Radiologists are more frequently reading cases for more remote hospitals and imaging centers. Just channeling the images from these facilities to different members of a reading group can be a nightmare.
Radiologists are more frequently reading cases for more remote hospitals and imaging centers. Just channeling the images from these facilities to different members of a reading group can be a nightmare.
Neurostar Solutions is reaching out to these groups and the facilities they serve, providing an innovative networking system that pulls the data from hospitals and imaging centers onto servers from which images can be retrieved and reports filed. This system, called the Virtual Radiology Network, is designed to manage the flow of radiology images from an unlimited number of sites to an established bank of servers.
Neurostar has installed the network at more than 200 sites in the U.S., according to the Atlanta-based company, whose client base is composed primarily of hospitals and imaging centers. About 70% of its revenue comes from facilities that need remote radiology reading service or want to convert to digital image management. The remaining 30% comes from radiology groups that want to increase their productivity, expand their coverage, or offer teleradiology services.
Costs vary, depending on whether customers acquire the technology themselves or use Virtual Radiology Network as a service. The latter is the more popular option, as most of the company's revenues-up to 85%-come from fee for service. Neurostar typically structures these agreements as a fee per study with a flat minimum monthly rate.
Dr. David Estle, president of the Chatham Radiology Group, said costs per facility for his group are in the hundreds rather than thousands of dollars. The Chatham group, based in Savannah, has been using Neurostar's Web-based network for about two years. Before signing on with NeuroStar, the group considered other options. None was particularly appealing.
"They were all PACS companies that wanted to sell us a product," Estle said. "We wanted something that would solve our problems. Neurostar did that quickly, easily, and cheaply."
Virtual Radiology Network draws data directly from imaging equipment, teleradiology, and PACS installed at individual facilities. It accomplishes this using remote agents, black boxes that are part of its MediCom component. These agents self-configure to the onsite network and then route the data to Neurostar's servers.
"The beauty of it is that with our server infrastructure already in place, we can set up a new site in a minimum of time," said Arman Sharafshani, cofounder of the company.
Radiologists query the servers using a Web-based software package called MediView, which runs on their own computers. MediView is optimized for viewing images, as well as other patient data.
"I can be on call for several different hospitals, calling up images from each of them on my computer, using Neurostar software," Estle said.
System integrity is managed by a SecureMed component that maintains audit trails, authenticates users, and allows appropriate access. Customers have the option of long-term data storage as part of the MediArch image archiving subsystem.
Before applying Virtual Radiology Network, the Chatham group had no choice but to visit its contracted facilities, sending radiologists each day to sites up to 50 miles away from its Savannah hub.
Since joining Virtual Radiology Network, the group's clientele has expanded. The seven-person Chatham group now reads for five hospitals and three imaging centers spread across southcentral and southeastern Georgia. One of the new centers
is a five-hour trip from Savannah. Yet just one member of the group
is on the road on any single day.
This partucular member doesn't read many images. His job, according to Estle, is to ensure quality and conduct procedures at the different facilities.
Readings are typically done at the group's hub, although images can be pulled to any computer that runs the Neurostar software. The problem isn't getting the images, but having enough radiologists to read them, Estle said.
"We have more business than we know what to do with," he said. "Once you start networking, your range just starts growing. To be frank, we need more bodies."
Can CT-Based Deep Learning Bolster Prognostic Assessments of Ground-Glass Nodules?
June 19th 2025Emerging research shows that a multiple time-series deep learning model assessment of CT images provides 20 percent higher sensitivity than a delta radiomic model and 56 percent higher sensitivity than a clinical model for prognostic evaluation of ground-glass nodules.
FDA Clears Ultrasound AI Detection for Pleural Effusion and Consolidation
June 18th 2025The 14th FDA-cleared AI software embedded in the Exo Iris ultrasound device reportedly enables automated detection of key pulmonary findings that may facilitate detection of pneumonia and tuberculosis in seconds.