Automatic classification of parasitized fruit fly pupae from X-ray images by convolutional neural networks

Abstract

The parasitoid wasp Diachasmimorpha longicaudata (Hymenoptera: Braconidae) has been used for the biological control of fruit fly larvae in many countries. Due to the large scale of production, quality control systems must be utilized to assess insect quality to optimize prerelease activities. However, the parasitism rate, and the unparasitized puparia, which become waste pupae, can only be known after waiting for the emergence of the adults from sampled pupae (ca. 16 days at 25 °C). This waiting time can result in resources being wasted. A way to speed up the quality control of pupal batches and increase the accuracy of the production process would be to combine digital radiography of the parasitized pupae and deep learning methods for the automatic classification of images. Therefore, the purpose of this work was to discriminate parasitized from waste pupae through X-ray images and to test the suitability of 7 Convolutional Neural Networks to classify the pupal images. Radiographic images from 11-day-old pupae allowed the in vivo identification of immature stages of the parasitoid, preserving the viability of the wasp. A positive correlation was found between the number of emerged parasitoids and the ones identified in the X-ray images. In terms of performance metrics, the accuracies achieved by all CNN-based neural architectures were higher than 97%, indicating a high predictive classification power. At least three of the CNNs tested showed great potential as classifiers of X-ray images of parasitized pupae and can be indicated for practical applications in quality control programs.