# Artificial Intelligence driven prediction of brain metastasis from primary tumor sites at diagnosis

> **NIH NIH R21** · UNIVERSITY OF MICHIGAN AT ANN ARBOR · 2021 · $182,325

## Abstract

Abstract:
Metastasis from the primary tumor site to the brain is the most lethal complication of cancer progression and is
experienced by approximately 20% of breast cancer patients worldwide. There is at present no translational
approach to detect if a primary tumor has brain metastatic potential, no markers that predict successful future
metastasis, and thus no therapies to target any of the processes involved. These gaps are difficult to bridge
due to a lack of technology that can classify a cancer cell’s brain metastatic potential. Current in vivo murine
models are slow to manifest metastasis and do not have the capability of capturing single cell morphology and
dynamics; therefore, we propose a diagnostic platform to measure the phenotypic differences between cancer
cells and to assign them a brain metastatic potential. The output is a quantitative diagnostic read out that
defines the probability of a patient's cell metastasizing to the brain.
Preliminary data suggests we may use this platform to brain metastatic behavior in 24-72 hrs. We have
demonstrated that we can classify non-brain seeking and brain seeking cell lines based on phenotypic metrics
such as migration, extravasation, shape and volume with a positive predictive value of 0.9. This study will
validate the performance of this platform on patient cells. Further we aim to understand what components of
the brain stromal space promote brain metastasis to further improve the performance of this technology and
identify candidates that could be targeted by therapeutics to prevent metastasis in patients that have been
identified as at risk. In summary, we propose a unique approach to measure the individual metastatic potential
of tumor cells spatially and temporally.
This work will result in both improved clinical stratification and, downstream from it, in a more robust set of
targetable pathways for prevention of brain metastasis from breast and other primary sites.

## Key facts

- **NIH application ID:** 10109103
- **Project number:** 5R21CA245597-02
- **Recipient organization:** UNIVERSITY OF MICHIGAN AT ANN ARBOR
- **Principal Investigator:** SOFIA DIANA MERAJVER
- **Activity code:** R21 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2021
- **Award amount:** $182,325
- **Award type:** 5
- **Project period:** 2020-03-01 → 2023-02-28

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10109103

## Citation

> US National Institutes of Health, RePORTER application 10109103, Artificial Intelligence driven prediction of brain metastasis from primary tumor sites at diagnosis (5R21CA245597-02). Retrieved via AI Analytics 2026-05-23 from https://api.ai-analytics.org/grant/nih/10109103. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*