1. Autofinding egg parasitoids in moth eggs by using machine learning methods in synchrotron-coherent X-ray imaging
- Author
-
Rodrigo Perez Vargas, J., Javier Talavera, R., Bostel, R., Rigon, L., Arfelli, F., Menk, Ralf Hendrik, Rocio Foerster, M., Amilton Foerster, L., Cusatis, C., Hönnicke, M. G., Rodrigo Perez Vargas, J., Javier Talavera, R., Bostel, R., Rigon, L., Arfelli, F., Menk, Ralf Hendrik, Rocio Foerster, M., Amilton Foerster, L., Cusatis, C., and Hönnicke, M. G.
- Abstract
The use of a non-destructive technique, such as the propagation-based X-ray phase contrast radiography (PBR) can be an innovative method for automatic parasitism analysis, especially if it presents standard structures. Herein, an artificial intelligence (AI) model is applied in order to establish a computer vision of egg parasitoids in PBRs of parasitized moth eggs acquired at the Synchrotron Radiation for Medical Physics (SYRMEP) beamline at ELETTRA. PBRs of eggs parasitized in four different stages of parasitism (0 days, 3 days, 5 days and 7 days) have been tested. The AI model performance was evaluated by using different metrics. Average Precision (AP), which measures the accuracy of object detection, was found to be 0.866 and 0.741 for the moth eggs and for the parasites, respectively. Additionally, we found that as stage of parasitism becomes longer, the accuracy of parasitism detection also increases (76 % at 7 days).
- Published
- 2024
- Full Text
- View/download PDF