@article{fdi:010088569,
  title = {{D}eep learning and wing interferential patterns identify {A}nopheles species and discriminate amongst {G}ambiae complex species},
  author = {{C}annet, {A}. and {S}imon-{C}hane, {C}. and {A}khoundi, {M}. and {H}istace, {A}. and {R}omain, {O}. and {S}ouchaud, {M}. and {J}acob, {P}. and {S}ereno, {D}. and {M}ouline, {K}arine and {B}arnab{\'e}, {C}hristian and {L}ardeux, {F}r{\'e}d{\'e}ric and {B}ouss{\`e}s, {P}hilippe and {S}ereno, {D}enis},
  editor = {},
  language = {{ENG}},
  abstract = {{W}e present a new and innovative identification method based on deep learning of the wing interferential patterns carried by mosquitoes of the {A}nopheles genus to classify and assign 20 {A}nopheles species, including 13 malaria vectors. {W}e provide additional evidence that this approach can identify {A}nopheles spp. with an accuracy of up to 100% for ten out of 20 species. {A}lthough, this accuracy was moderate (>65%) or weak (50%) for three and seven species. {T}he accuracy of the process to discriminate cryptic or sibling species is also assessed on three species belonging to the {G}ambiae complex. {S}trikingly, {A}n. gambiae, {A}n. arabiensis and {A}n. coluzzii, morphologically indistinguishable species belonging to the {G}ambiae complex, were distinguished with 100%, 100%, and 88% accuracy respectively. {T}herefore, this tool would help entomological surveys of malaria vectors and vector control implementation. {I}n the future, we anticipate our method can be applied to other arthropod vector-borne diseases.},
  keywords = {},
  booktitle = {},
  journal = {{S}cientific {R}eports : {N}ature},
  volume = {13},
  numero = {1},
  pages = {13895 [13 ]},
  ISSN = {2045-2322},
  year = {2023},
  DOI = {10.1038/s41598-023-41114-4},
  URL = {https://www.documentation.ird.fr/hor/fdi:010088569},
}