Scientists in Australia have developed an artificial intelligence (AI) screening tool, giving pathologists “super vision” to detect hidden cancer markers in routine tissue samples.
Researchers at Australia’s QIMR (Queensland Institute of Medical Research) Berghofer Medical Research Institute showed how the machine learning tool, STimage, used spatial biology analysis to accurately predict breast, skin and kidney cancers and a liver immune disease, while also assessing prognosis and treatment response, said a QIMR Berghofer statement released Wednesday.
The study, published in Nature Communications, found the tool was reliable, low-cost and rapidly generated results that were easy for pathologists to interpret, the statement said.
The breakthrough could usher in a new era of digital pathology and precision medicine, enabling faster and more accurate diagnoses, personalized treatments and improved access to specialist care in remote areas, it said.
“It’s like giving pathologists the super resolution vision of Superman or Superwoman to scan millions of invisible biomarkers in a tiny tissue sample to find the two or three that are showing signs of cancer,” said QIMR Berghofer Associate Professor Quan Nguyen, who led development of the tool.
“It makes a diagnostic prediction and mathematically computes the level of certainty about the result,” Nguyen said, adding the tool is designed to assist, not replace, pathologists, and could provide “extra information about cell types and genetic activity that they can’t see with their own eyes.”
Spatial biology provides insights not accessible through standard pathology, the team said, hoping the STimage tool could be part of clinical practice within two years.
