The CancerInSight Initiative
Transforming the future of breast cancer screening with the power of AI
Get Involved
How does MIRAI work?
MIRAI is a state-of-the-art deep learning algorithm developed by a team of researchers at MIT and Mass General Brigham that uses patient’s mammogram to predict their 5-year breast cancer risk by producing a risk score. This risk score helps the physician determine how soon a patient needs to return for their next mammogram to ensure that breast cancer can be detected early and interventions are minimally invasive and less costly.
Does MIRAI really work?
MIRAI’s performance has been validated on over 1.7 million mammograms from diverse populations in hospitals around the world. Unlike Tyrer-Cuzick, a statistical model that is currently used to calculate a patient’s risk, MIRAI maintains performance across diverse populations.
Support the Adoption of a Revolutionary Deep Learning Mammography Model for Breast Cancer Risk Prediction
1 in 8 women will develop breast cancer in her lifetime. However, predicting who will be affected remains a challenge. Until recently, methods for assessing risk, such as breast density, have not reliably stratified patient risk of developing breast cancer. As a result, current screening guidelines adopt a “one size fits all” approach.
In the last 5 years, a new generation of AI-based risk models has been developed. These methods analyze existing mammograms and accurately predict a patient’s risk of developing breast cancer in the next 5 years. MIRAI, an AI model developed by MIT and Mass General Brigham researchers, has been tested in large, diverse populations both in the United States and around the world. It has consistently demonstrated superior performance compared to all existing risk stratification methods. In contrast to traditional models, MIRAI’s performance is equitable across race, age, and breast densities.
Unfortunately, today, AI-based screening models are not yet used in clinical practice. This delay is partially due to the slow change in clinical guidelines and insurance policies. To address this, we have launched the #CancerInSight initiative aimed at accelerating the adoption of AI-driven risk stratification to benefit patients. Achieving this goal will require updates to clinical guidelines and support from insurance companies.
Get Involved
How can you help? We plan to engage with committees that create clinical guidelines and policymakers to bring innovative technology like MIRAI to patient care. We need your participation to make our demands heard. By adding your name to our list, we will keep you informed via email and share petitions that you can choose to sign. Your email will not be shared with others and will only be used for this purpose.
Artificial intelligence–based risk-stratified programs were estimated to be cost-saving and increase QALYs compared with the current screening program. A screening schedule…was estimated to give yearly net monetary benefits within the NHS of approximately £60.4 (US $77.3) million and £85.3 (US $109.2) million, with QALY values set at £20 000 (US $25 600) and £30 000 (US $38 400), respectively.JAMA NETWORK OPEN
VOLUME 7 NO. 9 / SEPTEMBER 2024
[MIRAI] showed good performance in a high-risk external dataset enriched for African American patients, benign breast disease, and BRCA mutation carriers, and study findings suggest that the model performance is likely driven by the detection of precancerous changes.RADIOLOGY ARTIFICIAL INTELLIGENCE
VOLUME 20 5(6) / NOVEMBER 2023
Of the risk-stratified regimens considered, we found using three screening intervals (1, 3 or 4 years) using Mirai 3-year risk thresholds (<1.56% for low risk, and ≥5.06% for high risk) was promising, and expected to reduce the number of advanced cancers diagnosed by approximately 18 advanced cancers per 1000 cancers diagnosed with triennial screening.npj Digital Medicine
VOLUME 6, NUMBER 223 / NOVEMBER 2023
AI provides a powerful way to stratify women for clinical considerations that necessitate shorter time horizons such as risk-based screening and supplemental imaging.RADIOLOGY
VOLUME 307, ISSUE 5 / JUNE 2023
Overall, 3-year risk was strongly associated with development of both future interval cancer and screen-detected cancer. There was no evidence of a significant difference in model performance between interval and screen-detected cancers (AUC, 0.69 vs 0.67; P = .085) or invasive cancer versus DCIS.RADIOLOGY
VOLUME 307, ISSUE 5 / JUNE 2023
This study concluded that Mirai has the potential to replace current breast cancer risk assessment models recommended by clinical guidelines for magnetic resonance imaging screening.Journal of Clinical Oncology
VOLUME 40, NUMBER 20 / APRIL 2022
The latest news about MIRAI
MIRAI is making headlines. Read the news about how MIRAI could be a gamechanger for breast cancer screening.
NEWS
