SimBioSys has been given FDA clearance for the Nvidia-powered TumorSight Risk, an AI and MRI-derived prognostic tool for assessing the risk of a breast cancer coming back.
The platform analyzes routinely collected breast MRI, pathology and clinical data to create a personalised prognosis at five and ten years.
The tech gives oncologists insight to support treatment planning for women with hormone receptor-positive (HR+), HER2-negative Stage I–IIIA breast cancer—a subtype representing around 75% of all breast cancers in the U.S.
“Achieving FDA clearance of TumorSight Risk marks a defining moment for SimBioSys and for precision breast cancer care,” said Stacey Stevens, President and CEO of SimBioSys, in a statement.
“For the first time, clinicians can use the rich biological and spatial information already captured in a patient’s breast MRI—together with standard pathology and clinical factors—to gain personalized insight into recurrence risk.”
Built on the FDA-cleared TumorSight Viz foundation and also powered by Nvidia technology, TumorSight Risk applies spatial AI modeling to tumor characteristics, surrounding tissue context, and clinical factors.
The cloud-based software platform can then create a categorical high, intermediate or low-risk classification. It uses data already collected as part of routine care, requires no additional procedure, tissue shipment, or specialized hardware, and is designed to make results available within standard clinical workflows.
The clearance is supported by a blinded, prospectively-designed retrospective, multi-institutional validation study of 2,129 patients from Mayo Clinic, Emory University, Stanford Medicine and Mercy Medical Cedar Rapids. Results were recently presented at the 2026 American Society of Clinical Oncology (ASCO) Annual Meeting. SimBioSys noted that the Mayo Clinic has a financial interest related to this research.
The study found that TumorSight Risk successfully stratified patients by recurrence-free survival. Patients classified as high risk had a 3.3-fold higher risk of recurrence than those classified as low risk. Each 10-point increase in the 0–100 score was associated with a 22% increase in relative recurrence risk.
Estimated five-year recurrence risk ranged from 2.2% for patients with the lowest scores (0–10) to 13.6% for those with the highest scores (58–100). At ten years, estimated recurrence risk ranged from 6.2% to 34.2% across those same score groups. The score remained significantly associated with recurrence-free survival after adjustment for standard of care prognostic information, including pathologic tumor and nodal stage, grade, age, race and treatment (p=0.002).
Current recurrence-risk assessment often relies on clinicopathologic features and tissue-based genomic assays, which can take up to two weeks to deliver results. Some patient groups—including premenopausal and lymph node-positive women—have historically had fewer validated options.
Able to produce an assessment in as little as one hour, TumorSight Risk is designed to complement existing methods with an imaging-native assessment that is available earlier in the care pathway and applicable across a broad population of patients with HR-positive, HER2-negative early-stage disease.
According to SimBioSys, this additional insight may help clinicians and patients weigh treatment options alongside potential side effects, quality of life and patient preferences.