AI that combines scans, pathology slides, and records to guide post-surgery treatment for colorectal cancer
Multi-modal machine learning to guide adjuvant therapy in surgically resectable colorectal cancer
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 ID | NIH-11319803 on NIH RePORTER |
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.
Who could benefit from this research
Good fit: 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.
Not a fit: 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.
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 performed: 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, United States
- Stanford University — Stanford, United States (Active)
Researchers
- Principal investigator: Shen, Jeanne — Stanford University
- Study coordinator: Shen, Jeanne
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 below.