A novel artificial intelligence application has the potential to transform the way hair is studied by scientists and pave way for the creation of hair-only medical diagnostics, a study showed on Thursday.
The hair quantification procedure is streamlined and
expedited by the AI model, enabling a microscope to scan slides and gather
pictures of hundreds of hairs at once.
Scientists at Washington State University's College of
Veterinary Medicine conducted and produced the application's research, which
was published in the Journal of Investigative Dermatology.
It can gather a large amount of high-resolution data in a
matter of seconds, which is subsequently processed by a deep learning algorithm
to determine the colour, form, width, and length of each individual hair.
Researchers used mouse fur to test it, but any species'
hair, including human hair, might be treated with it.
"In many ways, an individual's hair is somewhat a
reflection of health. If you start separating them out with tweezers, which a
lot of hair scientists do, you can make interesting discoveries. The idea was
what happens if you can make a computer program do that for you," said
Ryan Driskell associate professor and principal investigator of the research.
A molecular biosciences graduate student Jasson Makkar at
Washington State University developed an AI computer vision model to identify
hair using a high-performance computing cluster and an Aperio GT450 microscope.
The application has implications in forensics and the hair
product industry, allowing scientists to assess health through hair.
It could create a scale for human doctors and veterinarians
to grade overall health based on hair and could aid criminal investigations by
identifying hair species and shedding light on age, health, and ethnicity.
"There's this methodology in law enforcement agencies
that utilises hair fibre classification as a forensic tool in criminal
investigations. This methodology has been somewhat controversial because much
of this work was performed by forensic technicians visually identifying hair
types found at a crime scene and then cross-referencing them against a limited
database of hair types across all mammals," Driskell added.
Overall this is a tool that could revolutionise the way
technology and health interact, which would be beneficial for both patients and
doctors in the long run.
No comments:
Post a Comment