SYDNEY, Sept. 4 (Xinhua) -- Researchers in Australia are developing an artificial intelligence (AI) algorithm that estimates dangerous hidden fat, or visceral fat, from bone density scans used to detect spine fractures.
Visceral fat, the harmful deep belly fat that surrounds organs, is a "troublemaker" strongly linked to serious health problems like heart disease, diabetes and cancer, according to a statement released Thursday by Australia's Edith Cowan University (ECU).
The ECU team is training its machine learning algorithm to analyze lateral spine Dual-energy X-ray Absorptiometry (DXA) scans, used to assess bone density, to accurately predict visceral fat levels from these images, offering valuable new health insights without requiring additional tests.
Current methods to estimate visceral fat, like body mass index, waist circumference, and waist-to-hip ratio, have limitations as they cannot distinguish between different types of body fat, leading to inconsistent obesity assessments, researchers said.
Imaging techniques such as MRI and CT provide accurate visceral fat measurement but are costly and, in the case of CT, expose patients to higher radiation, they said.
"The machine-learning model has been trained on thousands of images; the next step is to incorporate further datasets from around the world, so it learns from the largest, most diverse cohort possible and becomes as effective as possible," said Syed Zulqarnain Gilani, a senior lecturer and lead AI scientist at ECU. Enditem
京公网安备 11010802027341号