The Onetouch-Pat system detects breast cancer in less than a minute without compression

According to research in the study

The system does not require painful compression like mammography. Instead, patients stand and gently press the breast against the imaging window.

In tests involving four healthy people and 61 patients with breast cancer, this produced clear, artificial 3D images powered by the intelligence of the common subtypes of breast cancer, such as Luminal A, Luminal B and triple negative breast cancer.

Our system, which is called Onetouch-Pat, combines advanced imaging, automation and artificial intelligence-while increasing the comfort of patients. “

Dr. Xia, correspondent author, professor at the University of Buffalo’s Department of Biomedical Engineering

He emphasizes that “more work is needed before it can be used in clinical conditions, but we are excited about the potential of Onetouch-Pat to increase current imaging methods and help in the fight against this terrible disease.”

Additional authors are researchers from the UB Biostatistics Department; Department of Computer Science and Engineering UB; Breast imaging department and surgery department, both at Roswell Park Comprehensive Cancer Center; and windsong Radiology.

The work was supported by the National Institutes of Health.

Breast cancer is one of the main causes of women’s death around the world. Early detection – most often through mammograms and ultrasounds – helped save countless life.

But each technique has restrictions. Mammography is widely available and relatively inexpensive, but it is less accurate among women with thick breast tissue, covers radiation and is painful. Ultrasound, which is often used in combination with mammography, is better with thick breast tissue, but can produce falsely positive, and its quality depends on the skills of the sonograph.

Other tools, such as MRI, are effective, but expensive, time -consuming and are not widely available.

XIA and colleagues studied photoacoustic imaging that works, emitting laser impulses that cause the light absorbing molecules heat and expand. This, in turn, creates ultrasonic waves that allow doctors to detect blood vessels that often grow in cancer tissues.

Usually, these systems require a sonographer manual breast scanning or rely on separate devices for photoacoustic imaging and imaging of ultrasound.

Onetouch-Pat combines both scans of automatically-other words, there is no potential of the operator’s error-a patient in the same standing position. The device first performs a photoacoustic scan, and then scanning ultrasound, and then repeats this pattern in an intertwined way until the whole breast is covered.

Then the system processes data using a deep learning network to improve image transparency. Depending on the computing power in this step, it can only take a few minutes. Ultimately, the research team stated that Onetouch-Pat provides a more in-depth and clearer view of breast tumors compared to photoacoustic and ultrasonic imaging systems that are dependent on the operator.

For example, his 3D images showed unique vascular patterns of the cancer subtype. This includes richer and more visible blood vessels associated with cancer in Luminal A and Luminal B, as well as high intensity stains, which correspond to the chaotic and abnormal blood supply often observed in the triple negative breast cancer.

Onetouch-Pat can be particularly helpful for women with thick breast tissue, which are often more difficult to diagnose and at a higher risk. This is due to the fact that the ultrasonic component of the system stands out in the detection of suspicious changes, and photoacoustic imaging reflects the growth of blood vessels around these changes to provide additional information on the potential cancer and tumor type. Both techniques are less affected by tissue density.

Although the results are promising, XIA says, further research is needed in a wider population to continue to confirm Onetouch-Pat. The team plans additional tests to include mild changes and improve data extraction methods. Scientists are also aimed at adding more sensors and more solid imaging tools to improve accuracy and speed.