Using AI to improve cancer diagnosis through better explanations
Official title: SCH: Counterfactual Explanations for AI-Assisted Cancer Diagnosis and Subtypiing
Funded at Rutgers, the State Univ of N.j. · NIH-11060758 · Data updated 2026-11-12
This study is working on making cancer diagnoses more accurate by using smart computer models that can explain their predictions about tissue samples, helping doctors understand why a tumor might be considered aggressive or not, so they can make better treatment choices.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Rutgers, the State Univ of N.j. NIH-funded |
| Lab location | 1 site (Piscataway, United States) |
| Project start | July 1, 2024 |
| Project end | June 30, 2028 |
| Funding year | 2024 |
| Award (this year) | $266,614 |
| NIH project number | 1R01CA297832-01 |
| Project ID | NIH-11060758 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are patients diagnosed with head and neck squamous cell carcinoma (HNSCC) who are undergoing histopathological evaluation.
✕Less likely to help
Patients with cancers that are not related to head and neck squamous cell carcinoma may not benefit from this research.
What this research studies
This research focuses on enhancing the accuracy of cancer diagnoses by developing AI models that can explain their predictions for histopathological images. It aims to create a framework that uses counterfactual explanations, allowing pathologists to understand how different features in tissue samples could influence the diagnosis of tumors. By generating explanations that clarify why a model predicts a tumor as aggressive or non-aggressive, the project seeks to improve the interpretability of AI tools in clinical settings. This could lead to more informed treatment decisions based on AI-assisted evaluations.
Why it matters
Potential benefit: If successful, this research could lead to more accurate and interpretable cancer diagnoses, ultimately improving patient outcomes.
How similar studies have gone: Other research has shown promise in using AI for medical imaging, but the specific approach of counterfactual explanations in histopathology is relatively novel.
Where this research is happening
-
Rutgers, the State Univ of N.j.
Piscataway, United States Active
Researchers
- Principal investigator: Wang, Hao — Rutgers, the State Univ of N.j.
- Study coordinator: Wang, Hao
Related research
Other NIH-funded projects on the same topics.
-
Causes and consequences of intra-genomic coevolution
Scientists are studying how repetitive DNA in human cells interacts with proteins to impact genome health, fertility, and cellular functions.
-
How BRAF changes spark serrated colon cancer, from stem cells
This project studies how a BRAF mutation affects colon stem cells to understand what triggers serrated colon cancer.
-
Understanding how copper affects staph bacteria to fight infections
Scientists are studying how copper ions change the proteins inside Staphylococcus aureus to find new ways to treat resistant infections.
-
Sensory guidance of how diet affects healthy aging
Researchers will study how the way we experience food and our senses influence aging, using fruit-fly models to mirror human dietary choices.
-
Non-Invasive AI-Enhanced Neonatal Blood Pressure Monitoring in NICUs
A new AI-powered system uses the baby’s existing sensors to continuously track blood pressure in the NICU without invasive procedures, helping clinicians spot problems early.
-
How the brain drives overeating and weight loss with GLP-1 medications
Scientists are studying how brain circuits that control food seeking respond to obesity and weight loss with a GLP-1 drug, to understand why weight loss often doesn’t hold.
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.