Researchers at Mayo Clinic have found that artificial intelligence (AI)-enabled analysis of routine pathology slides may help identify pancreatic cancer patients who face a higher risk of disease recurrence following treatment and surgery.
The study, published in Clinical Cancer Research, examined tissue samples from 203 patients with pancreatic ductal adenocarcinoma who received chemotherapy before surgery but showed limited treatment response. Using an AI-enabled digital pathology platform, researchers analyzed how residual cancer cells and surrounding stromal tissue were distributed within the samples.
The findings suggest that the organization and spatial pattern of residual cancer may provide important information beyond the amount of cancer remaining. Patients whose cancer showed more fragmented and intermixed patterns with surrounding tissue experienced earlier recurrence.
“Current pathology assessments largely tell us how much tumor is left after treatment. We wanted to know whether the geography of that remaining cancer could reveal additional biology about recurrence risk,” says Ryan Carr, M.D., Ph.D., a Mayo Clinic oncologist and senior author of the study.
Two spatial signatures were associated with shorter disease-free survival, with high-risk groups showing substantially higher adjusted risks of recurrence even after accounting for established clinical factors such as cancer stage and lymph node status.
Also read: UAE Healthcare Giant Expands UK Reach with New Laboratory Network
The analysis also identified differences in immune-cell distribution within high-risk tumors, highlighting the potential role of the tumor microenvironment in treatment resistance and recurrence.
Researchers say the approach could eventually provide additional information for personalized surveillance and treatment planning using pathology slides already collected during routine care. However, prospective studies are needed before the technology can be applied to clinical decision-making.
