Application

Uses AI analysis of immune cells in pathology images to predict cancer prognosis and support personalized treatment decisions.

Key Benefits

• Quantifies immune cell characteristics from pathology images to provide objective prognostic information.
• Captures both immune cell abundance and spatial relationships within the tumor microenvironment.
• May improve patient risk stratification and treatment planning using routinely acquired pathology data.

Market Summary

The immune microenvironment plays a critical role in cancer progression, treatment response, and patient outcomes. However, accurately assessing immune cell populations within tumors remains challenging using conventional pathology review alone. Current evaluation methods often rely on subjective interpretation and may not fully capture complex spatial relationships among immune cells. As immunotherapies and precision oncology approaches continue to expand, there is a growing need for objective, scalable tools that can characterize the tumor immune landscape and generate clinically meaningful prognostic information. Technologies that can extract deeper insights from existing pathology images may improve patient stratification while reducing the need for additional testing.

Technical Summary

Researchers at Emory University have developed an artificial intelligence-based approach that analyzes immune cells identified in immunohistochemistry (IHC)-based pathology images. The technology extracts quantitative immune cell features, including measures of immune cell density and spatial organization within the tumor microenvironment, and uses these features to generate prognostic assessments for cancer patients. Machine learning models evaluate these immune characteristics to identify patients at different levels of risk and potentially predict clinical outcomes. Unlike traditional pathology assessments, the proposed approach provides an objective and reproducible evaluation of the tumor immune landscape using digital image analysis.

Development Stage

Proof-of-concept demonstrated using retrospective pathology image datasets.

Publication

• Bharadwaj S, Corredor G, Al-Shakhshir H, Medina S, Almahfouz SN, Dhamdhere R, Pathak T, Fu P, Liu Y, Gandhi S, Badve S, Madabhushi A, “Computationally derived spatial immune signature identifies trastuzumab responders in HER2+ breast cancer: NSABP B-41 clinical trial validation”, Clin Cancer Res. 2026 Mar 31. doi: 10.1158/1078-0432.CCR-25-4185. Online ahead of print. (PMID: 41915435).
• Aggarwal, A., Jana, M., Singh, A., Dam, T., Maurya, H., Pathak, T., Orsulic, S., Yang, K., Chute, D., Bishop, J. A., Faraji, F., Thorstad, W. M., Koyfman, S., Steward, S., Shi, Q., Sandulache, V., Saba, N. F., Lewis, J. S. Jr., Corredor, G., & Madabhushi, A, ”Artificial Intelligence-Based Virtual Staining Platform for Identifying Tumor-Associated Macrophages from Hematoxylin and Eosin-Stained Images”, Eur J Cancer. 2025 Mar 26;220:115390. doi: 10.1016/j.ejca.2025.115390. Online ahead of print. (PMID: 40158294).