Researchers have developed an artificial intelligence (AI) tool that could help identify patients at greater risk of recurrent bowel cancer, potentially enabling earlier life-saving treatment.
The AI algorithm, called SEMIL (Semantically-Enhanced Multiple Instance Learning), analyzes routine pathology slides using both images and written descriptions to assess tumour growth patterns associated with cancer recurrence, according to a statement released Wednesday by Australia's La Trobe University.
Researchers analyzed more than 1,600 pathology slides and validated the findings across 1,220 stage-two bowel cancer patients in three independent cohorts from multiple Australian institutions. Bowel cancer is the third most common cancer worldwide.
The study, published in the journal Gastroenterology, found that when AI-based assessments and pathologists' evaluations aligned, they produced the most accurate predictions of relapse risk.
Lead author Francis Magisson from La Trobe University said the technology could help identify which stage-two cancer patients are at higher risk of relapse and may need closer monitoring or additional treatment such as chemotherapy. Current Australian clinical guidelines recommend chemotherapy after surgery only for patients considered at high risk of recurrence.
The research highlighted the growing role of AI in supporting precision medicine, the researchers said, adding the tool could be "integrated into existing digital pathology workflows without requiring expensive new tests or tissue samples to provide more consistent and objective assessments of cancer pathology."
