Virtual breast to provide clinicians with practice in cancer detection
With the aim of improving clinicians' interpreting of ultrasound elstography images for breast cancer diagnosis, researchers at Michigan Technological University (MTU) have created a fake breast – that's silicon fake, not silicone fake.
With the ability to pinpoint potential tumors throughout the body, including the breasts, ultrasound elastography is gaining in popularity as a screening tool providing a way to avoid the often needless worry resulting from suspicious mammograms, of which only a minority actually lead to a cancer diagnosis.
The imaging technique maps the elastic properties of soft tissue revealing potential cancer tissues that are usually stiffer than surrounding healthy tissue. While potential tumors are clearly visible in some images, others will be more difficult to discern. The problem is that the technology is still relatively new and relies on clinicians who may not have a lot of practice to interpret the images.
"Depending on who does the reading, the accuracy can vary from 95 percent to 40 percent," says Jingfeng Jiang, a biomedical engineer at MTU. "Forty percent is very bad – you get 50 percent when you toss a coin. In part, the problem is that ultrasound elastography is a new modality, and people don’t know much about it."
This is what prompted Jiang and his team to set about building a virtual breast. Using data from the Visible Human Project, which gathered thousands of cross-sectional images from a female cadaver, the team was able to create a 3D, computer-generated "phantom" that mimics the intricacy of the real thing with details such as different tissue types, ligaments and milk ducts.
Clinicians are able to gain experience looking for cancers in the safety of the lab by applying virtual ultrasound elastography to the virtual breast and then analyzing the resulting images. Jiang hope the virtual breast and accompanying software will one day be made available to anyone who needs training with the imaging technique.
Jiang and his team presented their work at the IEEE Ultrasonics Symposium in Chicago last month.