This technology is a convolutional neural network based algorithm for predicting individualized breast cancer risk based on a mammogram image.
Breast cancer is a leading cause of death worldwide and is the second most common cause of cancer death among women in the United States. Currently, the risk for breast cancer is primarily predicted using genetic factors such as BRCA mutation and clinical factors such as family history of breast cancer. Unfortunately, while these factors are very important, they only account for ~20% of the population at risk for breast cancer. Majority of the patients with a new cancer diagnosis do not have either genetic or clinical risk factors associated with breast cancer. Thus, CNN based algorithm was developed to identify mammographic features that may be associated with patient’s risk for breast cancer.
This technology is a convolutional neural network based algorithm that was trained in large sets of mammogram image features associated with breast cancer risk for potential use in individual breast cancer risk assessment.
IR CU18102, CU18103, CU18104, CU18106, CU18109, CU18110
Licensing Contact: Jerry Kokoshka