Automated identification of insect vectors of Chagas disease in Brazil and Mexico: the Virtual Vector Lab
Identification of arthropods important in disease transmission is a crucial, yet difficult, task that can demand considerable training and experience. An important case in point is that of the 150+ species of Triatominae, vectors of Trypanosoma cruzi, causative agent of Chagas disease across the Ame...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2017-04-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/3040.pdf |
| _version_ | 1797418461606969344 |
|---|---|
| author | Rodrigo Gurgel-Gonçalves Ed Komp Lindsay P. Campbell Ali Khalighifar Jarrett Mellenbruch Vagner José Mendonça Hannah L. Owens Keynes de la Cruz Felix A Townsend Peterson Janine M. Ramsey |
| author_facet | Rodrigo Gurgel-Gonçalves Ed Komp Lindsay P. Campbell Ali Khalighifar Jarrett Mellenbruch Vagner José Mendonça Hannah L. Owens Keynes de la Cruz Felix A Townsend Peterson Janine M. Ramsey |
| author_sort | Rodrigo Gurgel-Gonçalves |
| collection | DOAJ |
| description | Identification of arthropods important in disease transmission is a crucial, yet difficult, task that can demand considerable training and experience. An important case in point is that of the 150+ species of Triatominae, vectors of Trypanosoma cruzi, causative agent of Chagas disease across the Americas. We present a fully automated system that is able to identify triatomine bugs from Mexico and Brazil with an accuracy consistently above 80%, and with considerable potential for further improvement. The system processes digital photographs from a photo apparatus into landmarks, and uses ratios of measurements among those landmarks, as well as (in a preliminary exploration) two measurements that approximate aspects of coloration, as the basis for classification. This project has thus produced a working prototype that achieves reasonably robust correct identification rates, although many more developments can and will be added, and—more broadly—the project illustrates the value of multidisciplinary collaborations in resolving difficult and complex challenges. |
| first_indexed | 2024-03-09T06:32:58Z |
| format | Article |
| id | doaj.art-63490c917e9c47eb968868a783eb98c5 |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T06:32:58Z |
| publishDate | 2017-04-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-63490c917e9c47eb968868a783eb98c52023-12-03T11:02:04ZengPeerJ Inc.PeerJ2167-83592017-04-015e304010.7717/peerj.3040Automated identification of insect vectors of Chagas disease in Brazil and Mexico: the Virtual Vector LabRodrigo Gurgel-Gonçalves0Ed Komp1Lindsay P. Campbell2Ali Khalighifar3Jarrett Mellenbruch4Vagner José Mendonça5Hannah L. Owens6Keynes de la Cruz Felix7A Townsend Peterson8Janine M. Ramsey9Faculty of Medicine, Universidade de Brasília, Brasilia, DF, BrazilInformation and Telecommunication Technology Center, University of Kansas, Lawrence, KS, United StatesBiodiversity Institute, University of Kansas, Lawrence, KS, United StatesBiodiversity Institute, University of Kansas, Lawrence, KS, United StatesSpencer Art Museum, University of Kansas, Lawrence, KS, United StatesFaculty of Medicine, Universidade de Brasília, Brasilia, DF, BrazilBiodiversity Institute, University of Kansas, Lawrence, KS, United StatesCentro Regional de Investigación en Salud Pública, Instituto Nacional de Salud Publica, Tapachula, Chiapas, MexicoBiodiversity Institute, University of Kansas, Lawrence, KS, United StatesCentro Regional de Investigación en Salud Pública, Instituto Nacional de Salud Publica, Tapachula, Chiapas, MexicoIdentification of arthropods important in disease transmission is a crucial, yet difficult, task that can demand considerable training and experience. An important case in point is that of the 150+ species of Triatominae, vectors of Trypanosoma cruzi, causative agent of Chagas disease across the Americas. We present a fully automated system that is able to identify triatomine bugs from Mexico and Brazil with an accuracy consistently above 80%, and with considerable potential for further improvement. The system processes digital photographs from a photo apparatus into landmarks, and uses ratios of measurements among those landmarks, as well as (in a preliminary exploration) two measurements that approximate aspects of coloration, as the basis for classification. This project has thus produced a working prototype that achieves reasonably robust correct identification rates, although many more developments can and will be added, and—more broadly—the project illustrates the value of multidisciplinary collaborations in resolving difficult and complex challenges.https://peerj.com/articles/3040.pdfIdentificationChagas diseaseTriatominaeAutomationPrimary occurrence data |
| spellingShingle | Rodrigo Gurgel-Gonçalves Ed Komp Lindsay P. Campbell Ali Khalighifar Jarrett Mellenbruch Vagner José Mendonça Hannah L. Owens Keynes de la Cruz Felix A Townsend Peterson Janine M. Ramsey Automated identification of insect vectors of Chagas disease in Brazil and Mexico: the Virtual Vector Lab PeerJ Identification Chagas disease Triatominae Automation Primary occurrence data |
| title | Automated identification of insect vectors of Chagas disease in Brazil and Mexico: the Virtual Vector Lab |
| title_full | Automated identification of insect vectors of Chagas disease in Brazil and Mexico: the Virtual Vector Lab |
| title_fullStr | Automated identification of insect vectors of Chagas disease in Brazil and Mexico: the Virtual Vector Lab |
| title_full_unstemmed | Automated identification of insect vectors of Chagas disease in Brazil and Mexico: the Virtual Vector Lab |
| title_short | Automated identification of insect vectors of Chagas disease in Brazil and Mexico: the Virtual Vector Lab |
| title_sort | automated identification of insect vectors of chagas disease in brazil and mexico the virtual vector lab |
| topic | Identification Chagas disease Triatominae Automation Primary occurrence data |
| url | https://peerj.com/articles/3040.pdf |
| work_keys_str_mv | AT rodrigogurgelgoncalves automatedidentificationofinsectvectorsofchagasdiseaseinbrazilandmexicothevirtualvectorlab AT edkomp automatedidentificationofinsectvectorsofchagasdiseaseinbrazilandmexicothevirtualvectorlab AT lindsaypcampbell automatedidentificationofinsectvectorsofchagasdiseaseinbrazilandmexicothevirtualvectorlab AT alikhalighifar automatedidentificationofinsectvectorsofchagasdiseaseinbrazilandmexicothevirtualvectorlab AT jarrettmellenbruch automatedidentificationofinsectvectorsofchagasdiseaseinbrazilandmexicothevirtualvectorlab AT vagnerjosemendonca automatedidentificationofinsectvectorsofchagasdiseaseinbrazilandmexicothevirtualvectorlab AT hannahlowens automatedidentificationofinsectvectorsofchagasdiseaseinbrazilandmexicothevirtualvectorlab AT keynesdelacruzfelix automatedidentificationofinsectvectorsofchagasdiseaseinbrazilandmexicothevirtualvectorlab AT atownsendpeterson automatedidentificationofinsectvectorsofchagasdiseaseinbrazilandmexicothevirtualvectorlab AT janinemramsey automatedidentificationofinsectvectorsofchagasdiseaseinbrazilandmexicothevirtualvectorlab |