Tag: Regina Barzilay
Balancing Power With Caution: AI’s Impact On Breast Cancer
During my seven years as president and CEO of Susan G. Komen, I’ve witnessed the impact of innovation in our mission to end breast cancer for good. Over the past four decades, we’ve seen a 44% reduction in breast cancer mortality, thanks to early detection and better treatments. AI is now accelerating this progress with its capacity to analyze vast datasets, discover new patterns and enhance diagnostic accuracy.Take, for example, the groundbreaking work of Komen scholar Dr. Regina Barzilay. Using her own mammograms in her research at MIT, Dr. Barzilay demonstrated how AI could have detected her breast cancer much earlier, potentially improving her prognosis. Studies show that incorporating AI into mammogram analysis boosts cancer detection rates by 20%, without increasing false positives. This is a significant leap forward, as early detection is key to a better chance at positive outcomes and survival. Learn more
Using AI to predict lung cancer risk
In recent years, lung cancer rates have been rising in nonsmokers, a troubling trend for the world's #1 deadliest cancer. Sybil is a deep learning model built by MIT Jameel Clinic and Mass General Brigham researchers that accurately predicts lung cancer risk up to 6 years in advance by analyzing a patient's LDCT scan. How exactly does this state-of-the-art model work and what was the key insight that brought it to life? Watch this 7-minute video featuring the researchers behind the model to learn more about how Sybil is transforming the future of lung cancer screening. Learn more
MIT researchers introduce Boltz-1, a fully open-source model for predicting biomolecular structures
MIT scientists have released a powerful, open-source AI model, called Boltz-1, that could significantly accelerate biomedical research and drug development. Developed by a team of researchers in the MIT Jameel Clinic for Machine Learning in Health, Boltz-1 is the first fully open-source model that achieves state-of-the-art performance at the level of AlphaFold3, the model from Google DeepMind that predicts the 3D structures of proteins and other biological molecules. MIT graduate students Jeremy Wohlwend and Gabriele Corso were the lead developers of Boltz-1, along with MIT Jameel Clinic Research Affiliate Saro Passaro and MIT professors of electrical engineering and computer science Regina Barzilay and Tommi Jaakkola. Wohlwend and Corso presented the model at a Dec. 5 event at MIT’s Stata Center, where they said their ultimate goal is to foster global collaboration, accelerate discoveries, and provide a robust platform for advancing biomolecular modeling. Learn more
