PIRIA
Cancer Areas

Separate the disease area. Clarify the research problem.

Each cancer type has different biology, treatment logic, data sources and clinically relevant AI use cases.

Illustration for breast cancer

Breast cancer

Important themes include subtype-specific pathology, treatment-response prediction, biomarker inference and immune microenvironment analysis in TNBC.

  • Histopathology classification and biomarker enrichment
  • Prediction of neoadjuvant response from MRI
  • AI-based quantification of TILs in TNBC
Examples on the Clinical Impact page include a 2026 MRI-based response model and a 2026 independent validation study of AI-based TIL quantification.
Illustration for lung cancer

Lung cancer

Lung oncology benefits from imaging-rich workflows. AI is especially relevant in planning support, case retrieval, lesion characterization and response assessment.

  • SABR planning assistance
  • Imaging-based workflow support
  • Potential links to smart patient retrieval in precision oncology
Illustration for colorectal cancer

Colorectal cancer

Useful directions include molecular stratification, drug-target context, response heterogeneity and microenvironment mapping with spatial tools.

  • Pathway-level target context
  • Spatial biology and microenvironment analysis
  • Potential patient-stratification workflows
Illustration for melanoma

Melanoma

Melanoma is important for immune-oncology work, especially around response heterogeneity, immune context and longitudinal monitoring.

  • Immunotherapy-response context
  • Longitudinal monitoring signals
  • Spatial and immune microenvironment questions
Illustration for prostate cancer

Prostate cancer

Radiotherapy is one of the clearest operational AI success areas in prostate cancer, particularly in auto-contouring and planning workflows.

  • Organ-at-risk contouring
  • Planning efficiency
  • Workflow standardization in radiotherapy
Illustration for glioblastoma

Glioblastoma and brain tumors

Key needs include imaging interpretation, response assessment and translational target intelligence in a disease area with high unmet need.

  • Imaging-driven analysis
  • Response assessment challenges
  • Integration of molecular and radiologic context
Illustration for hematologic malignancies

Hematologic malignancies

Data-rich hematology settings are relevant for response prediction, biomarker correlation and precision stratification.

  • Molecular classification
  • Longitudinal response monitoring
  • Data integration across assays
These cancer-area summaries are meant to organize PIRIA’s product and research direction. They are not claims that all listed workflows are already deployed by PIRIA in clinical practice.