Sheep CT scans could be analysed at lightning speed using machine learning, according to a new study carried out at Scotland's Rural College.

Using a deep neural network – a collection of mathematical artificial neurones designed to mimic a brain – the work demonstrated that a properly trained computer can almost instantly perform image editing, such as removal of the cradle which sheep are scanned in, and then extract key information at a speed of 0.11 seconds per CT scan.

Read more: Sheep Breeders Round Table is just around the corner

The image processing model was trained on CT scans already routinely collected by SRUC’s CT scanning team, allowing new unseen images to be processed using machine learning with an accuracy of 98% compared to those produced manually.

The results of the study, carried out by researcher Dr James Robson, showcase how machine learning could be used to help guide genetic improvement programmes and aid detection of invisible diseases. Important traits such as muscle or fat percentage and length or width of limbs, which are typically measured from the image by hand, were calculated automatically.

Dr Robson said: “This tool not only saves a lot of time but allows us to process far more data than before and gather information which can then be used to guide genetic breeding programmes.

Read more: Sheep OPA scanning justified on welfare and economic grounds

“It’s really amazing to see the wide variety of challenges that machine learning can be used to address. We are hoping to expand this research into other areas and invite any organisation to come forward if they have image or video datasets they think might contain something of interest.”