GE, Boston Children's to create deep-learning tool for pediatric brain scans

A comparison of scans showing normal and abnormal pediatric brain development--Courtesy of Boston Children's Hospital

GE Healthcare is teaming up with Boston Children’s Hospital to develop digital tools for the diagnosis and treatment of childhood diseases with an initial focus on diagnostic imaging for brain disease.

In this first project, GE will contribute its software and cloud computing prowess, while Boston Children’s radiologists will pitch in their clinical knowledge. The goal will be to create a decision-support tool to help radiologists interpret pediatric MRI scans of the brain, according to a statement. This has the potential to save money, time and stress associated with misdiagnosis and unnecessary testing.

Because the brain changes so quickly during early childhood, a disorder may be misinterpreted as normal brain maturation, while normal development may be mistaken for abnormal changes and lead to unnecessary testing, according to the statement. While some image databases exist against which to compare pediatric images, they tend to be restricted to the pediatric units of major academic institutions. The partners will build a platform with scans from children of varying ages to be used worldwide as a reference when interpreting pediatric brain images.

Webinar

How ICON, Lotus, and Bioforum are Improving Study Efficiency with a Modern EDC

CROs are often at the forefront of adopting new technologies to make clinical trials more efficient. Hear how ICON, Lotus Clinical Research, and Bioforum are speeding database builds and automating reporting tasks for data management.

"Pediatric brain scans of children under the age of four can be particularly tricky to read because the brain is rapidly developing during this period of childhood," said Dr. Sanjay Prabhu, a pediatric neuroradiologist at Boston Children’s, in the statement. "Since pediatric neuroradiologists are very scarce, we approached GE Healthcare to collaborate on the development of digital tools to help physicians of varying expertise read the scans."

While this initial project focuses on brain imaging, GE plans to flesh out its stable of deep learning tools, aiming for a “hundreds of apps” in the GE Health Cloud by 2020, said Charles Koontz, GE Healthcare’s chief digital officer, in the statement.

GE’s other cloud-based solutions include a handful of radiology-based apps launched a year ago, such as apps for collaborative care planning for radiologists and pathologists, image and report sharing and storing and analyzing a patient’s imaging data over time. Additionally, the company added a new software application to its Health Cloud in March: Imbio’s Lung Density Analysis. The app is an automated, biomarker-based quantitative lung imaging analysis tool to provide clinicians with more insights into lung CT data.

Suggested Articles

Janssen’s BCMA-targeting CAR-T therapy eliminated tumors in 69% of patients with advanced multiple myeloma in a small phase 1 study.

In a study, BMS' CAR-T therapy banished tumors in more than half and shrank tumors in nearly three-quarters of relapsed blood cancer patients.

The ADDF announced its second round of research awards, with a total of $6 million in new funding for diagnostic tests.