From Voxels to Viruses: Using Deep Learning and Crowdsourcing to Understand a Virus Factory
Many bioimaging research projects require objects of interest to be identified, located, and then traced to allow quantitative measurement. Depending on the complexity of the system and imaging, instance segmentation is often done manually, and automated approaches still require weeks to months of a...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ubiquity Press
2024-12-01
|
| Series: | Citizen Science: Theory and Practice |
| Subjects: | |
| Online Access: | https://account.theoryandpractice.citizenscienceassociation.org/index.php/up-j-cstp/article/view/739 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554965214003200 |
|---|---|
| author | Avery Pennington Oliver N. F. King Win Min Tun Mark Boyce Geoff Sutton David I. Stuart Mark Basham Michele C. Darrow |
| author_facet | Avery Pennington Oliver N. F. King Win Min Tun Mark Boyce Geoff Sutton David I. Stuart Mark Basham Michele C. Darrow |
| author_sort | Avery Pennington |
| collection | DOAJ |
| description | Many bioimaging research projects require objects of interest to be identified, located, and then traced to allow quantitative measurement. Depending on the complexity of the system and imaging, instance segmentation is often done manually, and automated approaches still require weeks to months of an individual’s time to acquire the necessary training data for AI models. As such, there is a strong need to develop approaches for instance segmentation that minimize the use of expert annotation while maintaining quality on challenging image analysis problems. Herein, we present our work on a citizen science project we ran called Science Scribbler: Virus Factory on the Zooniverse platform, in which citizen scientists annotated a cryo-electron tomography volume by locating and categorising viruses using point-based annotations instead of manually drawing outlines. One crowdsourcing workflow produced a database of virus locations, and the other workflow produced a set of classifications of those locations. Together, this allowed mask annotation to be generated for training a deep learning–based segmentation model. From this model, segmentations were produced that allowed for measurements such as counts of the viruses by virus class. The application of citizen science–driven crowdsourcing to the generation of instance segmentations of volumetric bioimages is a step towards developing annotation-efficient segmentation workflows for bioimaging data. This approach aligns with the growing interest in citizen science initiatives that combine the collective intelligence of volunteers with AI to tackle complex problems while involving the public with research that is being undertaken in these important areas of science. |
| format | Article |
| id | doaj-art-c7b85ec4d16e4096953989d1438c4f5a |
| institution | Kabale University |
| issn | 2057-4991 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Ubiquity Press |
| record_format | Article |
| series | Citizen Science: Theory and Practice |
| spelling | doaj-art-c7b85ec4d16e4096953989d1438c4f5a2025-01-08T07:54:40ZengUbiquity PressCitizen Science: Theory and Practice2057-49912024-12-0191373710.5334/cstp.739721From Voxels to Viruses: Using Deep Learning and Crowdsourcing to Understand a Virus FactoryAvery Pennington0https://orcid.org/0000-0002-1179-4243Oliver N. F. King1https://orcid.org/0000-0002-6152-7207Win Min Tun2https://orcid.org/0000-0003-0991-8785Mark Boyce3https://orcid.org/0000-0003-1687-4848Geoff Sutton4https://orcid.org/0000-0003-4854-590XDavid I. Stuart5https://orcid.org/0000-0002-3426-4210Mark Basham6https://orcid.org/0000-0002-8438-1415Michele C. Darrow7https://orcid.org/0000-0001-6259-1684Rosalind Franklin InstituteDiamond Light SourceDiamond Light SourceDivision of Structural Biology, Oxford UniversityDivision of Structural Biology, Oxford UniversityDiamond Light Source; Division of Structural Biology, Oxford UniversityRosalind Franklin InstituteRosalind Franklin InstituteMany bioimaging research projects require objects of interest to be identified, located, and then traced to allow quantitative measurement. Depending on the complexity of the system and imaging, instance segmentation is often done manually, and automated approaches still require weeks to months of an individual’s time to acquire the necessary training data for AI models. As such, there is a strong need to develop approaches for instance segmentation that minimize the use of expert annotation while maintaining quality on challenging image analysis problems. Herein, we present our work on a citizen science project we ran called Science Scribbler: Virus Factory on the Zooniverse platform, in which citizen scientists annotated a cryo-electron tomography volume by locating and categorising viruses using point-based annotations instead of manually drawing outlines. One crowdsourcing workflow produced a database of virus locations, and the other workflow produced a set of classifications of those locations. Together, this allowed mask annotation to be generated for training a deep learning–based segmentation model. From this model, segmentations were produced that allowed for measurements such as counts of the viruses by virus class. The application of citizen science–driven crowdsourcing to the generation of instance segmentations of volumetric bioimages is a step towards developing annotation-efficient segmentation workflows for bioimaging data. This approach aligns with the growing interest in citizen science initiatives that combine the collective intelligence of volunteers with AI to tackle complex problems while involving the public with research that is being undertaken in these important areas of science.https://account.theoryandpractice.citizenscienceassociation.org/index.php/up-j-cstp/article/view/739machine learningcitizen sciencehuman-in-the-loopvolume segmentationimage processingcryo-electron tomography |
| spellingShingle | Avery Pennington Oliver N. F. King Win Min Tun Mark Boyce Geoff Sutton David I. Stuart Mark Basham Michele C. Darrow From Voxels to Viruses: Using Deep Learning and Crowdsourcing to Understand a Virus Factory Citizen Science: Theory and Practice machine learning citizen science human-in-the-loop volume segmentation image processing cryo-electron tomography |
| title | From Voxels to Viruses: Using Deep Learning and Crowdsourcing to Understand a Virus Factory |
| title_full | From Voxels to Viruses: Using Deep Learning and Crowdsourcing to Understand a Virus Factory |
| title_fullStr | From Voxels to Viruses: Using Deep Learning and Crowdsourcing to Understand a Virus Factory |
| title_full_unstemmed | From Voxels to Viruses: Using Deep Learning and Crowdsourcing to Understand a Virus Factory |
| title_short | From Voxels to Viruses: Using Deep Learning and Crowdsourcing to Understand a Virus Factory |
| title_sort | from voxels to viruses using deep learning and crowdsourcing to understand a virus factory |
| topic | machine learning citizen science human-in-the-loop volume segmentation image processing cryo-electron tomography |
| url | https://account.theoryandpractice.citizenscienceassociation.org/index.php/up-j-cstp/article/view/739 |
| work_keys_str_mv | AT averypennington fromvoxelstovirusesusingdeeplearningandcrowdsourcingtounderstandavirusfactory AT olivernfking fromvoxelstovirusesusingdeeplearningandcrowdsourcingtounderstandavirusfactory AT winmintun fromvoxelstovirusesusingdeeplearningandcrowdsourcingtounderstandavirusfactory AT markboyce fromvoxelstovirusesusingdeeplearningandcrowdsourcingtounderstandavirusfactory AT geoffsutton fromvoxelstovirusesusingdeeplearningandcrowdsourcingtounderstandavirusfactory AT davidistuart fromvoxelstovirusesusingdeeplearningandcrowdsourcingtounderstandavirusfactory AT markbasham fromvoxelstovirusesusingdeeplearningandcrowdsourcingtounderstandavirusfactory AT michelecdarrow fromvoxelstovirusesusingdeeplearningandcrowdsourcingtounderstandavirusfactory |