Anatomy Detection of Cats and Dogs using Localization

The proposed work is an application of artificial intelligence and medical imaging. When positioning a dog to have an X-ray image taken of its paw, a neural network trained in canine anatomy can be configured to inform radiologists if the patient’s paw is improperly placed or even drive motorized hardware to automatically center the patient’s anatomy with respect to the imaging hardware. Diagnostic X-ray images like DICOMs contain header information about the subject including species, anatomy imaged, and the orientation of the image. This information is filled out manually, but the aforementioned neural network could be configured to automatically populate this DICOM tag information. The methods developed in this research will be immediately applicable to the partner organization; these tools will be integrated within iMi’s x-ray imaging system for use in veterinary clinics. Additionally, automatic anatomy detection will allow iMi to develop new hardware informed by this technology.

Intern: 
Fatemeh Esfahani
Faculty Supervisor: 
Alex Thomo
Province: 
British Columbia
Partner University: 
Discipline: 
Program: