Image recognition based on deep learning in Haemonchus contortus motility assays

Martin Žofka; Linh Thuy Nguyen; Eva Mašátová; Petra Matoušková

doi:10.1016/j.csbj.2022.05.014

Image recognition based on deep learning in Haemonchus contortus motility assays

Comput Struct Biotechnol J. 2022 May 13:20:2372-2380. doi: 10.1016/j.csbj.2022.05.014. eCollection 2022.

Authors

Martin Žofka¹, Linh Thuy Nguyen¹, Eva Mašátová¹, Petra Matoušková¹

Affiliation

¹ Department of Biochemical Sciences, Faculty of Pharmacy, Charles University, Heyrovského 1203, 500 05 Hradec Králové, Czech Republic.

Abstract

Poor efficacy of some anthelmintics and rising concerns about the widespread drug resistance have highlighted the need for new drug discovery. The parasitic nematode Haemonchus contortus is an important model organism widely used for studies of drug resistance and drug screening with the current gold standard being the motility assay. We applied a deep learning approach Mask R-CNN for analysing motility videos containing varying rates of motile worms and compared it to other commonly used algorithms with different levels of complexity, namely the Wiggle Index and the Wide Field-of-View Nematode Tracking Platform. Mask R-CNN consistently outperformed the other algorithms in terms of the detection of worms as well as the precision of motility forecasts, having a mean absolute percentage error of 7.6% and a mean absolute error of 5.6% for the detection and motility forecasts, respectively. Using Mask R-CNN for motility assays confirmed the common problem with algorithms that use non-maximum suppression in detecting overlapping objects, which negatively impacts the overall precision. The use of intersect over union as a measure of the classification of motile / non-motile instances had an overall accuracy of 89%, indicating that it is a viable alternative to previously used methods based on movement characteristics, such as body bends. In comparison to the existing methods evaluated here, Mask R-CNN performed better and we anticipate that this method will broaden the number of possible approaches to video analysis of worm motility.

Keywords: CNN, convolutional neural network; GPU, graphics processing unit; Instance segmentation; IoU, intersection over union; L3, third-stage larva; MAE, mean absolute error; MAPE, mean absolute percentage error; ME, mean error; MPE, mean percentage error; Mask R-CNN; Mask R-CNN, region based convolutional neural network; NMS, non-maximum suppression; Nematode; Object detection; Parasite; ROI, region of interest; RPN, regional proposal network; WF-NTP, Wide Field-of-View Nematode Tracking Platform; WI, Wiggle Index; fps, frames per second; mAP, mean average precision.