Mosquito species identification using convolutional neural networks with a multitiered ensemble model for novel species detection

Abstract With over 3500 mosquito species described, accurate species identification of the few implicated in disease transmission is critical to mosquito borne disease mitigation. Yet this task is hindered by limited global taxonomic expertise and specimen damage consistent across common capture met...

Full description

Saved in:
Bibliographic Details
Main Authors: Autumn Goodwin, Sanket Padmanabhan, Sanchit Hira, Margaret Glancey, Monet Slinowsky, Rakhil Immidisetti, Laura Scavo, Jewell Brey, Bala Murali Manoghar Sai Sudhakar, Tristan Ford, Collyn Heier, Yvonne-Marie Linton, David B. Pecor, Laura Caicedo-Quiroga, Soumyadipta Acharya
Format: Article
Language:English
Published: Nature Portfolio 2021-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-021-92891-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850190836725186560
author Autumn Goodwin
Sanket Padmanabhan
Sanchit Hira
Margaret Glancey
Monet Slinowsky
Rakhil Immidisetti
Laura Scavo
Jewell Brey
Bala Murali Manoghar Sai Sudhakar
Tristan Ford
Collyn Heier
Yvonne-Marie Linton
David B. Pecor
Laura Caicedo-Quiroga
Soumyadipta Acharya
author_facet Autumn Goodwin
Sanket Padmanabhan
Sanchit Hira
Margaret Glancey
Monet Slinowsky
Rakhil Immidisetti
Laura Scavo
Jewell Brey
Bala Murali Manoghar Sai Sudhakar
Tristan Ford
Collyn Heier
Yvonne-Marie Linton
David B. Pecor
Laura Caicedo-Quiroga
Soumyadipta Acharya
author_sort Autumn Goodwin
collection DOAJ
description Abstract With over 3500 mosquito species described, accurate species identification of the few implicated in disease transmission is critical to mosquito borne disease mitigation. Yet this task is hindered by limited global taxonomic expertise and specimen damage consistent across common capture methods. Convolutional neural networks (CNNs) are promising with limited sets of species, but image database requirements restrict practical implementation. Using an image database of 2696 specimens from 67 mosquito species, we address the practical open-set problem with a detection algorithm for novel species. Closed-set classification of 16 known species achieved 97.04 ± 0.87% accuracy independently, and 89.07 ± 5.58% when cascaded with novelty detection. Closed-set classification of 39 species produces a macro F1-score of 86.07 ± 1.81%. This demonstrates an accurate, scalable, and practical computer vision solution to identify wild-caught mosquitoes for implementation in biosurveillance and targeted vector control programs, without the need for extensive image database development for each new target region.
format Article
id doaj-art-e21bc90183f8402585e3f54b7e9d49ad
institution OA Journals
issn 2045-2322
language English
publishDate 2021-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e21bc90183f8402585e3f54b7e9d49ad2025-08-20T02:15:08ZengNature PortfolioScientific Reports2045-23222021-07-0111111510.1038/s41598-021-92891-9Mosquito species identification using convolutional neural networks with a multitiered ensemble model for novel species detectionAutumn Goodwin0Sanket Padmanabhan1Sanchit Hira2Margaret Glancey3Monet Slinowsky4Rakhil Immidisetti5Laura Scavo6Jewell Brey7Bala Murali Manoghar Sai Sudhakar8Tristan Ford9Collyn Heier10Yvonne-Marie Linton11David B. Pecor12Laura Caicedo-Quiroga13Soumyadipta Acharya14VectechVectechCenter for Bioengineering Innovation and Design, Biomedical Engineering Department, Whiting School of Engineering, The Johns Hopkins UniversityVectechCenter for Bioengineering Innovation and Design, Biomedical Engineering Department, Whiting School of Engineering, The Johns Hopkins UniversityCenter for Bioengineering Innovation and Design, Biomedical Engineering Department, Whiting School of Engineering, The Johns Hopkins UniversityCenter for Bioengineering Innovation and Design, Biomedical Engineering Department, Whiting School of Engineering, The Johns Hopkins UniversityCenter for Bioengineering Innovation and Design, Biomedical Engineering Department, Whiting School of Engineering, The Johns Hopkins UniversityVectechVectechCenter for Bioengineering Innovation and Design, Biomedical Engineering Department, Whiting School of Engineering, The Johns Hopkins UniversityWalter Reed Biosystematics Unit (WRBU), Smithsonian Institution Museum Support CenterWalter Reed Biosystematics Unit (WRBU), Smithsonian Institution Museum Support CenterWalter Reed Biosystematics Unit (WRBU), Smithsonian Institution Museum Support CenterCenter for Bioengineering Innovation and Design, Biomedical Engineering Department, Whiting School of Engineering, The Johns Hopkins UniversityAbstract With over 3500 mosquito species described, accurate species identification of the few implicated in disease transmission is critical to mosquito borne disease mitigation. Yet this task is hindered by limited global taxonomic expertise and specimen damage consistent across common capture methods. Convolutional neural networks (CNNs) are promising with limited sets of species, but image database requirements restrict practical implementation. Using an image database of 2696 specimens from 67 mosquito species, we address the practical open-set problem with a detection algorithm for novel species. Closed-set classification of 16 known species achieved 97.04 ± 0.87% accuracy independently, and 89.07 ± 5.58% when cascaded with novelty detection. Closed-set classification of 39 species produces a macro F1-score of 86.07 ± 1.81%. This demonstrates an accurate, scalable, and practical computer vision solution to identify wild-caught mosquitoes for implementation in biosurveillance and targeted vector control programs, without the need for extensive image database development for each new target region.https://doi.org/10.1038/s41598-021-92891-9
spellingShingle Autumn Goodwin
Sanket Padmanabhan
Sanchit Hira
Margaret Glancey
Monet Slinowsky
Rakhil Immidisetti
Laura Scavo
Jewell Brey
Bala Murali Manoghar Sai Sudhakar
Tristan Ford
Collyn Heier
Yvonne-Marie Linton
David B. Pecor
Laura Caicedo-Quiroga
Soumyadipta Acharya
Mosquito species identification using convolutional neural networks with a multitiered ensemble model for novel species detection
Scientific Reports
title Mosquito species identification using convolutional neural networks with a multitiered ensemble model for novel species detection
title_full Mosquito species identification using convolutional neural networks with a multitiered ensemble model for novel species detection
title_fullStr Mosquito species identification using convolutional neural networks with a multitiered ensemble model for novel species detection
title_full_unstemmed Mosquito species identification using convolutional neural networks with a multitiered ensemble model for novel species detection
title_short Mosquito species identification using convolutional neural networks with a multitiered ensemble model for novel species detection
title_sort mosquito species identification using convolutional neural networks with a multitiered ensemble model for novel species detection
url https://doi.org/10.1038/s41598-021-92891-9
work_keys_str_mv AT autumngoodwin mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT sanketpadmanabhan mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT sanchithira mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT margaretglancey mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT monetslinowsky mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT rakhilimmidisetti mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT laurascavo mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT jewellbrey mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT balamuralimanogharsaisudhakar mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT tristanford mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT collynheier mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT yvonnemarielinton mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT davidbpecor mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT lauracaicedoquiroga mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection
AT soumyadiptaacharya mosquitospeciesidentificationusingconvolutionalneuralnetworkswithamultitieredensemblemodelfornovelspeciesdetection