This program can offer more sensitive screenings to those at higher risk
Researchers are now using artificial intelligence (AI) in predicting the formation of breast cancer in the future.
Scientists from the Massachusetts Institute of Technology’s CSAIL and Jameel Clinic created a deep learning system to predict cancer risk from mammograms.
A mammogram is an X-ray of the breast used to detect breast changes in women who have no signs or symptoms of breast cancer.
This model was promising, showing equal accuracy for both white and Black women, a significant advancement given Black women’s 43% higher mortality rate from breast cancer.
To integrate image-based risk models into clinical care, researchers needed algorithmic improvements and large-scale validation across multiple hospitals. They developed the “Mirai” algorithm to address these needs.
Mirai predicts a patient’s risk across various future time points and can incorporate clinical risk factors like age and family history if available. It is also designed to maintain consistent predictions despite minor clinical variances, such as different mammography machines.
The model can predict that a patient has a higher risk of developing cancer within two years than they do within five years.
The team trained Mirai on over 2,00,000 exams from Massachusetts General Hospital (MGH) and validated it using data from MGH, Karolinska Institute in Sweden, and Chang Gung Memorial Hospital in Taiwan.
Mirai, now installed at MGH, showed significantly higher accuracy than previous methods in predicting cancer risk and identifying high-risk groups. It outperformed the Tyrer-Cuzick model, identifying nearly twice as many future cancer diagnoses.
Mirai maintained accuracy across different races, age groups, breast density categories, and cancer subtypes.
“Improved breast cancer risk models enable targeted screening strategies that achieve earlier detection and less screening harm than existing guidelines,” said Adam Yala, a CSAIL PhD student and lead author of the paper published in Science Translational Medicine.
The team is collaborating with clinicians from various global institutions to further validate the model on diverse populations and study its clinical implementation.
Mirai’s development included three key innovations: joint modeling of time points, optional use of non-image risk factors, and ensuring consistent performance across clinical environments.
This approach allows Mirai to provide accurate risk assessments and adapt to different clinical settings.
The researchers are now improving Mirai by utilising a patient’s full imaging history and incorporating advanced screening techniques like tomosynthesis.
These enhancements could refine risk-screening guidelines, offering more sensitive screenings to those at higher risk while reducing unnecessary procedures for others.
This AI model represents a significant step toward personalised cancer screening and better patient outcomes.
