain: Life Sciences
Open Access status: green
Awards: Digitization TCN: Collaborative Research: oVert: Open Exploration of Vertebrate Diversity in 3D, MRI: Acquisition of Nano-resolution Zeiss Xradia 620 Versa X-ray Computed Tomography with Phase Contrast and Lab Diffraction Contrast Tomography, Collaborative Research: Cross-Cutting Improvements: Non-Clinical Tomography Users Research Network (NoCTURN), Collaborative Research: Harnessing a high-resolution fossil record and novel (AI) workflows to study the effects of climate change on mammalian functional diversity, Collaborative Research: BIO AI: Is asexual reproduction an evolutionary dead end? Leveraging AI and the fossil record to compare evolutionary outcomes across reproductive modes
OpenAlex ID: W7223209836