Workers at an industrial textile factory.
"Dust thou art, and unto dust shalt thou return." Whoever wrote that famous line probably didn't realize that dust actually contains a secret weapon.
"We have developed the capability to turn dust into data that can be used to trace problems in the supply chain."
Far from being a collection of mere inanimate particles, dust is now recognized as a powerful tool filled with living sensors. Studying those sensors can reveal an object's location history, which can help brands fight unethical manufacturing.
"We have developed the capability to turn dust into data that can be used to trace problems in the supply chain," explains Jessica Green, the CEO of Phylagen, a San-Francisco-based company that she co-founded in 2014.
So how does the technology work?
Dust gathers everywhere—on our bodies, on objects—and that dust contains microbes like bacteria and viruses. Just as we humans have our own unique microbiomes, research has shown that physical locations have their own identifiable patterns of microbes as well. Visiting a place means you may pick up its microbial fingerprint in the dust that settles on you. The DNA of those microbes can later be sequenced in a lab and matched back to the place of origin.
"Your environment is constantly imprinted on you and vice versa," says Justin Gallivan, the director of the Biotechnology Office at DARPA, the research and defense arm of the Pentagon, which is funding Phylagen. "If we have a microbial map of the world," he posits, "can we infer an object's transit history?"
So far, Phylagen has shown that it's possible to identify where a ship came from based on the unique microbial populations it picked up at different naval ports. In another experiment, the sampling technology allowed researchers to determine where a person had walked within 1 kilometer in San Francisco, because of the microbes picked up by their shoes.
One application of this technology is to help companies that make products abroad. Such companies are very interested in determining exactly where their products are coming from, especially if foreign subcontractors are involved.
"In retail and apparel, often the facilities performing the subcontracting are not up to the same code that the brands require their suppliers to be, so there could be poor working conditions," says Roxana Hickey, a data scientist at Phylagen. "A supplier might use a subcontractor to save on the bottom line, but unethical practices are very damaging to the brand."
Before this technology was developed, brands sometimes faced a challenge figuring out what was going on in their supply chain. But now a product can be tested upon arrival in the States; its microbial signature can theoretically be analyzed and matched against a reference database to help determine if its DNA pattern matches that of the place where the product was purported to have been made.
Phylagen declined to elaborate further about how their process works, such as how they are building a database of reference samples, and how consistent a microbial population remains across a given location.
As the technology grows more robust, though, one could imagine numerous other applications, like in police work and forensics. But today, Phylagen is solely focused on helping commercial entities bring greater transparency to their operations so they can root out unauthorized subcontracting.
Then those unethical suppliers can – shall we say – bite the dust.
A recent study in The Lancet Oncology showed that AI found 20 percent more cancers on mammogram screens than radiologists alone.
Published in The Lancet Oncology, the study analyzed the scans of 80,000 Swedish women with a moderate hereditary risk of breast cancer who had undergone a mammogram between April 2021 and July 2022. Half of these scans were read by AI and then a radiologist to double-check the findings. The second group of scans was read by two researchers without the help of AI. (Currently, the standard of care across Europe is to have two radiologists analyze a scan before diagnosing a patient with breast cancer.)
The study showed that the AI group detected cancer in 6 out of every 1,000 scans, while the radiologists detected cancer in 5 per 1,000 scans. In other words, AI found 20 percent more cancers than the highly-trained radiologists.
Scientists have been using MRI images (like the ones pictured here) to train artificial intelligence to detect cancers earlier and with more accuracy. Here, MIT's AI system, MIRAI, looks for patterns in a patient's mammograms to detect breast cancer earlier than ever before. news.mit.edu
But even though the AI was better able to pinpoint cancer on an image, it doesn’t mean radiologists will soon be out of a job. Dr. Laura Heacock, a breast radiologist at NYU, said in an interview with CNN that radiologists do much more than simply screening mammograms, and that even well-trained technology can make errors. “These tools work best when paired with highly-trained radiologists who make the final call on your mammogram. Think of it as a tool like a stethoscope for a cardiologist.”
AI is still an emerging technology, but more and more doctors are using them to detect different cancers. For example, researchers at MIT have developed a program called MIRAI, which looks at patterns in patient mammograms across a series of scans and uses an algorithm to model a patient's risk of developing breast cancer over time. The program was "trained" with more than 200,000 breast imaging scans from Massachusetts General Hospital and has been tested on over 100,000 women in different hospitals across the world. According to MIT, MIRAI "has been shown to be more accurate in predicting the risk for developing breast cancer in the short term (over a 3-year period) compared to traditional tools." It has also been able to detect breast cancer up to five years before a patient receives a diagnosis.
The challenges for cancer-detecting AI tools now is not just accuracy. AI tools are also being challenged to perform consistently well across different ages, races, and breast density profiles, particularly given the increased risks that different women face. For example, Black women are 42 percent more likely than white women to die from breast cancer, despite having nearly the same rates of breast cancer as white women. Recently, an FDA-approved AI device for screening breast cancer has come under fire for wrongly detecting cancer in Black patients significantly more often than white patients.
As AI technology improves, radiologists will be able to accurately scan a more diverse set of patients at a larger volume than ever before, potentially saving more lives than ever.