A group of Japanese researchers has announced that it has developed a deep-learning model to predict the cancer onset risk from fatty liver images.

The team, led by the University of Tokyo, created the model by using some of digital images of fatty liver tissues collected from 46 people who developed liver cancer within seven years of biopsy and 639 others who did not.

For the artificial intelligence application project, the researchers gathered such images from a total of 2,432 people who had undergone the live tissue examination at nine medical institutions in the country.

The model has proved that it can predict cancer onset risk with 82.3% accuracy, which compares with 78.2% for biopsy-based manual analyses, the researchers said.

They also saw AI judge cell dysplasia and declining fat deposition despite the progression of fatty liver as cancer risk factors and predict a high probability of mild fibrosis developing into cancer.

"It's also possible to create deep-learning models to predict cancer development from images gathered through stomach and intestine mucosa biopsies," said group member Ryosuke Tateishi, associate professor at the university's Graduate School of Medicine.

The team's research paper has been released in the online edition of Journal of Hepatology, a dedicated U.S. medical magazine.