UW researcher creates AI-assisted technology to detect bone fractures

A University of Waterloo (UW) engineer help create AI-assisted technology to improve how doctors detect a bone fracture.

Omar Ramahi, a professor in the department of electrical and computer engineering, is the lead researcher on the project and claims it could be a breakthrough for the medical industry.

He’s created a tool that can detect bone fractures without using radiation.

“Early diagnosis will allow doctors to assess what is needed to fix,” Ramahi said.

It can take time for a patient to get an x-ray, CT or MRI. The equipment is not readily available in ambulances or primary care centres. Patients often have to wait for an x-ray or scan at the hospital.

Ramahi said his idea creates a more portable and cost-effective alternative to what currently exists.

Ramahi uses a cow bone for the research. He pairs inexpensive wireless communication antennas with artificial intelligence. Two antennas are placed on opposite sides of the suspected fracture site. One antenna transmits low-frequency microwaves through the bone to the other. A deep neural network AI model, trained on extensive datasets of human body parts and bone fracture types, then analyzes the data.

“So it's basically information rather than an image or an impression,” Ramahi said.

Another benefit to the tool is interpretation. Conventional medical imaging methods require expert interpretation, but this system could provide a preliminary fracture diagnosis in emergencies and avoids using radiation.

“The energy is much less than what we use in our cell phone. So it's a very benign, non-invasive, non-ionizing, non-harmful,” Ramahi said.

The system is still in the lab phase, but portability is the key. The researchers hope to develop a portable device, like a cuff that wraps around the injured area, and one day get the technology in the hands of medical professionals.

“We can come up with a prototype within a year to 18 months, because the system is really simple,” Ramahi said.

Ramahi said it could be used in all kinds of medical fields, like paramedics, elite athletic team doctors, nursing homes and emergency room patients.

Ramahi said it's not meant to replace medical imaging, but instead assist medical professionals. He said it could be used in all kinds of fields, from paramedics to elite athletic teams, or nursing homes and emergency room patients.

“Anything that has 100 per cent prediction never exists in the biomedical world. But if we can have something that can compete with whatever is available at much lower cost, I think we are making good progress,” Ramahi said.

According to the University of Waterloo, the system was developed in collaboration with an international research team. It is believed to be the first system to use AI with microwaves to detect bone fractures without using imaging techniques.