Automated segmentation of synchrotron-scanned fossils

Computed tomography has revolutionised the study of the internal three-dimensional structure of fossils. Historically, fossils typically spent years in preparation to be freed from the enclosing rock. Now, X-ray and synchrotron tomography reveal structures that are otherwise invisible, and data acqu...

Full description

Saved in:
Bibliographic Details
Main Authors: Melanie A. D. During, Jordan K. Matelsky, Fredrik K. Gustafsson, Dennis F. A. E. Voeten, Donglei Chen, Brock A. Wester, Konrad P. Kording, Per E. Ahlberg, Thomas B. Schön
Format: Article
Language:English
Published: Pensoft Publishers 2025-03-01
Series:Fossil Record
Online Access:https://fr.pensoft.net/article/139379/download/pdf/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850028252834299904
author Melanie A. D. During
Jordan K. Matelsky
Fredrik K. Gustafsson
Dennis F. A. E. Voeten
Donglei Chen
Brock A. Wester
Konrad P. Kording
Per E. Ahlberg
Thomas B. Schön
author_facet Melanie A. D. During
Jordan K. Matelsky
Fredrik K. Gustafsson
Dennis F. A. E. Voeten
Donglei Chen
Brock A. Wester
Konrad P. Kording
Per E. Ahlberg
Thomas B. Schön
author_sort Melanie A. D. During
collection DOAJ
description Computed tomography has revolutionised the study of the internal three-dimensional structure of fossils. Historically, fossils typically spent years in preparation to be freed from the enclosing rock. Now, X-ray and synchrotron tomography reveal structures that are otherwise invisible, and data acquisition can be fast. However, manual segmentation of these 3D volumes can still take months to years. This is especially challenging for resource-poor teams, as scanning may be free, but the computing power and (AI-assisted) segmentation software required to handle the resulting large data sets are complex to use and expensive. Here we present a free, browser-based segmentation tool that reduces computational overhead by splitting volumes into small chunks, allowing processing on low-memory, inexpensive hardware. Our tool also speeds up collaborative ground-truth generation and 3D visualisation, all in-browser. We developed and evaluated our pipeline on various open-data scans of differing contrast, resolution, textural complexity, and size. Our tool successfully isolated the Thrinaxodon and Broomistega pair from an Early Triassic burrow. It isolated cranial bones from the Cretaceous acipenseriform Parapsephurus willybemisi on both 45.53 µm and 13.67 µm resolution (voxel size) scanning data. We also isolated bones of the Middle Triassic sauropterygian Nothosaurus and a challenging scan of a squamate embryo inside an egg dating back to the Early Cretaceous. Our tool reliably reproduces expert-supervised segmentation at a fraction of the time and cost, offering greater accessibility than existing tools. Beyond the online tool, all our code is open source, enabling contributions from the palaeontology community to further this emerging machine-learning ecosystem.
format Article
id doaj-art-800d211e9fb6471a9d9d5ed65885a3c9
institution DOAJ
issn 2193-0074
language English
publishDate 2025-03-01
publisher Pensoft Publishers
record_format Article
series Fossil Record
spelling doaj-art-800d211e9fb6471a9d9d5ed65885a3c92025-08-20T02:59:52ZengPensoft PublishersFossil Record2193-00742025-03-0128110311410.3897/fr.28.e139379139379Automated segmentation of synchrotron-scanned fossilsMelanie A. D. During0Jordan K. Matelsky1Fredrik K. Gustafsson2Dennis F. A. E. Voeten3Donglei Chen4Brock A. Wester5Konrad P. Kording6Per E. Ahlberg7Thomas B. Schön8Uppsala UniversityUniversity of PennsylvaniaKarolinska InstitutetUppsala UniversityUppsala UniversityJohns Hopkins University Applied Physics LaboratoryUniversity of PennsylvaniaUppsala UniversityUppsala UniversityComputed tomography has revolutionised the study of the internal three-dimensional structure of fossils. Historically, fossils typically spent years in preparation to be freed from the enclosing rock. Now, X-ray and synchrotron tomography reveal structures that are otherwise invisible, and data acquisition can be fast. However, manual segmentation of these 3D volumes can still take months to years. This is especially challenging for resource-poor teams, as scanning may be free, but the computing power and (AI-assisted) segmentation software required to handle the resulting large data sets are complex to use and expensive. Here we present a free, browser-based segmentation tool that reduces computational overhead by splitting volumes into small chunks, allowing processing on low-memory, inexpensive hardware. Our tool also speeds up collaborative ground-truth generation and 3D visualisation, all in-browser. We developed and evaluated our pipeline on various open-data scans of differing contrast, resolution, textural complexity, and size. Our tool successfully isolated the Thrinaxodon and Broomistega pair from an Early Triassic burrow. It isolated cranial bones from the Cretaceous acipenseriform Parapsephurus willybemisi on both 45.53 µm and 13.67 µm resolution (voxel size) scanning data. We also isolated bones of the Middle Triassic sauropterygian Nothosaurus and a challenging scan of a squamate embryo inside an egg dating back to the Early Cretaceous. Our tool reliably reproduces expert-supervised segmentation at a fraction of the time and cost, offering greater accessibility than existing tools. Beyond the online tool, all our code is open source, enabling contributions from the palaeontology community to further this emerging machine-learning ecosystem.https://fr.pensoft.net/article/139379/download/pdf/
spellingShingle Melanie A. D. During
Jordan K. Matelsky
Fredrik K. Gustafsson
Dennis F. A. E. Voeten
Donglei Chen
Brock A. Wester
Konrad P. Kording
Per E. Ahlberg
Thomas B. Schön
Automated segmentation of synchrotron-scanned fossils
Fossil Record
title Automated segmentation of synchrotron-scanned fossils
title_full Automated segmentation of synchrotron-scanned fossils
title_fullStr Automated segmentation of synchrotron-scanned fossils
title_full_unstemmed Automated segmentation of synchrotron-scanned fossils
title_short Automated segmentation of synchrotron-scanned fossils
title_sort automated segmentation of synchrotron scanned fossils
url https://fr.pensoft.net/article/139379/download/pdf/
work_keys_str_mv AT melanieadduring automatedsegmentationofsynchrotronscannedfossils
AT jordankmatelsky automatedsegmentationofsynchrotronscannedfossils
AT fredrikkgustafsson automatedsegmentationofsynchrotronscannedfossils
AT dennisfaevoeten automatedsegmentationofsynchrotronscannedfossils
AT dongleichen automatedsegmentationofsynchrotronscannedfossils
AT brockawester automatedsegmentationofsynchrotronscannedfossils
AT konradpkording automatedsegmentationofsynchrotronscannedfossils
AT pereahlberg automatedsegmentationofsynchrotronscannedfossils
AT thomasbschon automatedsegmentationofsynchrotronscannedfossils