Development and validation of software that quantifies the larval mortality of Rhipicephalus (Boophilus) microplus cattle tick

Sousa, Isabella Chaves; Figueredo, Weslley Kelson Ribeiro; Tavares, Caio P.; Gomes, Matheus N; Klafke, Guilherme Marcondes; Silva, Aristófanes Corrêa; Costa, Lívio Martins

doi:10.1016/j.ttbdis.2022.101930

Cited by 2 publications

(2 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method was based on the use of the firefly algorithm and fast radial symmetry transform (FRST) techniques and did not present statistical difference in the determination of the LD 50 of ivermectin and fipronil when compared with manual counting. The automation of this method accelerated the process of assessing larval mortality by up to 4.4‐fold (Sousa et al, 2022). Still on the application of artificial intelligence in the field of study of ticks, deep learning models were used to develop an approach based on computer vision for the identification of ticks of the species Amblyomma americanum , Dermacentor variabilis and Ixodes scapularis (Luo et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

“…Nowadays machine learning has been allied with human beings to automate processes in medicine (Zhao et al, 2020), industry (Wang et al, 2018), agribusiness (Lin, Gong, Huang, Liu, & Pan, 2019), among others, with satisfactory results. Industry and universities have also invested in the automation of the process involving ticks and acaricides (Luo, Pearson, Xu, & Rich, 2022;Paiva, Queiroz, Silva, & Silva, 2016;Sousa et al, 2022), which despite the few published works, automation is gradually becoming a reality.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic method based on deep learning to identify and account Rhipicephalus microplus larval hatching

Santos

Tavares

Klafke

et al. 2023

Medical Vet Entomology

Self Cite

View full text Add to dashboard Cite

Reports of Rhipicephalus microplus resistant populations worldwide have increased extensively, making it difficult to control this ectoparasite. The adult immersion test, commonly used to screen for acaricide resistance, produces the results only after 40 days of the tick collection because it needs the eggs to be laid and larvae to hatch. The present study aims to develop an automatic method, based on deep learning, to predict the hatching of R. microplus larva based on egg morphology. Initially, the time course of embryonic development of tick eggs was performed to discriminate between viable and non‐viable eggs. Secondly, using artificial intelligence deep learning techniques, a method was developed to classify and count the eggs. The larval hatching rate of three populations of R. microplus was evaluated for the software validation process. Groups of three and six images of eggs with 12 days of embryonic development were submitted to the software to predict the larval hatching percent automatically. The results obtained by the software were compared with the prediction results of the hatching percentage performed manually by the specialist and with the results of the hatching percentage of larvae obtained in the biological assay. The group with three images of each population submitted to the software for automatic prediction of the larval hatching percent presented mean values of 96.35% ± 3.33 (Piracanjuba population), 95.98% ± 3.5 (Desterro population) and 0.0% ± 0.0 (Barbalha population). For groups with six images, the values were 94.41% ± 3.84 (Piracanjuba population), 95.93% ± 2.36 (Desterro population) and 0.0% ± 0.0 (Barbalha population). Biological assays showed the following hatching percentage values: 98% ± 1.73 (Piracanjuba population); 96% ± 2.1 (Desterro population); and 0.14% ± 0.25 (Barbalha population). There was no statistical difference between the evaluated methods. The automatic method for predicting the hatching percentage of R. microplus larvae was validated and proved to be effective, with considerable reduction in time to obtain results.

show abstract

Section: Discussionmentioning

confidence: 99%