Forensic anthropologists at MSU have developed an innovative AI-driven system to significantly accelerate and enhance human identification using chest radiographs. The research is the first to assess how different regions of interest within radiographs can be used for human identification in forensic contexts.
This research could also be used in unidentified or missing person databases to propose potential matches for consideration which helps reduce practitioner bias.
“There has not been this type of application previously,” said Dr. Carolyn Isaac, director of the MSU Forensic Anthropology Lab, “so it is showing the computer science world how forensics uses radiographs differently than the medical field, which primarily uses them to diagnose disease.”
