Digital image workstations have progressed rapidly since first being introduced to radiology more than 25 years ago. But they have yet to achieve the intuitive ease of use that characterized the light boxes they replaced, said presenters at the meeting of the Society for Imaging Informatics in Medicine (formerly SCAR), held in Austin, Texas, from 27 to 30 April.
Digital image workstations have progressed rapidly since first being introduced to radiology more than 25 years ago. But they have yet to achieve the intuitive ease of use that characterized the light boxes they replaced, said presenters at the meeting of the Society for Imaging Informatics in Medicine (formerly SCAR), held in Austin, Texas, from 27 to 30 April.
Session speakers identified two general problems with workstations: functions that exist in specialized settings and need to be easily available, and interface problems that stand in the way of effective use. Both problems tend to interrupt workflow and have kept radiologists from achieving additional efficiencies that workstations should provide, they said.
Dr. Steven C. Horii, a pioneer in the development of workstations from the University of Pennsylvania Health System, cited some notable successes. Workstations have proved useful for interpreting cross-sectional images and projection radiographs and in teleradiology.
But other common applications, including mammography, PET/CT fusion, and studies that combine 2D, 3D, and 4D images, still require specialized workstations. When physicians must leave their general PACS stations to perform these specialized tasks, the workflow is broken and efficiency sacrificed, Horii said.
Workstation problems also lurk outside the reading room. PACS is gaining ground in orthopedics, but most orthopedic surgeons still rely on film for surgical planning, Horii said. Medical images are increasingly being used outside the reading room, but referring physicians often rely on technologically inferior computers and software that lack the power and sophistication to display images.
Images could be invaluable in the operating room, but calling them up and manipulating them is challenging in a sterile environment. Surgeons don't want to scrub up each time they touch a computer control, Horii said. One solution is to put a mouse in a sterile bag, but surgeons are still resistant because they want to concentrate on surgery and not work a mouse.
Dr. David L. Weiss, head of imaging informatics at the Geisinger Health System in Danville, Pennsylvania, found fault with workstations that fail to achieve full efficiency for radiologists. He noted that viewboxes achieved a fairly high level of user efficiency before PACS led to the development of workstations. Viewboxes were intuitive, with hanging protocols that could be customized, read, and dictated without radiologists taking their eyes off images. Tasks such as annotation, magnification, and measurements could be performed with tools readily at hand.
Try the same thing with a workstation, and the task may not be quite so easy. A wax pencil for annotating film can be put down, but a workstation tool that performs the same function must be turned off after it is used. Weiss compared that glitch to having the wax pencil stick to the radiologist's hand. Workstation magnification tools can sometimes be so cumbersome that radiologists resort to hand magnifying glasses to accomplish the same task, he said.
Other issues involve the user interface. Too often, workstations require users to take their eyes off the image to change settings-an enemy of efficiency, Weiss said. Players can use gaming systems and devices without taking their eyes off the screen, and radiologists should be able to view images the same way.
There should be no icons to click and no keyword searches. Interfaces should be intuitive and rely on two hands, 10 fingers, and five senses, Weiss said.
Study: AI Boosts Ultrasound AUC for Predicting Thyroid Malignancy Risk by 34 Percent Over TI-RADS
February 17th 2025In a study involving assessment of over 1,000 thyroid nodules, researchers found the machine learning model led to substantial increases in sensitivity and specificity for estimating the risk of thyroid malignancy over traditional TI-RADS and guidelines from the American Thyroid Association.
Can CT-Based AI Provide Automated Detection of Colorectal Cancer?
February 14th 2025For the assessment of contrast-enhanced abdominopelvic CT exams, an artificial intelligence model demonstrated equivalent or better sensitivity than radiologist readers, and greater than 90 percent specificity for the diagnosis of colorectal cancer.
Emerging PET/CT Agent Shows Promise in Detecting PCa Recurrence in Patients with Low PSA Levels
February 13th 202518F-DCFPyL facilitated detection of recurrent prostate cancer in 51 percent of patients with PSA levels ranging between 0.2 to 0.5 ng/ml, according to new research presented at the American Society of Clinical Oncology Genitourinary Cancers (ASCO-GU) Symposium.