A new ultrasound processing method from Johns Hopkins can distinguish fluid-filled cysts from potentially cancerous solid breast masses with near-perfect accuracy, promising fewer false alarms, fewer biopsies and less anxiety for patients.
A new ultrasound technology developed at Johns Hopkins University could spare many patients from unnecessary biopsies and sleepless nights by sharply reducing false alarms in breast cancer screening.
In early tests with patients, radiologists using the new method correctly identified whether a breast mass was fluid-filled or solid 96% of the time. Using standard ultrasound tools on the same masses, their accuracy was 67%.
That difference matters because benign, fluid-filled cysts can look a lot like potentially cancerous solid tumors on traditional ultrasound images, especially in people with dense breast tissue. When doctors cannot be sure, they often order follow-up scans or biopsies, which can be painful, costly and stressful.
The new approach directly tackles that long-standing problem, according to senior author Muyinatu “Bisi” Bell, a biomedical and electrical engineer at Johns Hopkins who specializes in imaging technology.
“This is important because the benefits of ultrasound in breast cancer detection can be limited by the similar appearance of benign fluid masses and solid masses, which can be cancerous,” Bell said in a news release.
The research, published in the journal Radiology Advances, focuses not on changing the ultrasound machines themselves, but on how the signals they collect are processed.
Standard ultrasound sends sound waves into the breast and records the echoes that bounce back from tissue and any masses. Those echoes are converted into an image based on signal strength, or amplitude, which shows up as blacks, whites and grays.
In dense breast tissue, however, sound waves scatter before they reach a mass, creating what researchers call acoustic clutter. A simple fluid-filled cyst that should appear black can instead look gray inside, similar to how a solid, possibly cancerous mass appears. That ambiguity is a major reason ultrasound can lead to false positives and extra testing.
The Johns Hopkins team’s method keeps the same hardware and raw data but analyzes the signals differently. Instead of focusing on how strong each echo is, the new system looks at how similar each signal is to its neighbors. The researchers describe this as a coherence-based approach.
By emphasizing coherence, the method produces cleaner, more reliable images that better separate fluid from solid structures. On top of that, the system assigns each mass a numerical score. Masses above a certain threshold are flagged as worrisome, while those below it are more likely to be benign.
That combination of clearer images and an objective score is key.
“It’s really exciting because what we do is take the same ultrasound data, sensed through the same process, but we change the signal processing and do a much better job at interpreting these images,” Bell added. “When we combine the visual with a number score, that’s when the technology really shows the greatest improvement. It takes away decision fatigue by automating something that would ordinarily require more thought and interpretation.”
In a study of 132 patients, radiologists using the new technique were able to distinguish fluid from solid masses with near-perfect accuracy, according to the research team. That improvement could be especially valuable for people with dense breasts, whose mammograms and ultrasounds are often harder to interpret.
Breast cancer screening typically starts with mammography for women over 40, but mammograms can be less informative in dense breast tissue, which appears white on the image, similar to many tumors. Ultrasound is often the next step, yet it, too, has limitations in dense tissue. Tools that make ultrasound more definitive could reduce the cycle of repeat imaging and biopsies that many patients endure.
The findings point to a meaningful shift in everyday practice, according to co-author Eniola Oluyemi, a diagnostic radiologist at Johns Hopkins Medicine.
“The results of this study are important for our specialty because they suggest that this technique can improve our ability to differentiate between solid masses and certain types of cysts that can mimic solid masses on ultrasound,” Oluyemi said in the news release. “This improved diagnostic certainty can lead to fewer false positive results and decrease the need for follow-up and biopsies, thus helping to give our patients increased peace of mind at the time of the initial exam.”
Beyond improving stand-alone ultrasound, the team sees potential in pairing their method with artificial intelligence. Existing AI tools can already help distinguish benign from malignant masses in ultrasound images. If those tools are fed cleaner, coherence-based images and the new numerical scores, doctors might be able to make confident decisions during the first ultrasound visit, rather than waiting for additional tests.
The researchers are also thinking ahead to how this technology might reach patients outside of hospitals and large imaging centers. Portable and handheld ultrasound devices are becoming more common and less expensive, raising the possibility of broader access in community clinics and, someday, at home.
Bell envisions a future where people could use simplified ultrasound tools as part of self-exams, then rely on automated analysis for guidance.
“My long-term vision is that as society becomes more self-sufficient and ultrasounds becomes even less expensive than they are today, patients might not have to go to a hospital or specialized clinic—our approach could instead be performed at home,” Bell added. “With an inexpensive ultrasound scan, a single number extracted from a coherence-based ultrasound image could tell whether or not a palpable breast lump is something to be concerned about.”
For now, the next steps include further testing in larger and more diverse patient groups, and working with clinicians to integrate the method into existing ultrasound systems. If those efforts succeed, the technology could help transform one of the most anxiety-filled moments in health care into a faster, clearer and less invasive experience.
Source: Johns Hopkins University