TechCrunch reporter Kylie Wiggers spotlights the SmartEM project by researchers from MIT and Harvard, which is aimed at enhancing lab work using, “a computer vision system and ML control system inside a scanning electron microscope” to examine a specimen intelligently. “It can avoid areas of low importance, focus on interesting or clear ones, and do smart labeling of the resulting image as well,” writes Wiggers.
Research scientist Nataliya Kosmyna speaks with The World host Chris Harland-Dunaway about the science behind using non-invasive brain scans and artificial intelligence to understand people’s different thoughts and mental images.
Graduate student Sarah Gurev and her colleagues have developed a new AI system named EVEscape that can, “predict alterations likely to occur to viruses as they evolve,” reports Erin Prater for Fortune. Gurev says that with the amount of data the system has amassed, it “can make surprisingly accurate predications.”
A study by researchers from MIT and Harvard examined the potential impact of the use of AI technologies on the field of radiology, reports Laura Landro for The Wall Street Journal. “Both AI models and radiologists have their own unique strengths and areas for improvement,” says Prof. Nikhil Agarwal.
7 News spotlights how MIT researchers have developed a new implantable device that could provide diabetes patients with insulin without using injections. “What we’ve been able to show is that with a minimally invasive implant that is sitting just under the skin, we’ve actually been able to sort of achieve a diabetic reversal,” explains Research Scientist Siddharth Krishnan.
Gizmodo reporter Ed Cara writes that MIT researchers have developed a new implantable device that can produce its own supply of insulin for up to a month. The team envisions that the device could “eventually be used for other medical conditions dependent on a regular supply of externally produced proteins, such as certain forms of anemia treated with erythropoietin,” writes Cara.
Prof. Regina Barzilay speaks with The Economist about how AI can help advance medicine in areas such as uncovering new drugs. With AI, “the type of questions that we will be asking will be very different from what we’re asking today,” says Barzilay.
MIT researchers have developed a new implant that in the future could be used to deliver insulin to patients for up to a month, potentially enabling patients to control diabetes without injections, reports Tony Ho Tran for the Daily Beast. In the future, the researchers hope to “develop a device for humans that would be roughly the size of a stick of gum,” writes Tran. “The implant could also be used to deliver things like drugs or proteins to help treat other diseases in humans as well.”
MIT researchers at MIT have developed a microfluidic chip-based model of liver tissue that “allows researchers to understand the biological mechanisms underlying liver tissue regeneration and points to several molecules that may promote the process,” reports William A. Haseltine for Forbes. "These results mark significant progress in our understanding of the human body’s regenerative properties," writes Haseltine.
Researchers from MIT and Massachusetts General Hospital have developed “Sybil,” an AI tool that can detect the risk of a patient developing lung cancer within six years, reports Mary Kekatos for ABC News. “Sybil was trained on low-dose chest computer tomography scans, which is recommended for those between ages 50 and 80 who either have a significant history of smoking or currently smoke,” explains Kekatos.
Institute Prof. Bob Langer speaks with Curiosity podcast hosts Immad Akhynd and Raj Suri about his work in the field of biotechnology, delving into how he has co-founded 40 companies. “I wanted to get out and do some good in the world,” says Langer. “That's where patents come in and that's where companies come in. And I think the challenge of the company is very different because you have what I call a platform technology.”
Prof. Regina Barzilay speaks with Nicole Estephan of WCVB-TV’s Chronicle about her work developing new AI systems that could be used to help diagnose breast and lung cancer before the cancers are detectable to the human eye.
Soledad O’Brien spotlights how researchers from MIT and Massachusetts General Hospital developed a new artificial intelligence tool, called Sybil, that an accurately predict a patient’s risk of developing lung cancer. “Sybil predicted with 86 to 94 percent accuracy whether a patient would develop lung cancer within a year,” says O’Brien.
Research from MIT and elsewhere have developed a mobile app that uses computer-vision techniques and AI to detect post-surgery signs of infection as part of an effort to help community workers in Kirehe, a district in Rwanda’s Eastern province, reports Shefali Malhotra for Science. “The researchers are now improving the app so it can be used across more diverse populations such as in Ghana and parts of South America,” writes Malhotra.
Researchers at MIT have developed a new nanoparticle sensor that can detect cancerous proteins through a simple urine test. “The researchers designed the tests to be done on a strip of paper, similar to the at-home COVID tests everyone became familiar with during the pandemic,” writes Lambert. “They hope to make it as affordable and accessible to as many patients as possible.”