AI and x-ray technology enable scientists to virtually read previously unreadable, carbonized Roman scrolls from Herculaneum.
Key Details
- 1Researchers used x-ray tomography and AI to virtually unroll and read ancient scrolls carbonized by Mt. Vesuvius in 79 CE.
- 2Discovery of lead in some ink enhances the ability of x-rays to distinguish text from papyrus.
- 3Scientists recreated carbonized scrolls with various lead concentrations to test imaging protocols.
- 4X-ray fluorescence and custom software successfully detected and deciphered lead-based writing in experimental scrolls.
- 5The method could improve unrolling algorithms by providing known controls for AI training.
- 6Findings published in PLOS One, September 2026.
Why It Matters
This method demonstrates the potential for advanced imaging and AI to recover lost historical texts, showcasing a novel application of radiology tools. The study bridges heritage science and imaging AI, offering new avenues for both fields.
Source
EurekAlert
Related News
•EurekAlert
UVA's $4M NIH Grant Backs AI to Optimize Cardiac MRI Therapies
UVA secures $4 million NIH funding to develop GenStrain, an AI model using MRI data to personalize cardiac pacing therapies.
•EurekAlert
Machine Learning Models Predict Cancer Risk with Routine Health Data
Researchers developed machine learning models using routinely collected health data to predict individual risk for 20 common cancers, outperforming traditional methods for several cancer types.
•EurekAlert
Duke Receives $25M to Lead National Trustworthy AI Hub for Dementia and Aging
Duke University has launched a $25 million national center to make AI for aging and dementia clinically robust and trustworthy.