Boston Children’s Hospital is teaming up with GE Healthcare to develop radiology-oriented AI software that will bring the pediatric hospital's expertise in image interpretation to a wider audience.
“How do you take knowledge? How do you apply it so that it doesn't sit in a few places in Children's Hospital, but you can literally make it so that no child going anywhere ends up with a misdiagnosis?” Sandra Fenwick, CEO of Boston Children’s Hospital, told a recent Boston Chamber of Commerce meeting, reported by the Boston Business Journal
. “That's one thing that we're working on that we really think is going to change the way children get care, not just at Children's but much more broadly.”
The effort is in the early stages and the hospital provided no further details to the publication, but did note that the first focus would be on brain scans.
“So many of our parents today are using their technology to care for their children, [to help] run their lives,” Fenwick said. “So how can we use that to help engage with our patients? How do we use that on the floors, how do we use it in our offices? And so that's on an effort that we've also made some significant strides in, and are beginning to make enormous investments in.”
GE has been involved in a number of AI developments that have made news of late. In April, its Deep Learning Image Reconstruction engine using AI with its new Revolution Apex CT device received FDA clearance
. It is an upgrade to its Revolution CT devices in the U.S. and applies AI analysis to reconstructed images, yielding what are called TrueFidelity CT images, which are cleaner and produced at low dose with better quality and noise texture.
“One of the challenges that we have when we’re talking about reconstruction has been the look and feel of the image quality,” Saad Sirohey, GE’s general manager of global MICT clinical applications, told HCB News at the time. “What we’re able to reproduce with the deep learning reconstruction is giving (clinicians) the same image texture they’ve been used to and using this technique to reduce the noise and improve the image quality.”
Sonia Sahney, global product marketing director for GE’s premium CT segment, said TrueFidelity images require no additional hardware and have no impact on the reconstruction time. “It will just fit into clinical workflow."
Children's Hospital has also teamed with a number of other firms to improve healthcare imaging workflows. In mid-May, it announced that it was working with Red Hat
to deploy the ChRIS Research Integration Service on the Massachusetts Open Cloud (MOC) — a web-based medical image platform with a distributed user interface permitting real-time collaboration between clinicians and radiologists around the world.
“Something that might have taken hours or days can now be executed in minutes or seconds, bringing valuable data back to the clinical front line in a time frame relevant to individual patient care,” P. Ellen Grant, director of the Fetal Neonatal Neuroimaging and Developmental Science Center at Boston’s Children’s Hospital, told HCB News at the time. “Further, the ChRIS platform, combined with an open cloud like the MOC, creates the possibility of establishing secure cost-effective storage and computing for medical data that is run by a consortium of hospitals and institutions at a fraction of the cost required to host in each hospital or use in today's public clouds.”