Vendors propose methods to boost quality of postprocessing, reducing stress of keeping up
Vendors propose methods to boost quality of postprocessing, reducing stress of keeping up
The slice-war battlefield has calmed as CT vendors dig in with 64 slices, but the fallout has begun to take a toll. Cardiac studies over several phases of the heart and head-to-toe exams on trauma patients are burying reading rooms in thousands of slices. What radiologists thought was bad before has gotten worse. Knowing that the future will only bring more, vendors at this RSNA meeting are doing something, actually many things, about the problem.
Siemens Medical Solutions will display WebSpace, a thin-client answer to slice overload. Running on a dedicated server, the software product will disperse thin-slice reconstructions throughout a network, turning PCs into workstations regardless of location, including the homes of radiologists, according to Scott Goodwin, vice president of Siemens CT division.
"We are focusing on CT because this is one of the dynamics we are seeing: people wanting to have access to CT studies anywhere, anytime," he said. "And, of course, doing it at an economic price point."
Toshiba America Medical Systems will bring a fortified version of its Sure Cardio, a software suite designed to optimize cardiac CT scans. The suite debuted several years ago with an annually expanding script of algorithms that automatically picks the best parameters for a scan, including reconstruction mode, pitch, and rotation time based on the patient's heart rate. This year, Sure Cardio with Phase Exact promises to reduce the thousand-plus CT slices generated during a cardiac exam to about 500. The secret sauce for this little dandy is an algorithm that automatically identifies and reconstructs the best data.
Sure Cardio will decrease the data load per exam, said Robb Young, senior manager for the Toshiba CT business unit, but the load itself will continue to rise with an increasing number of cardiac CTs, as this modality gains prominence in the years ahead. Toshiba's answer is a storage system dedicated to CT that will be christened at the RSNA meeting.
"I see a lot of people doing cardiac imaging and runoffs in which they are archiving data to DVDs," Young said. "What makes more sense is coming out with a product that can store thin-slice data right there at the CT for six months or a year, then send the data to a tape drive. This keeps you from bogging down your PACS."
Philips Medical Systems will attack slice overload at the source, gathering fewer data. Its Brilliance 64 platform, augmented with an advanced cardiac imaging mode, will capture the heart in just four beats, reducing the volume of data acquired and exposing patients to a lower x-ray dose.
The first rotation, a 4-cm slice, coincides with a single heartbeat. After this, the x-ray tube shuts off, and the detector aligns for the next swipe. This step-and-shoot method keeps going until the heart is completely covered through a total of four scans, one per heartbeat, although not necessarily of four beats spaced equally apart.
"If we have a premature heartbeat, we can ignore that beat all together," said John Steidley, vice president of Philips CT marketing. "That is the really clever thing about this strategy."
GE Healthcare will leverage advances in computing architecture to implement an iterative reconstruction algorithm that promises to improve image quality, particularly for cardiac applications. Instead of going once through the data to create an image, iterative reconstruction makes several passes, improving the spatial resolution while reducing noise.
"If the image is quieter, you can take your foot off the gas and not shoot so much x-ray, saving dose to the patient, or you can make the same exposure and get a quieter, better picture," said Brian Duchinsky, general manager of GE's global CT business.
Getting the most from iterative reconstruction, even with present-day computing platforms, would take hours of postprocessing. But GE will unveil at the RSNA meeting an "ultralight" version that, when triggered as an option, will slow reconstruction from the current pace of 16 to 20 frames per second, "but not to the point that will cause customers to feel bad about the slowdown," Duchinsky said.
Techniques designed to speed or simplify workflow will also dot the exhibit floor. Philips will demonstrate a link between its Brilliance CT and Allura Xper cardiac cath and electrophysiology suites. Cardiac data sets obtained on CT and processed into 3D will help plan interventions and guide the alignment of x-ray-based studies.
"As you put the 3D coronary tree up, you can rotate that image with tableside controls and, doing this, you move the C-arm into the right position," Steidley said. "After that, you can turn on the fluoro, and you don't have to hunt around for the right angle."
The Dutch company will also bring advances in vascular, lung, and colon processing, buoyed by tableside controls for diagnostic as well as interventional studies, and a bariatric table that won't droop from challenges up to 650 pounds.
GE will point to its latest development in volume computer-assisted reading (VCAR) for CT. Colon VCAR is GE's third-generation software for visualizing this anatomy and the first to involve computer-aided detection. Radiologists assess images, while pattern matching algorithms point out tissues with suspicious shapes.
"It looks for shapes characteristic of polyps and highlights them," said Bob Beckett, global product manager for diagnostic oncology applications.
Toshiba will migrate 3D software to the console of its 16-, 32-, and 64-slice scanners, making the life of the emergency room staff a bit easier.
"Whether it's chest pain or a suspected fracture, the assessment can be made immediately without having to network the data or process it on a separate box," Young said.
The technologist's job will become a bit simpler when doing vascular exams, thanks to a connector between the Aquilion CT and injector. For CTs and injectors cabled together with this simple interface, pushing the scan button will trigger the injector to start pumping-a simple improvement but one with critically important results.
"A lot of image quality issues happen as a result of operator error," he said. "So we want to automate the process as much as possible."
With these sometimes simple, other times complex answers, vendors are mouthing a technological mea culpa to the problems created by making CT such a prolific modality. They will have to keep at it if they are to keep up with coming generation of CTs that promise more of the same.
AI Facilitates Nearly 83 Percent Improvement in Turnaround Time for Fracture X-Rays
December 19th 2023In addition to offering a 98.5 percent sensitivity rate in diagnosing fractures on X-ray, an emerging artificial intelligence (AI) software reportedly helped reduce mean turnaround time on X-ray fracture diagnosis from 48 hours to 8.3 hours, according to new research presented at the Radiological Society of North America (RSNA) conference.
The Reading Room: Artificial Intelligence: What RSNA 2020 Offered, and What 2021 Could Bring
December 5th 2020Nina Kottler, M.D., chief medical officer of AI at Radiology Partners, discusses, during RSNA 2020, what new developments the annual meeting provided about these technologies, sessions to access, and what to expect in the coming year.
Can an Emerging PET Radiotracer Enhance Detection of Prostate Cancer Recurrence?
December 14th 2023The use of 68Ga-RM2 PET/MRI demonstrated a 35 percent higher sensitivity rate than MRI alone for the diagnosis of biochemical recurrence of prostate cancer, according to research recently presented at the Radiological Society of North America (RSNA) conference.
RSNA 2020: Addressing Healthcare Disparities and Access to Care
December 4th 2020Rich Heller, M.D., with Radiology Partners, and Lucy Spalluto, M.D., with Vanderbilt University School of Medicine, discuss the highlights of their RSNA 2020 session on health disparities, focusing on the underlying factors and challenges radiologists face to providing greater access to care.
Can AI Improve Detection of Extraprostatic Extension on MRI?
December 4th 2023Utilizing a deep learning-based AI algorithm to differentiate between diagnostic and non-diagnostic quality of prostate MRI facilitated a 10 percent higher specificity rate for diagnosing extraprostatic extension on multiparametric MRI, according to research presented at the recent RSNA conference.
Study: Regular Mammography Screening Reduces Breast Cancer Mortality Risk by More than 70 Percent
November 30th 2023Consistent adherence to the five most recent mammography screenings prior to a breast cancer diagnosis reduced breast cancer death risk by 72 percent in comparison to women who did not have the mammography screening, according to new research findings presented at the annual Radiological Society of North America (RSNA) conference.