Breast imagers and their allies cornered vendor representatives during a special session at the SCAR meeting Saturday and demanded more standardization and consistency in the handling of digital breast images.
Breast imagers and their allies cornered vendor representatives during a special session at the SCAR meeting Saturday and demanded more standardization and consistency in the handling of digital breast images.
Although digital mammography could potentially provide important patient benefits, currently available systems require too much time for reading and managing images, users said. And differences in presentation algorithms can change the appearance of an image generated on one digital capture system when it is displayed on another vendor's workstation. Session attendees also asked for a common toolbox in all digital mammography workstations.
Responses from the vendor reps were, for the most part, muted. Although more than a dozen participated in a panel at the close of the five-hour session, their replies were necessarily short and failed to rebut many of the complaints raised in the session.
In pushing for standardization and consistency, breast imagers are contending with commercial imperatives that could be tough to overcome. Vendors try to develop equipment designs and features, including display algorithms, that give them a competitive edge. Regulatory issues have also been a factor. Until now, for example, the FDA, which must approve digital mammography systems, has linked digital capture technology and display algorithms.
Nonetheless, breast imagers insisted that the current situation is untenable.
As digital mammography first evolved, vendors were told to build mammography silos to maintain image integrity, said Dr. Margarita Zuley from the Elizabeth Wende Breast Imaging Clinic in Rochester, NY. But sending mammograms between facilities, moving them into a PACS, or viewing them on a different vendor's soft-copy workstation can be problematic because of the various ways they can be interpreted from system to system.
"We want to be able to pick any gantry based on our specific patient population, view the resulting images on any soft-copy workstation, store the images on any hospital PACS, and then be able to send that image out facility-wide," Zuley said.
Image presentation currently varies from display to display, image processing algorithms vary from vendor to vendor, and mammographers are confined in their choice of processing algorithm, she said.
"This is hurting our patients," Zuley said.
Citing a study by Dr. Eric A. Berns et al that was presented at the 2004 American Roentgen Ray Society meeting, Dr. Judith Wolfman a radiologist at the Lynn Sage Comprehensive Breast Center at Northwestern University, said that although digital mammography reduced the time needed to image a patient by 33%, it actually increased interpretation time by 59%,
This increased time is like a pencil in the eye when you're reading hundreds of cases a day, said Dr. Dianne Georgian-Smith from Massachusetts General Hospital. Her experience with digital mammography led her to coin the phrase "knobology": the science of learning how to use all the knobs on new digital mammography workstations, which differ from vendor to vendor.
In addition to common toolkits, mammographers requested consistency in display. Breast images have to be presented back to back in the same size every time, and new images should appear the same way as priors, said David Clunie, chief technology officer for RadPharm.
Streamlining the entire digital mammography workflow process is an absolute requirement, according to moderator J. Anthony Siebert, Ph.D., a professor of radiology at the University of California, Davis, and current SCAR chair. Reducing the amount of image manipulation needed to improve efficiency of interpretation would achieve that goal.
A study done 30 years ago, which reported that radiation introduced by mammograms may create more cancers than it catches, brought imagers and vendors together to tackle the issue of radiation dose, said Dr. Wendy Logan Young, a veteran breast imager at the Elizabeth Wende Breast Imaging Clinic. As a result, the technology quickly improved.
"We are now on the verge of a digital mammography era. There are still tremendous problems, however, and we need to disseminate that information to others," she said.
Mammography Study Suggests DBT-Based AI May Help Reduce Disparities with Breast Cancer Screening
December 13th 2024New research suggests that AI-powered assessment of digital breast tomosynthesis (DBT) for short-term breast cancer risk may help address racial disparities with detection and shortcomings of traditional mammography in women with dense breasts.
FDA Clears Updated AI Platform for Digital Breast Tomosynthesis
November 12th 2024Employing advanced deep learning convolutional neural networks, ProFound Detection Version 4.0 reportedly offers a 50 percent improvement in detecting cancer in dense breasts in comparison to the previous version of the software.