Eye on AI - May 27th, 2022
Welcome to Aigora's "Eye on AI" series, where we round up exciting news at the intersection of consumer science and artificial intelligence!
We’re all about smell this week as we look into two new applications of olfactory AI, including a sensor that smells nomadic mushrooms and diagnoses diseases in livestock, and another that smells cancer in patients.
Huge Potential for New AI That Sniffs Urine to Diagnose Cancer
We begin with a look at a potentially new revolutionary sniffing technology. According to the article “A Sensor Sniffs for Cancer, Using Artificial Intelligence,” researchers at Memorial Sloan Kettering Cancer Center (MSK) have developed a new sensor that uses AI to sniff out cancer in patients.
“Like the nose, the cancer detection technology uses an array of multiple sensors to detect a molecular signature of the disease,” writes MSKCC’s editorial team. “Instead of the signals going to the brain, they are interpreted by machine learning — a type of computer artificial intelligence.”
The technology was built using sensors composed of carbon nanotubes, which are fluorescent tubes 100,000 times smaller than the width of a human hair that is sensitive to minute interactions with molecules in their environment. Each nanotube sensor detects different molecules in a patient’s blood sample and creates a unique fluorescent pattern based on what molecules are identified. The pattern is tracked by a machine-learning algorithm, which has been trained to identify the difference between a cancer fingerprint and a normal one. Through testing, the researchers found that their sensors more accurately detect ovarian cancer in patients than current methods.
“Early detection, facilitated by cancer screening efforts, is a crucial strategy to prevent cancer deaths,” continues MSKCC’s editorial staff. “As a recent briefing from the White House states, ‘With regular recommended screenings, we can often catch cancer when there may be more effective treatment options or even prevent it from developing by removing precancerous tissue.’”
This new technology doesn’t need a biomarker, which has many researchers excited. The hope is that in the future, this technology can be used to detect numerous types of cancer by smelling urine samples. If the technology proves successful, it could have a huge impact on reducing cancer deaths.
Student-Developed Sensor Can Smell Disease in Livestock
Continuing on the theme of smell, according to the article “Computer chips that can smell and nomadic mushrooms win the AtlasInvest Entrepreneurship Grant,” LumiNose, which uses receptor chips to diagnose early diseases in livestock, recently won the AtlasInvest Entrepreneurship Grant for the most commercially impactful idea.
“... development manager Saptarshi Mukhopadhyay made a reference in his impressive pitch to the WUR study in which bees were trained to smell coronavirus,” writes WUR’s editorial team. “By combining the olfactory receptor chips with machine learning, LumiNose developed equipment that will allow many livestock farmers to diagnose illness in animals sooner.”
LumiNose is a platform-based technology that uses something called “Insect Odour Receptors”, a biomimicry technology that mimics the very sensitive olfactory ability of insects. It is used to detect early diseases in animals, which is a major concern for farmers and the CDC. Each year, according to the CDC, enteric diseases linked to animals or their environments are estimated to cause 450,000 illnesses, 5,000 hospitalizations, and 76 deaths in humans in the United States alone. LumiNose has the potential to seriously reduce animal-induced ailments at their root, which could go a long way in keeping people healthy. I’ll be interested to see how LumiNose progresses, and if it can expand to larger-scale applications that help reduce animal disease.
Google’s DeepMind says it is on verge of achieving human-level AI
Artificial intelligence powered an autonomous cargo ship for an entire 500 miles
Tiny robotic crab is the smallest remote-controlled walking robot to date
That's it for now. If you'd like to receive email updates from Aigora, including weekly video recaps of our blog activity, click on the button below to join our email list. Thanks for stopping by!