New ultrasound method accurately distinguishes fluid from solid breast masses

New ultrasound method accurately distinguishes fluid from solid breast masses

New ultrasound technology developed at Johns Hopkins can distinguish fluid from solid breast masses with near-perfect accuracy, an advance that could save patients, especially those with dense breast tissue, unnecessary follow-ups, painful procedures and anxiety.

In initial tests with real patients, doctors using the new method identified masses accurately 96% of the time - they were correct only 67% of the time when they analyzed the same masses with their regular machines.

"This is important because the benefits of ultrasound in breast cancer detection may be limited by the similar appearance of benign fluid masses and solid masses that may be cancerous," said lead author Muyinatu "Bisi" Bell, a biomedical and electrical engineer at Johns Hopkins University who specializes in imaging technology. "Our achievement will change the way breast cancer is diagnosed. Radiologists can have immediate confidence in the diagnosis. And patients will not be sent for biopsies and invasive procedures when there is more confidence that a mass is not a cause for concern."

The government-funded work is published today inAdvances in radiology.

It is recommended that every woman over 40 have a mammogram to detect breast cancer early. However, in women with dense breast tissue, the results may be inconclusive. These women are often next sent for an ultrasound scan - a technology that also has problems with dense breast tissue.

Ultrasound works by sending sound waves through a probe into the chest. The sound bounces off structures such as masses and is recorded. If it works perfectly, the sound travels directly from the mass back to the probe. However, with dense chest problems, sound is scattered before reaching the mass, causing “acoustic noise” in the image. A benign, fluid-filled cyst that should appear black on pictures often looks gray inside, just as a cancerous growth would look.

The new process does not change the way ultrasound is generated, but rather improves the processing of the signals. Traditional ultrasound is based on the amplitude of signals and converts high and low signals into black, white or gray tones. The new method is “coherence-based,” meaning the image depends on how similar signals are to neighboring signals.

In addition to providing cleaner images, the new system makes it even easier for radiologists by providing a numerical rating for each mass - only those above a certain threshold are considered worrisome.

It's really exciting because we're taking the same ultrasound data, acquired using the same process, but we're changing the signal processing and we're able to interpret those images much better. When we combine the visual with a numerical value, the technology actually shows the greatest improvement. It eliminates decision fatigue by automating something that would normally require more thought and interpretation.”

Muyinatu “Bisi” Bell, a biomedical and electrical engineer at Johns Hopkins University

A study of 132 patients found that radiologists can correctly identify masses 96% of the time using the new technology, compared to 67% of the time with traditional ultrasound.

“The results of this study are important to our field because they suggest that this technique may improve our ability to differentiate between solid masses and certain types of cysts that can mimic solid masses on ultrasound,” said co-author Eniola Oluyemi, a diagnostic radiologist at Johns Hopkins Medicine. “This improved diagnostic confidence can result in fewer false positive results and reduce the need for follow-up examinations and biopsies, helping to provide our patients with greater confidence at the time of initial evaluation.”

Existing artificial intelligence can distinguish between benign and cancerous masses in ultrasound images. The team believes their innovation, along with AI, could allow doctors to quickly determine the composition of a mass and determine whether it is cancer during an initial ultrasound appointment.

Bell also hopes the innovation could one day become something people can use at home as part of a breast self-exam.

“My long-term vision is that as society becomes more self-sufficient and ultrasounds become even cheaper than they are today, patients may no longer need to go to a hospital or specialty clinic – our approach could be done at home instead,” Bell said. “With a low-cost ultrasound scan, a single number extracted from a coherence-based ultrasound image could indicate whether or not a palpable lump in the breast is a cause for concern.”

Authors, all from Johns Hopkins, include Arunima Sharma; Madhavi Tripathi; Emily B. Ambinder; Lisa A. Mullen; Babita Panigrahi; Joanna Rossi; Nethra Venkatayogi and Kelly S. Myers.

Sources: