MIRAI – MIT Jameel Clinic

Our Mission

Breast cancer is the #1 most common cancer in women worldwide. Half of breast cancers develop in women who have no identifiable risk factors other than gender and age.

We believe that every person has the right to know their risk of developing cancer. Mirai is a deep learning model that produces a personalized risk score up to 5 years in advance just by analyzing a patient’s mammogram, ensuring that cancer can be detected early.

48 Hospitals

22 Countries

2M+ Mammograms validated

Mirai has been validated extensively on mammograms from patients all over the world. Thanks to the support of Wellcome Trust, we have been able to expand the deployment of Mirai to include hospitals serving under-resourced regions. This validation process is key to ensuring that Mirai maintains high performance and that it can be safely used on real patients.

Try Mirai

Collaborate with us

Hospitals around the world have installed Mirai, with some publishing independent research on Mirai.

We welcome hospitals to join our Hospital Network.

How does Mirai work?

In Japanese, “mirai” (未来) means future.

Mirai produces a risk score that helps the clinician determine if a patient requires additional screening if the patient is high-risk, or if the patient can avoid unnecessary screening if they are low-risk.

Evaluate Mirai’s performance.

The team behind Mirai

MIT Jameel Clinic AI faculty lead Regina Barzilay decided to build Mirai after completing her breast cancer treatment in 2016, when she learned there were no clinically-available AI models that assess breast cancer risk.

Joined by then-student Adam Yala and Mass General Brigham radiologists, Barzilay led the team to develop the technology behind Mirai.

The scale and computational power needed for bold ideas to work is not possible without the support of grants, foundations, and donors. Your support would enable MIT Jameel Clinic to make a better, healthier future for all.

Give Now

Mirai has been a leader in image-based cancer risk, setting the stage for this to become the new standard. Past approaches at risk models, such as Tyrer-Cuzick and Gail, have maxed out. The future belongs to image based cancer risk models. Dr. Kevin S. Hughes, MD, FACS
Director of Cancer Genetics
McKoy Rose Professor of Surgery
Medical University of South Carolina

In Chile, we are working on a development plan through a partnership between Hospital Digital and the University of Chile, aimed at implementing Mirai for clinical use…A cost-effectiveness analysis is currently underway to optimize breast cancer screening and enable the deployment of this technology for clinical use within Hospital Digital. Dr. Arnaldo Marín, MD, PhD
Assistant Professor
University of Chile