What You Should Know:
– Microsoft has joined forces with renowned academic medical centers – Mass General Brigham and the University of Wisconsin School of Medicine and Public Health (UW School of Medicine) and its affiliated health system, UW Health – to tackle key challenges in radiology and propel the use of generative AI in medical imaging.
– The collaboration between Microsoft, Mass General Brigham, UW School of Medicine, and UW Health represents a significant step forward in harnessing generative AI to revolutionize medical imaging.
The Need for AI in Medical Imaging
Medical imaging plays a central role in healthcare, with imaging exams forming part of roughly 80% of hospital visits. However, the industry faces hurdles, including physician burnout and staffing shortages. Generative AI, a powerful form of artificial intelligence, emerges as a potential solution.
How AI Can Revolutionize Radiology
By leveraging generative AI, Microsoft and its partners envision a future where advanced algorithms and applications:
- Assist radiologists and other clinicians in interpreting medical images.
- Generate reports automatically.
- Classify diseases more accurately.
- Analyze structured data efficiently.
This translates to reduced workloads for radiologists, improved report accuracy, and potentially faster diagnoses. Additionally, generative AI can expedite turnaround times for imaging results, improving patient experiences and access to care.
Developing AI Foundational Models for Medical Imaging
The collaboration focuses on developing state-of-the-art “multimodal foundation models” – AI models trained on a vast amount of diverse medical imaging data. These models will serve as the building blocks for a wide range of AI applications within the secure Microsoft Azure AI platform. Moreover, the project will integrate with Nuance’s (a Microsoft company) suite of radiology applications, further expanding the reach of AI in radiology.
Responsible AI Development Priority
As AI advancements accelerate, so does the responsibility to prioritize patient privacy. Microsoft emphasizes its commitment to “Responsible AI principles” throughout this project. This commitment includes building and deploying AI systems ethically and providing tools and resources to empower its partners to do the same.
“Generative AI has transformative potential to overcome traditional barriers in AI product development and to accelerate the impact of these technologies on clinical care. As healthcare leaders, we need to carefully and responsibly develop and evaluate such tools to ensure high-quality care is in no way compromised,” said Keith J. Dreyer, D.O., Ph.D., chief data science officer and chief imaging officer at Mass General Brigham and leader of the Mass General Brigham AI business. “Foundation models fine-tuned on Mass General Brigham’s vast multimodal longitudinal data assets can enable a shorter development cycle of AI/ML-based software as a medical device and other clinical applications, for example, to automate the segmentation of organs and abnormalities in medical imaging and increase radiologists’ efficiency and consistency.”