Abstract
The speed and accuracy of phenotype detection from medical images are some of the most important qualities needed for any informed and timely response such as early detection of cancer or detection of desirable phenotypes for animal breeding. To improve both these qualities, the world is leveraging artificial intelligence and machine learning against this challenge. Most recently, deep learning has successfully been applied to the medical field to improve detection accuracies and speed for conditions including cancer and COVID-19. In this study, we applied deep neural networks, in the form of a generative adversarial network (GAN), to perform image-to-image processing steps needed for ovine phenotype analysis from CT scans of sheep. Key phenotypes such as gigot geometry and tissue distribution were determined using a computer vision (CV) pipeline. The results of the image processing using a trained GAN are strikingly similar (a similarity index of 98%) when used on unseen test images. The combined GAN-CV pipeline was able to process and determine the phenotypes at a speed of 0.11 s per medical image compared to approximately 30 min for manual processing. We hope this pipeline represents the first step towards automated phenotype extraction for ovine genetic breeding programmes.
Highlights
Increase in global food demand has led to livestock breeders seeking to produce breeding lines more able to match economic demand which have genetic advantages to primary traits such as growth speed and reduced feed intake
The accuracy of these transformations was confirmed by visual inspection of predicted images and measurement of image similarity metrics including mean squared error (MSE) and structural similarity index (SSI)
Raw computed tomography (CT) scans not previously seen by the generative adversarial network (GAN) were processed using the trained model at a speed of 0.11 s per scan
Summary
Increase in global food demand has led to livestock breeders seeking to produce breeding lines more able to match economic demand which have genetic advantages to primary traits such as growth speed and reduced feed intake. Non-invasive imaging techniques, such as computed tomography (CT), magnetic resonance imaging (MRI) and ultrasound, can provide detailed data from which phenotypes can be extracted [11,12] and used in breeding programmes. One major benefit of using these non-invasive imaging techniques is that internal phenotypic data, such as muscle and fat distribution [13], organ size and limb morphology, can be incorporated more swiftly into genetic breeding programmes for live breeding animals [14]. One hurdle which can impact extraction of useful phenotypic information is the processing and analysis of these images which can be time consuming and costly, especially if there is a need to re-analyse historic databases to measure newly emerging phenotypes
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
