Boston Children’s, GE Develop on Smart Imaging Technology

November 28, 2016 - Boston Children’s Hospital and GE Healthcare announced a collaboration to develop improved brain scan technology for better and more accurate diagnosis and to provide real-time contextual information for radiologists.

Using GE Health Cloud to process the high-volume of data and images, Boston Children’s Hospital lends their radiologists to assist in developing a new decision support platform intended to help distinguish the large variability in brain MRI scans. The system will provide doctors with scans of children of all ages with different conditions to use as reference points for reading scans.

"Interpreting pediatric brain scans requires a specific understanding of the developing brain," said Richard Robertson, MD, radiologist-in-chief at Boston Children's.  "Since most pediatric imaging is not performed in children's hospitals by specialists, this new digital tool, once available, will provide non-specialists with access to knowledge and expertise to help effectively diagnose children. We believe that by providing decision support at the time of interpretation, we can improve both the confidence and performance of the interpreting radiologist."

By using GE Health Cloud technology, the imaging performed at Boston Children’s Hospital allows non-specialist doctors to make an accurate diagnosis without sending the child away for further testing. The improved availability of information will give children and parents the answers they are looking for quickly and could help save lives by beginning life-saving treatments sooner.

The developing technology will offer a database of ad hoc images that are currently unavailable to most general radiologists. Without a large database of labeled images as a reference point, conditions can be misdiagnosed at different stages of development.

“Changes in myelination occurring during the first few years of life are particularly likely to be confused with disease states or, conversely, may lead to misinterpretation of the exam as normal for the patient when the abnormality is symmetric in the brain,” the announcement explained.

GE Healthcare is looking to the future of technology in healthcare and plans to assist in developing further solutions for healthcare institutions.

"This brain app that we are targeting to develop will be the first of many digital tools we are creating for our deep learning library," said Charles Koontz, chief digital officer, GE Healthcare.  "By 2020, we'll have hundreds of apps in the GE Health Cloud, enabling insights that will transform healthcare in each disease area and help the seven billion people on earth."

GE Healthcare has also partnered with the University of California San Francisco’s Center for Digital Health Innovation (CDHI) to develop a library of deep learning algorithms to assist clinicians in making faster and more effective diagnosis for common and complex medical conditions using imaging.

Similar to Boston Children’s Hospital, UCSF created a library of images to be used as reference points for clinicians, with the ultimate goal of using a machine learning algorithm to identify pneumothorax, or a collapsed lung.

Imaging analytics is growing in for health IT infrastructure because of the amount of data x-rays, MRIs, CAT scans, and other tests contain, which is often unusable without machine learning. With recent advances in machine learning and pattern recognition, computers are now able to understand images and identify subtleties clinicians may miss when examining an image.

One of the biggest challenges in healthcare big data analytics is extracting and analyzing data from static images and organizations are looking to develop machine learning solutions to make better use of image data.

Using machine learning for medical imaging is a complicated process and both Boston Children’s Hospital and UCSF are focusing in one area for the moment. Boston Children’s Hospital is currently focusing on childhood brain development and UCSF is using their technology to develop imaging machines to identify pneumothorax. If these collaborations with GE Healthcare are successful, more research instances will follow.

GE Healthcare’s collaboration with Boston Children’s Hospital demonstrates the continued need for  advanced imaging analytics in healthcare and imaging technology in healthcare.

Dig Deeper:

• Understanding HIPAA-Compliant Cloud Options for Health IT
• Growth of Medical IoT Devices Supports Healthcare Analytics