Tiny magnetic bots that are activated by light can clear bacterial infections deep in the sinus cavities, then be expelled by blowing out the nose.

A new study published in Science Robotics unveiled copper single–atom–doped bismuth oxoiodide microbots, each smaller than a grain of salt, that can be tracked and guided to the location of infection via X-ray imaging, thus providing a precise, minimally invasive therapeutic strategy for managing sinusitis clinically.

Sinusitis is a common respiratory condition often linked to biofilm produced by bacteria like Streptococcus pyogenes. This condition causes inflammation of the sinus lining and leads to symptoms such as nasal congestion, reduced sense of smell, facial pain, and, in some dire cases, even memory impairment.

Microsoft says it has developed an AI system that creates a ‘path to medical superintelligence’ that can deal with ‘diagnostically complex and intellectually demanding’ cases and diagnose disease four times more accurately than a panel of human doctors.

[ https://microsoft.ai/wp-content/uploads/2025/06/MAI-Dx-Orche…0x1498.jpg https://microsoft.ai/new/the-path-to-medical-superintelligence/

[ https://arxiv.org/abs/2506.22405](https://arxiv.org/abs/2506.

“Benchmarked against real-world case records published each week in the New England Journal of Medicine, we show that the Microsoft AI Diagnostic Orchestrator (MAI-DxO) correctly diagnoses up to 85% of NEJM case proceedings, a rate more than four times higher than a group of experienced physicians. MAI-DxO also gets to the correct diagnosis more cost-effectively than physicians.”

AI that thinks like a doctor: a new era in medical diagnosis.

Imagine walking into a doctor’s office with a strange set of symptoms. Rather than jumping to conclusions, the doctor carefully asks questions, orders tests, and adjusts their thinking at every step based on what they learn. This back-and-forth process—called sequential diagnosis—is what real-world medicine is all about. But most AI systems haven’t been tested this way. Until now.

A new benchmark called Sequential Diagnosis is flipping the script.

In radiation therapy, precision can save lives. Oncologists must carefully map the size and location of a tumor before delivering high-dose radiation to destroy cancer cells while sparing healthy tissue. But this process, called tumor segmentation, is still done manually, takes time, varies between doctors—and can lead to critical tumor areas being overlooked.

Now, a team of Northwestern Medicine scientists has developed an AI tool called iSeg that not only matches doctors in accurately outlining lung tumors on CT scans but can also identify areas that some doctors may miss, reports a large new study.

Unlike earlier AI tools that focused on static images, iSeg is the first 3D deep learning tool shown to segment tumors as they move with each breath—a critical factor in planning radiation treatment, which half of all cancer patients in the U.S. receive during their illness.