Researchers from the University of Surrey’s Centre for Vision, Speech and Signal Processing (CVSSP) and School of Veterinary Medicine (SVM) in the U.K. are exploring how a completely automated, image mapping method can be used to discover patterns in MRI data that could help veterinary professionals identify dogs suffering from CM-associated pain.
Published in the Journal of Veterinary Internal Medicine (JVIM), the research focused on CKCS dogs, as the breed is predisposed to the disease, which causes deformity of the skull and neck and can lead to spinal cord damage (syringomyelia [SM]).
The study helped identify features that characterize the differences in the MRI images of dogs with clinical signs of pain associated with CM and those with SM from healthy dogs.
The AI identified the floor of the third ventricle and its close neural tissue, as well as the region in the sphenoid bone, as biomarkers for pain associated with CM, researchers say. Meanwhile, for SM, these biomarkers were the presphenoid bone and the region between the soft palate and the tongue.
“This study suggests the whole skull, rather than just the hindbrain, should be analyzed in diagnostic tests,” says Penny Knowler, PhD, the study’s lead author from SVM. “It also impacts on how we should interpret MRI from affected dogs and the choices we make when we breed predisposed dogs, and [show why we should] develop breeding recommendations.”
While SM is straightforward to diagnose, the pain associated with CM is difficult to confirm, the study’s authors say.
“The success of our technique suggests machine learning can be developed as a diagnostic tool to help treat Cavalier King Charles Spaniels suffering from this enigmatic and terrible disease,” says Michaela Spiteri, MSc, PhD, lead author of the study from CVSSP. “We believe AI can be a useful tool for veterinarians caring for our four-legged family members.”
Identification of these biomarkers inspired an additional study, also published in JVIM, which found dogs with CM-associated pain had more brachycephalic features.
“This project demonstrates the potential for AI using machine learning to provide new diagnostic tools for animal health,” says Adrian Hilton, BSc, a distinguished professor at the University of Surrey and director of CVSSP. “Collaboration between experts in CVSSP and Surrey’s SVM is pioneering new approaches to improve animal health and welfare.”
For more, click here.