GE HealthCare has unveiled cutting-edge AI tools aimed at empowering radiologists in their efforts to improve cancer care, maternal health, and diagnostic procedures.
By leveraging artificial intelligence, GE HealthCare is continuously redefining the possibilities within the healthcare landscape.
On Tuesday, the company announced the opening of a new AI Innovation Lab, designed to accelerate innovations in AI that will enhance medical devices, improve decision-making, and increase operational efficiencies across the healthcare sector.
Dr. Taha Kass-Hout, GE HealthCare’s Global Chief Science and Technology Officer, emphasized the significance of the lab, stating, “The AI Innovation Lab lifts the curtain on the work we are undertaking at the vanguard of healthcare innovation. At GE HealthCare, we’re not just developing technology—we’re striving to break new ground by exploring novel ways that AI could enable healthcare.”
He further explained that projects like Health Companion aim to deliver clinical knowledge and problem-solving insights directly to clinicians, empowering them to make informed decisions swiftly.
Among the pioneering projects, GE HealthCare is investigating the application of multi-agentic AI to differentiate between expected symptoms resulting from treatments and symptoms indicative of disease progression, such as cancer metastasis.
This technology aims to alert care teams effectively, providing suggested next steps for patient management.
One of the primary focuses of the lab, as highlighted in the news release, is the development of multi-agentic AI technology. This cutting-edge system aims to distinguish between symptoms that are expected as a result of treatment and those that may indicate disease progression, such as cancer metastasis.
“This innovative approach is designed to effectively alert care teams, offering timely recommendations for patient management that could enhance outcomes and optimize care,” the release states.
In partnership with the Winship Cancer Institute of Emory University, GE HealthCare is advancing efforts to predict the recurrence of triple-negative breast cancer, a notably aggressive subtype that presents significant treatment challenges.
The news release emphasizes that up to 50% of early-stage patients may experience recurrence.
“To address this, the collaboration aims to utilize deep learning techniques to analyze multi-modal data, including genomic and pathology information.
“This research has the potential to improve predictive accuracy, allowing healthcare providers to customize treatment plans and monitoring schedules more effectively allowing radiologists to focus more of their time on suspicious cases,” It states.
Preventable risks associated with childbirth remain one of the most pressing health issues facing women today. In response, GE HealthCare is collaborating directly with health systems and their care teams to develop solutions aimed at addressing these challenges.
GE Healthcare is engaged in a research project focused on creating a full-body foundation model, utilizing a dataset of 1.2 million anonymized, PHI-free X-ray images from diverse anatomical regions.
According to the report, this model shows significant promise, yielding “promising early internal benchmark testing on key tasks including segmentation, classification, and visual localization.”
According to the report, this model shows significant promise, yielding “promising early internal benchmark testing on key tasks including segmentation, classification, and visual localization.”
With approximately 90% of screening mammograms in the U.S. returning normal results, there is currently no efficient method for radiologists to quickly differentiate between clearly normal scans and potentially suspicious ones.
The report notes that GE HealthCare is developing a cloud-based AI solution that aims to enable clinicians to swiftly identify normal breast screening exams, thereby allowing radiologists to dedicate more time to cases that require closer examination.