MIT Jameel Clinic collaborates with Japan to test Cancer prediction AI Mirai

JAPAN — The MIT Jameel Clinic, a leading center for artificial intelligence (AI) and health at the Massachusetts Institute of Technology (MIT), has partnered with Japan’s National Cancer Center Hospital to evaluate Mirai, an innovative deep learning model.

Mirai has the ability to analyze mammograms and accurately predict a patient’s risk of developing breast cancer up to five years in advance.

Mirai was developed at the Jameel Clinic, which was established in 2018 by MIT and Community Jameel, an international organization dedicated to advancing science and education for thriving communities.

The model has already been validated on over two million mammograms from 72 hospitals across 23 countries, demonstrating its wide applicability.

The collaboration was formally announced during a ceremony attended by Mohammed Jameel KBE, founder and chairman of Community Jameel, and Dr. Yasuyuki Seto, director of the National Cancer Center Hospital.

The partnership will begin with a study focused on assessing Mirai’s ability to predict breast cancer risk specifically in Japanese women using mammography images.

This study will analyze mammography data collected from screenings between 2013 and 2024.

Researchers aim to determine if Mirai can reliably assess breast cancer risk in the Japanese population, which would further strengthen its validation record.

If successful, this work could support more personalized breast cancer screening strategies in Japan.

Higher-risk individuals might receive closer monitoring, while those at lower risk could avoid unnecessary tests.

Breast cancer is the most common cancer among women in Japan, accounting for about 23 percent of female cancer cases, or roughly 98,782 new diagnoses each year.

Approximately 16,000 women die from breast cancer annually, which underlines the critical need for early detection.

When detected at an early stage, the five-year relative survival rate exceeds 90 percent, highlighting the importance of early risk identification and appropriate follow-up care.

Currently, the Japanese health system recommends mammography screenings every two years for women aged 40 and above.

While mammograms help detect small lumps and microcalcifications not visible through self-examination, interpreting these images depends heavily on clinical experience and visual assessment.

Mohammed Jameel KBE described Mirai as a powerful AI tool that promises to improve cancer care for women worldwide.

He expressed enthusiasm about the longstanding connection between the Jameel family and Japan, and the opportunity for the MIT Jameel Clinic and Community Jameel to collaborate with the National Cancer Center Hospital to advance breast cancer care through Mirai.

Dr. Kan Yonemori, Director of the Department of Medical Oncology at the National Cancer Center Hospital, noted the study’s potential to enhance women’s health by predicting individual breast cancer risks using large-scale mammography screening data.

He emphasized his team’s commitment to this international collaboration with the MIT Jameel Clinic and their dedication to contributing to global research efforts.

Regina Barzilay, AI faculty lead at the MIT Jameel Clinic, expressed hope that Mirai’s ability to forecast cancer risk up to five years ahead will inspire new approaches to breast cancer screening and treatment in Japan.

The study will include data from individuals screened at both the National Cancer Center Hospital and Yotsuya Medical Cube between 2013 and 2024.

Mirai will analyze these mammogram images to predict the breast cancer risk over a one- to five-year period.

Researchers will then compare the predicted risk scores with actual outcomes to assess the model’s accuracy and reliability within the Japanese clinical context.

Supported by Community Jameel and Jameel Corporation, this research aims to bring AI-powered, risk-based breast cancer screening closer to clinical practice in Japan.

Such technology could enable earlier cancer detection and more personalized care driven by advanced AI analytics.