The Automatic Classification of Pyriproxyfen-Affected Mosquito Ovaries

Abstract

Pyriproxyfen (PPF) may become an alternative insecticide for areas where pyrethroid-resistant vectors are prevalent. The efficacy of PPF can be assessed through the dissection and assessment of vector ovaries. However, this reliance on expertise is subject to limitations. We show here that these limitations can be overcome using a convolutional neural network (CNN) to automate the classification of egg development and thus fertility status. Using TensorFlow, a resnet-50 CNN was pretrained with the ImageNet dataset. This CNN architecture was then retrained using a novel dataset of 524 dissected ovary images from An. gambiae s.l. An. gambiae Akron, and An. funestus s.l., whose fertility status and PPF exposure were known. Data augmentation increased the training set to 6973 images. A test set of 157 images was used to measure accuracy. This CNN model achieved an accuracy score of 94%, and application took a mean time of 38.5 s. Such a CNN can achieve an acceptable level of precision in a quick, robust format and can be distributed in a practical, accessible, and free manner. Furthermore, this approach is useful for measuring the efficacy and durability of PPF treated bednets, and it is applicable to any PPF-treated tool or similarly acting insecticide.

Insecticides for Mosquito Control: Improving and Validating Methods to Strengthen the Evidence Base

“…Standardised methodologies such as SOPs generated by consensus [ 13 , 14 ] will facilitate a comparison and interpretation of the results between testing sites and across studies. Data collection should be made as objective as possible, for example by the use of automated scoring tools [ 20 ]. It is also best practice, when reporting results of a study, to include methodological detail alongside the data and ensure that raw disaggregated data, including control data, is presented.…”

A Novel Deep Learning Model for Accurate Pest Detection and Edge Computing Deployment

“…Mark T. Fowler pretrained a resnet-50 CNN using the ImageNet dataset with TensorFlow. The structure was retrained, achieving an accuracy of 94%, with an average application time of 38.5 s [20]. Qingwen Guo used saliency maps and an improved non-maximum suppression to compute the number of insect pests, achieving a significant improvement in the F1 score [21].…”