Treffer: Deep learning approaches to landmark detection in tsetse wing images.

Morphometric analysis of wings has been suggested for identifying and controlling isolated populations of tsetse (Glossina spp), vectors of human and animal trypanosomiasis in Africa. Single-wing images were captured from an extensive data set of field-collected tsetse wings of species Glossina pallidipes and G. m. morsitans. Morphometric analysis required locating 11 anatomical landmarks on each wing. The manual location of landmarks is time-consuming, prone to error, and infeasible for large data sets. We developed a two-tier method using deep learning architectures to classify images and make accurate landmark predictions. The first tier used a classification convolutional neural network to remove most wings that were missing landmarks. The second tier provided landmark coordinates for the remaining wings. We compared direct coordinate regression using a convolutional neural network and segmentation using a fully convolutional network for the second tier. For the resulting landmark predictions, we evaluate shape bias using Procrustes analysis. We pay particular attention to consistent labelling to improve model performance. For an image size of 1024 × 1280, data augmentation reduced the mean pixel distance error from 8.3 (95% confidence interval [4.4,10.3]) to 5.34 (95% confidence interval [3.0,7.0]) for the regression model. For the segmentation model, data augmentation did not alter the mean pixel distance error of 3.43 (95% confidence interval [1.9,4.4]). Segmentation had a higher computational complexity and some large outliers. Both models showed minimal shape bias. We deployed the regression model on the complete unannotated data consisting of 14,354 pairs of wing images since this model had a lower computational cost and more stable predictions than the segmentation model. The resulting landmark data set was provided for future morphometric analysis. The methods we have developed could provide a starting point to studying the wings of other insect species. All the code used in this study has been written in Python and open sourced. Author summary: Tsetse flies, vectors of human and livestock disease, cost African countries billions of dollars annually. Wing shape can be used to identify isolated tsetse populations for suppression. The shape can be captured from digital images by locating anatomical points termed landmarks on the wings. Manual positioning of landmarks is prone to error and only feasible for small data sets. We analyse 14,354 wings and have developed a novel method for automatically positioning landmarks on insect wings. We use a two-step approach, first removing wings that are missing landmarks due to damage. We thereby provide accurate landmarks, unbiased for wing shape. We compared two modern deep-learning models to locate landmarks and showed how data manipulation techniques improve performance. We deployed the final system to generate the landmark data for the tsetse wing images and provide the trained models for transfer learning on similar tasks with smaller data sets. Our methods will allow researchers to study tsetse wing shape in relation to other biological data and to gauge how wing shape characterises tsetse populations. Our method could provide a starting point to the study of the wings of other insect species. [ABSTRACT FROM AUTHOR]