Newsroom

As AI is deployed in clinical centers across the U.S., one important consideration is to assure that models are fair and perform equally across patient groups and populations. To better understand the fairness of medical imaging AI, researchers trained over 3,000 models spanning multiple model configurations, algorithms, and clinical tasks. Their analysis of these models reinforced some previous findings about bias in AI algorithms and uncovered new insights about deployment of models in diverse settings.

Cancer cells frequently overhaul their surroundings, making tumors stiffer than nearby healthy tissue. While tumor stiffening makes some cancers easier to detect, it can also ramp up drug resistance. New research suggests that these detrimental changes are not set in stone, however.

A team of researchers funded by a NIBIB Small Business program grant developed a new ultrasound navigation system that could provide accurate, real-time, and intuitive needle insertion planning and guidance for lumbar puncture procedures.

NIH has just awarded $17 million for a group of projects undertaken by small and mid-sized businesses, nonprofit organizations, and academia participating in the Blueprint MedTech program.

Early detection of respiratory diseases is critical for treatment. Researchers at the Georgia Institute of Technology have developed a wearable lung patch which, in a pilot study, detected wheezing, a common indicator of asthma and COPD.

Physical human feats require a high level of coordination between sensory and motor functions. What kind of achievements could robots perform with the same cohesion between sensing and action? In the medical space, researchers have begun to explore the possibilities.

A team of NIBIB-funded researchers recently developed an AI platform that can analyze 3D pathology images to predict disease outcomes. Their method had improved performance in predicting prostate cancer outcomes when compared with traditional pathology approaches, such as analysis by expert pathologists using 2D images.

Due to its high accuracy, lab-based PCR testing is the gold standard for infectious disease diagnostics. Yet PCR's availability is limited, especially in low-resource settings. New research suggests a new kind of test could be more streamlined without sacrificing performance.

Researchers have established an RNA-based method that drives cells in the body to produce therapeutic proteins and secrete them into the bloodstream. The approach could extend the lifespan of drugs in the body, reducing the burden on patients.