Making AI Explanations for Cancer Diagnosis Clearer

SCH: Counterfactual Explanations for AI-Assisted Cancer Diagnosis and Subtypiing

NIH-funded research Rutgers, the State Univ of N.j. · NIH-11128769

This project aims to create new ways for artificial intelligence to explain its decisions when helping doctors diagnose different types of cancer from tissue images.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionRutgers, the State Univ of N.j. NIH-funded
Lab location1 site (Piscataway, United States)
Project IDNIH-11128769 on NIH RePORTER

What this research studies

Doctors rely on tissue samples to accurately diagnose cancer and guide treatment. Artificial intelligence (AI) models are very good at classifying tumors from these images, sometimes even using genetic information. However, it's hard for doctors to understand *why* the AI makes a certain diagnosis, which limits its usefulness. This project is developing a special framework to help AI models explain their cancer diagnoses in a clear way. By asking "what if" questions, like "what would the image need to look like for the AI to predict a different tumor type," the AI can better show its reasoning to pathologists. This will help doctors trust and use AI more effectively in cancer care.

Who could benefit from this research

Good fit: Patients who have received or will receive a cancer diagnosis based on tissue samples could potentially benefit from the improved diagnostic accuracy and clarity this research aims to provide.

Not a fit: Patients whose conditions do not involve cancer diagnosis from histopathological images would not directly benefit from this specific AI explanation tool.

Why it matters

Potential benefit: If successful, this work could lead to more accurate and understandable AI tools for cancer diagnosis, helping doctors make better treatment decisions for patients.

How similar studies have performed: While AI models show promise in cancer diagnosis, developing systematic and interpretable explanation methods for these complex models, especially for textural images, is a novel and ongoing area of research.

Where this research is happening

Piscataway, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.