MIT Jameel Clinic Brings AI Breast Cancer Tool to Japan in Bid to Cut Deaths

Mirai model to be validated on mammography data from two Tokyo hospitals

Breast cancer kills roughly 16,000 women in Japan every year. Early detection pushes the five-year survival rate above 90 percent. A new collaboration between the MIT Jameel Clinic and the National Cancer Center Hospital in Tokyo is testing whether an artificial intelligence tool can shift the odds.

The two institutions have agreed to evaluate Mirai, a deep learning model that reads mammogram images and generates a personalized risk score spanning up to five years. The study will draw on screening data collected at the National Cancer Center Hospital and Yotsuya Medical Cube between 2013 and 2024, comparing Mirai’s predictions against actual patient outcomes to gauge its accuracy in a Japanese clinical setting.

Mirai was built at the MIT Jameel Clinic, which MIT and Community Jameel cofounded in 2018. Community Jameel is an international organization, launched by Mohammed Abdul Latif Jameel KBE, that advances science and learning for communities to thrive. Before arriving in Japan, the model had been validated on more than 2 million mammograms across 72 hospitals in 23 countries.

Japan screens women for breast cancer every two years starting at age 40. Radiologists read mammograms visually, relying on clinical experience to flag abnormalities — a process that Mirai is designed to augment, not replace. If validated for Japanese patients, the model could allow clinicians to increase monitoring frequency for higher-risk women while spacing out tests for those at lower risk.

“Mirai is a powerful tool that harnesses AI to improve cancer care for women around the world,” said Mohammed Jameel KBE, founder and chairman of Community Jameel, who attended the ceremony alongside National Cancer Center Hospital Director Dr. Yasuyuki Seto. “With the Jameel family’s deep and longstanding connection to Japan, we are delighted that the MIT Jameel Clinic and Community Jameel are collaborating with the National Cancer Center Hospital to open the way for Mirai to improve care for Japanese women at risk of breast cancer.”

Dr. Kan Yonemori, director of medical oncology at the National Cancer Center Hospital, said the study aims to predict an individual’s future risk using large-scale screening data. Regina Barzilay, AI faculty lead at the clinic, expressed hope that the collaboration would “inspire new approaches” to how Japan screens and treats breast cancer. The study is supported by Community Jameel and Jameel Corporation. More detail on the IsDB and MIT Jameel Clinic collaboration on AI cancer tools offers additional context on how similar work is being extended to other countries.