AI that combines scans, pathology slides, and records to guide post-surgery treatment for colorectal cancer
Official title: Multi-modal machine learning to guide adjuvant therapy in surgically resectable colorectal cancer
Funded at Stanford University · NIH-11319803 · Data updated 2026-11-12
This project uses artificial intelligence to combine CT/MRI scans, pathology slides, and medical records to help doctors decide which people with stage I–III colorectal cancer should get additional treatment after surgery.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Stanford University NIH-funded |
| Lab location | 1 site (Stanford, United States) |
| Project start | May 2, 2023 |
| Project end | April 30, 2028 |
| Funding year | 2026 |
| Award (this year) | $644,202 |
| NIH project number | 5R01CA270437-04 |
| Project ID | NIH-11319803 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for related future studies are people with surgically resected stage I–III colorectal cancer who have available preoperative CT/MRI images, pathology slides, and medical-record data.
✕Less likely to help
Patients with metastatic (stage IV) colorectal cancer, those without available imaging or pathology records, or people with non-colorectal cancers are unlikely to benefit directly from this project.
What this research studies
Researchers will assemble a large, expert-annotated collection of de-identified pathology whole-slide images, preoperative CT and MRI scans, and structured medical-record data from patients with surgically resectable (stage I–III) colorectal cancer. They will train deep-learning models that use each data type alone and together to predict the risk of cancer coming back after surgery and who might benefit from adjuvant therapy. The team will create and share a public multimodal dataset to speed future research and compare the AI-based risk sorting with current clinical methods. Participation would typically involve sharing existing scans, pathology material, and medical-record information rather than undergoing extra procedures.
Why it matters
Potential benefit: If successful, this work could more accurately identify patients who truly need adjuvant chemotherapy and spare low-risk patients from unnecessary treatment.
How similar studies have gone: AI approaches in pathology and radiology have shown promise for prognosis, but integrating pathology, imaging, and EMR data specifically to guide adjuvant therapy in colorectal cancer is relatively new and still being tested.
Where this research is happening
-
Stanford University
Stanford, United States Active
Researchers
- Principal investigator: Shen, Jeanne — Stanford University
- Study coordinator: Shen, Jeanne
Related research
Other NIH-funded projects on the same topics.
-
Using machine learning to improve treatment decisions for colorectal cancer patients after surgery
This study is looking to improve treatment decisions for patients with colorectal cancer who have had surgery by using smart computer technology to analyze their medical information and images, helping doctors find out who might need extra therapy to prevent the cancer from coming back.
-
Improving colorectal cancer screening and follow-up care.
This study is working to help more people get screened for colorectal cancer and receive the follow-up care they need, especially those who haven't been screened much before, so that everyone can have better access to important health checks and improve their overall health.
-
Colorectal cancer prognosis through a broad, collaborative study
A large, multi-center study follows people newly diagnosed with colorectal cancer to find biomarkers and patterns that predict outcomes and guide future care.
-
Ceramides and how they affect metabolism and colorectal cancer in adults
A study in adults with obesity-related health issues will explore how a fat-related molecule called ceramide influences metabolic problems and colorectal cancer risk.
-
Automated point-of-care DNA methylation test for colorectal cancer in LMICs
A fast, affordable blood test using DNA markers to help identify people at higher risk of colorectal cancer in low- and middle-income countries.
-
Rewiring Colorectal Cancer to Harness Therapeutic Hyperactivation
A Yale team is exploring brain-storming new ways to treat colorectal cancer by safely boosting certain cancer signaling pathways to kill cancer cells and by reshaping cancer cell states to improve responses to existing therapies.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.