Digital pathology relies on high-resolution imaging for accurate cancer diagnosis, yet high-magnification systems remain slow and costly for large-scale screening. Meanwhile, standard AI super-resolution often generates hallucinated cellular artifacts that risk diagnostic accuracy. To overcome this, researchers developed a hybrid bright-dark field computational framework using fast LED illumination to provide physical guidance. This physics-guided approach doubles spatial resolution, reduces reconstruction artifacts by 84%, and boosts AI cancer screening sensitivity by 11.14%.

Untangling the meta-biomaterial puzzle one property at a time

From repairing damaged tissues to developing better implants, many medical developments depend on materials that can mimic the complex properties of human tissue. Meta-biomaterials are among the most promising candidates. By tailoring their geometry, researchers can create materials with properties similar to those of natural tissues. But there is a catch: changing one property often changes several others at the same time. TU Delft scientists have now developed a method to decouple these properties. Their work, published in Nature Communications, helps to understand how individual material properties influence cell behaviour and could accelerate the development of next-generation biomaterials.

Researchers developed WiFo-2, a wireless foundation model for heterogeneous future wireless systems. Pretrained on 11.6 billion CSI points, it surpassed fully supervised task-specific models in three zero-shot reconstruction tasks and used 1% of labeled data for nine downstream tasks. Its confidence estimates support reliable operation. A prototype validated three tasks across indoor and outdoor scenarios and bands spanning sub-6 GHz and millimeter-wave.

Researchers at The University of Manchester have developed a physics-based artificial intelligence framework that, for the first time, enables global-scale predictions of dissolved organic carbon cycling between seawater and marine sediments. The approach reveals a previously unquantified component of Earth's carbon cycle and could improve climate models, support research into ocean-based climate mitigation strategies, and provide new insights into the long-term storage of carbon in marine environments.

The smell of Japanese Igusa (rush grass), the core component of tatami mats, has long been associated with comfort and relaxation. However, there was little scientific evidence behind such claims. To test this, researchers measured the brain activity of volunteers while they sat on Igusa mats and completed simple tasks. The researchers found that when using the Igusa mats the participants’ brain activity suggested they had better focus, cognitive engagement, and stress resilience.