Cargando…

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

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. Con...

Descripción completa

Detalles Bibliográficos
Autores principales: Goodwin, Adam, Padmanabhan, Sanket, Hira, Sanchit, Glancey, Margaret, Slinowsky, Monet, Immidisetti, Rakhil, Scavo, Laura, Brey, Jewell, Sai Sudhakar, Bala Murali Manoghar, Ford, Tristan, Heier, Collyn, Linton, Yvonne-Marie, Pecor, David B., Caicedo-Quiroga, Laura, Acharya, Soumyadipta
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8249627/
https://www.ncbi.nlm.nih.gov/pubmed/34211009
http://dx.doi.org/10.1038/s41598-021-92891-9
Descripción
Sumario: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.