Patented AI technology improves bruise detection across all skin tones
Can new technology make it easier to understand bruises? That's the question researchers at George Mason University's Injury Analytics Lab (IAL) are answering with a patented technology that combines artificial intelligence, advanced imaging and clinical data to give clinicians, forensic professionals and researchers better information about skin injuries.
Researchers at George Mason University's Injury Analytics Lab have developed a patented AI technology that enhances bruise detection across various skin tones. This innovative system merges artificial intelligence, high-resolution imaging, and clinical data to offer clinicians, forensic professionals, and researchers more comprehensive information about skin injuries.
By combining visual data with factors such as medical history, demographics, and skin color, the technology can account for elements that influence injury appearance, leading to more precise and reliable assessments compared to traditional visual evaluations alone.
One of the key features of this patented technology is its ability to adapt imaging conditions, tailoring light wavelengths and camera filters to each individual's skin tone. This ensures optimal capture of injury evidence, especially important for those with darker skin tones, whose bruises can be harder to detect with standard imaging setups. The system also estimates characteristics of bruises, such as age, size, color, and shape, while providing confidence levels for its predictions.
Developed through a collaborative effort involving experts in nursing, health informatics, and engineering, the technology's foundation rests on a large repository of over 100,000 injury images and electronic health records. This extensive dataset trains the system's deep-learning models, enabling it to recognize patterns that might be difficult for the human eye to identify consistently.
The patent marks a significant milestone in the lab's mission to create evidence-based technologies that improve injury assessment and documentation, with the potential to reduce disparities in how injuries are documented and evaluated across diverse skin tones.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
