Meticulous Science. Mindfully Delivered.
Machine Learning for Mammography
Screening mammography saves lives, yet the volume of cases generated by screening puts an enormous demand on radiologists. We are using deep learning to create tools that will help radiologists interpret mammograms more accurately and efficiently, for both 2D full-field digital mammograms and 3D digital breast tomosynthesis.
Algorithms Based on Expert Knowledge
Our models learn from interpretations provided by expert radiologists and pathologists to map images to gold standard diagnoses.
Learning from Lifetimes of Data
Our models have been trained on more data than a single clinician could possibly see in her/his lifetime.
Improving Patient Outcomes
Ultimately, our greatest goal is to improve the lives of patients, by helping detect cancers as early as possible while minimizing unnecessary callbacks.
Reading Mammograms is Difficult
The subtle nature of cancerous lesions and the large number of cases to interpret can be straining, especially for digital breast tomosynthesis.
Beyond Traditional CAD
Our software uses deep learning to achieve higher performance levels than traditional CAD, enabling more effective clinical use cases.
An Accuracy Boost
Our software highlights a small number of suspicious lesions so breast imagers can identify more cancers without having to sort through all of the false positives generated by traditional CAD.
Software as an Assistant
Our software empowers radiologists by helping them interpret more efficiently, so they can spend more time on other critical tasks.