GE HealthCare and Mass General Brigham Bring AI to Boost Research

Leading medical technology company GE HealthCare and not-for-profit medical research company Mass General Brigham are expanding their partnership in AI by integrating medical imaging foundation models into their research endeavors. 

Since committing a decade-long commitment to AI exploration in 2017, both entities have collaborated closely to develop AI solutions for diagnostic and treatment purposes, emphasizing sustainable AI development and responsible practices.

Dr. Keith Dreyer, Chief Data Science Officer at Mass General Brigham, highlights the significance of foundation models in reshaping AI innovation. 

“I think we are all optimistic that foundation models may actually complement and enhance the work we have been doing with convolutional neural networks over the past few years. Hopefully, this work will help make healthcare delivery more efficient for our practitioners, more accessible for our patients and more equitable for our diverse communities,” added Dreyer. 

Traditional AI integration in healthcare involves costly and complex model retraining to suit diverse patient populations and hospital settings, hindering widespread adoption. Foundation models, however, offer promise in streamlining workflow efficiency and imaging diagnosis, having demonstrated versatility across various tasks. They serve as a dependable framework for tailoring AI applications to the healthcare sector.

Parminder Bhatia, Chief AI Officer at GE HealthCare, underscores the partnership's track record in developing AI-powered tools to enhance operational effectiveness. With the incorporation of foundation models into their research, they aim to advance technology innovations for improved patient care and outcomes. Furthermore, they prioritize responsible AI practices, ensuring adherence to guidelines, patient safety, privacy, and fairness across applications.

Back in July 2021, Google DeepMind launched AlphaFold, an advanced AI system for predicting protein structures. Since then, healthcare companies have been slowly tapping into AI. However, it continues to be one of the most challenging areas because of the sensitive and unstructured nature of the data.