01
Cancer-type specific views
Breast, lung, colorectal, melanoma, prostate, glioblastoma and hematologic disease are separated so the biology and research questions do not blur together.
Oncology research intelligence
Separate the cancer biology. Keep the evidence visible.
PIRIA is being designed to organize oncology evidence by cancer type, research question and translational relevance. The aim is not to replace scientists or clinicians, but to make hard evidence easier to compare, inspect and use.
What this site now covers
A stronger, more specific view of AI in oncology.
This version of PIRIA separates major cancer areas, summarizes where AI has already shown practical benefit, and tracks current scientific signals through recent peer-reviewed literature.
02
Clinical impact without overclaiming
Where AI has already shown practical success, the site explains the use case clearly—such as radiotherapy contouring, planning efficiency, biomarker analysis and treatment-response prediction.
03
Recent evidence
The research sections are updated around 2026 literature on multi-omics, spatial biology, liquid biopsy, target identification and translational validation.
Research structure
One platform. Multiple oncology workflows.
PIRIA is being developed around evidence synthesis, target landscape review, translational scanning and question-specific briefs. The workflow starts with a cancer area and ends with an inspectable research view.
Cancer-type modulesTarget prioritizationMulti-omics contextHuman review
Cancer areas
Start with the disease context.
The biology, treatment questions and data modalities differ substantially across tumor types. PIRIA therefore organizes work by disease area instead of presenting oncology as one generic problem.
Breast cancer
Focus on pathology AI, response prediction, biomarker inference and immune context in subtypes such as TNBC.
Lung cancer
Focus on radiotherapy planning, imaging-derived risk assessment, liquid biopsy signals and treatment-selection support.
Colorectal cancer
Focus on pathway stratification, response heterogeneity and emerging spatial biology workflows.
Prostate cancer
Focus on imaging, radiotherapy contouring and workflow efficiency where AI has already shown measurable operational benefit.
Where AI is already helping
Useful outcomes are often operational before they are curative.
The most mature successes are not “AI cures cancer”. They are clinically useful improvements in planning, contouring, pathology analysis, biomarker quantification and patient stratification.
Radiotherapy workflows
Multi-centre real-world studies in 2026 continue to show that AI-assisted contouring can save time while maintaining clinically acceptable quality in treatment-planning workflows.
Pathology and biomarkers
AI models are showing practical value in histopathology classification, biomarker inference and standardized quantification of features such as tumor infiltrating lymphocytes.
Response prediction
In selected settings, imaging-based AI models can help predict who is more likely to respond to a given treatment pathway, supporting better upstream decision-making.
PIRIA direction
Build around evidence, not hype.
PIRIA is interested in real oncology workflows: target review, study intelligence, biomarker context, treatment-planning support and structured evidence synthesis across major cancer areas.