The Potential of Deep Learning Object Detection in Citizen-Driven Snail Host Monitoring to Map Putative Disease Transmission Sites
Schistosomiasis is a neglected tropical disease caused by parasitic flukes transmitted by freshwater snails. Despite increasing efforts of mass drug administration, schistosomiasis remains a public health concern and the World Health Organization recommends complementary snail control. To address th...
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/724 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554948756602880 |
|---|---|
| author | Kin Ho Chan Julius Tumusiime Liesbet Jacobs Tine Huyse |
| author_facet | Kin Ho Chan Julius Tumusiime Liesbet Jacobs Tine Huyse |
| author_sort | Kin Ho Chan |
| collection | DOAJ |
| description | Schistosomiasis is a neglected tropical disease caused by parasitic flukes transmitted by freshwater snails. Despite increasing efforts of mass drug administration, schistosomiasis remains a public health concern and the World Health Organization recommends complementary snail control. To address the need for broad-scale and actual snail distribution data to guide snail control, we adopted a citizen science approach and recruited citizen scientists (CSs) to perform weekly snail sampling in an endemic setting in Uganda. Snails were identified, sorted and counted according to genus, and photographed; and the photos were uploaded for expert-led validation and feedback. However, expert validation is time-consuming and introduces a delay in verified data output. Thus, artificial intelligence could provide a solution by means of automated detection and counting of multiple snails collected from the field. Trained on approximately 2,500 citizen-collected images, the resulting model can simultaneously detect and count Biomphalaria and Radix snails with average precision of 98.1% and 98.8%, respectively. The object detection model also agreed with the expert’s decision, on average, for 98.8% of the test images and can be run in real time (24.6 images per second). We conclude that the automatic and instant detection can rapidly and reliably validate data submitted by CSs in the field, ultimately minimizing expert validation efforts and thereby facilitating the mapping of putative schistosomiasis transmission sites. An extension to a mobile application could equip CSs in remote areas with instant learning opportunities and expert-like identification skills, overcoming the need for on-site training and extensive expert intervention. |
| format | Article |
| id | doaj-art-88dde7591fb646c09f87d2d4539fc50b |
| 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-88dde7591fb646c09f87d2d4539fc50b2025-01-08T07:54:41ZengUbiquity PressCitizen Science: Theory and Practice2057-49912024-12-0191343410.5334/cstp.724706The Potential of Deep Learning Object Detection in Citizen-Driven Snail Host Monitoring to Map Putative Disease Transmission SitesKin Ho Chan0https://orcid.org/0000-0003-2573-4898Julius Tumusiime1https://orcid.org/0000-0002-4822-1078Liesbet Jacobs2https://orcid.org/0000-0002-1137-5372Tine Huyse3https://orcid.org/0000-0001-8164-9757Dept. of Biology, Royal Museum for Central AfricaDepartment of Environment and Livelihoods Support Systems, Mbarara University of Science and TechnologyDept. of Earth & Environmental Sciences, KU Leuven, BE; Institute for Biodiversity and Ecosystem Dynamics, University of AmsterdamDept. of Biology, Royal Museum for Central AfricaSchistosomiasis is a neglected tropical disease caused by parasitic flukes transmitted by freshwater snails. Despite increasing efforts of mass drug administration, schistosomiasis remains a public health concern and the World Health Organization recommends complementary snail control. To address the need for broad-scale and actual snail distribution data to guide snail control, we adopted a citizen science approach and recruited citizen scientists (CSs) to perform weekly snail sampling in an endemic setting in Uganda. Snails were identified, sorted and counted according to genus, and photographed; and the photos were uploaded for expert-led validation and feedback. However, expert validation is time-consuming and introduces a delay in verified data output. Thus, artificial intelligence could provide a solution by means of automated detection and counting of multiple snails collected from the field. Trained on approximately 2,500 citizen-collected images, the resulting model can simultaneously detect and count Biomphalaria and Radix snails with average precision of 98.1% and 98.8%, respectively. The object detection model also agreed with the expert’s decision, on average, for 98.8% of the test images and can be run in real time (24.6 images per second). We conclude that the automatic and instant detection can rapidly and reliably validate data submitted by CSs in the field, ultimately minimizing expert validation efforts and thereby facilitating the mapping of putative schistosomiasis transmission sites. An extension to a mobile application could equip CSs in remote areas with instant learning opportunities and expert-like identification skills, overcoming the need for on-site training and extensive expert intervention.https://account.theoryandpractice.citizenscienceassociation.org/index.php/up-j-cstp/article/view/724object detectionschistosomiasissnail monitoringcitizen sciencesub-saharan africa |
| spellingShingle | Kin Ho Chan Julius Tumusiime Liesbet Jacobs Tine Huyse The Potential of Deep Learning Object Detection in Citizen-Driven Snail Host Monitoring to Map Putative Disease Transmission Sites Citizen Science: Theory and Practice object detection schistosomiasis snail monitoring citizen science sub-saharan africa |
| title | The Potential of Deep Learning Object Detection in Citizen-Driven Snail Host Monitoring to Map Putative Disease Transmission Sites |
| title_full | The Potential of Deep Learning Object Detection in Citizen-Driven Snail Host Monitoring to Map Putative Disease Transmission Sites |
| title_fullStr | The Potential of Deep Learning Object Detection in Citizen-Driven Snail Host Monitoring to Map Putative Disease Transmission Sites |
| title_full_unstemmed | The Potential of Deep Learning Object Detection in Citizen-Driven Snail Host Monitoring to Map Putative Disease Transmission Sites |
| title_short | The Potential of Deep Learning Object Detection in Citizen-Driven Snail Host Monitoring to Map Putative Disease Transmission Sites |
| title_sort | potential of deep learning object detection in citizen driven snail host monitoring to map putative disease transmission sites |
| topic | object detection schistosomiasis snail monitoring citizen science sub-saharan africa |
| url | https://account.theoryandpractice.citizenscienceassociation.org/index.php/up-j-cstp/article/view/724 |
| work_keys_str_mv | AT kinhochan thepotentialofdeeplearningobjectdetectionincitizendrivensnailhostmonitoringtomapputativediseasetransmissionsites AT juliustumusiime thepotentialofdeeplearningobjectdetectionincitizendrivensnailhostmonitoringtomapputativediseasetransmissionsites AT liesbetjacobs thepotentialofdeeplearningobjectdetectionincitizendrivensnailhostmonitoringtomapputativediseasetransmissionsites AT tinehuyse thepotentialofdeeplearningobjectdetectionincitizendrivensnailhostmonitoringtomapputativediseasetransmissionsites AT kinhochan potentialofdeeplearningobjectdetectionincitizendrivensnailhostmonitoringtomapputativediseasetransmissionsites AT juliustumusiime potentialofdeeplearningobjectdetectionincitizendrivensnailhostmonitoringtomapputativediseasetransmissionsites AT liesbetjacobs potentialofdeeplearningobjectdetectionincitizendrivensnailhostmonitoringtomapputativediseasetransmissionsites AT tinehuyse potentialofdeeplearningobjectdetectionincitizendrivensnailhostmonitoringtomapputativediseasetransmissionsites |