Cancer research
AI in Cancer Research
- 6 studies cited
- Cancer research
- Evidence: 1 high-evidence · 5 medium
This article is AI-assisted and human-reviewed. Drafts are generated from peer-reviewed research and checked before publishing. See our methodology.
Cancer research is using AI to look for patterns in images, genes, tissue samples, and study records. These tools may help researchers sort large amounts of cancer data faster and more carefully. The work is still early, but it shows hopeful ways AI could support future cancer research.
Prostate Cancer imaging patterns
A review in Abdominal Radiology looked at many studies of AI on MRI scans for Significant Prostate Cancer. Across the studies, AI classified cancer on MRI with good accuracy. This suggests AI may help researchers study image patterns that are hard to measure by hand.
Another study in Journal of Clinical Oncology looked at Localized Prostate Cancer. It found that AI information and a 22-gene test together were better at predicting the risk that Prostate Cancer might spread.
Pancreatic Cancer survival clues
A study in Discover Oncology used AI to help build a tool for Pancreatic Ductal Adenocarcinoma. The tool was made to better predict survival by studying cell death patterns and related pathways. This kind of work may help researchers understand why some tumors behave differently from others.
Bladder Cancer tissue markers
A study in World Journal of Surgical Oncology combined different kinds of data and checked results in clinical samples. AI helped point to CKAP2 as a strong marker linked with Bladder Cancer in tissue samples. Markers like this may give researchers new clues about how Bladder Cancer appears in the body.
Cancer trial matching data
A Journal of Clinical Oncology study used AI to quickly organize cancer data for Oncology Clinical Trial Enrollment. The goal was to help match patient records with trial rules across different countries, reading levels, and resource settings. This may help researchers make trial matching more open and easier to scale.
What this does not prove yet
This research does not prove that AI can find every cancer, predict every outcome, or replace a health care team. These studies also do not show that the same tools will work equally well in every hospital, scanner, lab, or patient group. More testing is needed before these tools can be trusted widely in real-world care.
Sources
- Deep learning classification of significant prostate cancer on MRI: a systematic review and meta-analysis. — Abdominal radiology (New York)
- Structure-Aware Hierarchical Sha-256 Hashing for Dicom Integrity Verification in Consortium Blockchain Systems — Journal of Artificial Intelligence and Technology
- Elucidating the pathway activity and prognostic significance of diverse regulatory cell death patterns in pancreatic ductal adenocarcinoma. — Discover oncology
- Multi-omics integration and clinical validation identify CKAP2 as a diagnostic biomarker for bladder cancer. — World journal of surgical oncology
- Assessing the clinical and biological associations between multimodal artificial intelligence (MMAI) and 22-gene genomic classifier (GC) in localized prostate cancer (PCa). — Journal of Clinical Oncology
- Expanding global access to oncology trials: mCODE-aligned AI for inclusive patient matching across literacy and resource settings. — Journal of Clinical Oncology
Keep exploring
Medical disclaimer: This content is for informational purposes only and does not constitute medical advice, diagnosis, or treatment. Always consult a qualified healthcare professional.
Published June 29, 2026
Last updated June 29, 2026