A breast scan to detect cancer lasts less than one minute using an experimental system that combines photocular and ultrasound imaging, according to a study in IEEE transactions for medical imaging.
The system does not require painful compression such as mammography. Instead, patients stand and gently press their breasts into a visualization window.
In tests involving four healthy people and 61 patients with breast cancer, it produced clear 3D images of artificial intelligence of common breast cancer subtypes such as lumen A, courtyard B and triple negative breast cancer.
Our system, which is called OneTouch-Pat, combines advanced imaging, automation and artificial intelligence-all of them enhance the comfort of patients. “
Jun Xia, PhD, corresponding author of the study, Professor at the University in Biomedical Engineering of Buffalo
He stresses that “more work is needed before being used in clinical environments, but we are excited about the ability of OneTouch-Pat to increase current imaging methods and help fight this terrible disease”.
Additional authors include researchers in the UB biostatic department. The UB Informatics and Engineering Department. The Breast Imaging Department and the Department of Surgery, both in the Roswell Park Comprehensive Cancer Center. and Windsong Radiology.
The project was supported by the National Institutes of Health.
Breast cancer is one of the main causes of death for women worldwide. Timely detection – most commonly through mammography and ultrasound – has helped to save countless lives.
But every technique has restrictions. Mammography is widely available and relatively cheap, but it is less accurate among women with dense breast tissue, includes radiation and is painful. Ultrasound, which is often used in combination with mammography, is better with dense breast tissue, but can produce falsely positively and its quality depends on the ability of the sonographer.
Other tools such as magnetic resonance imaging are effective but expensive, time -consuming and are not widely available.
Xia and his colleagues have studied the photocular imaging, which works with the laser pulse emission that cause light absorption molecules to warm and expand. This in turn creates ultrasound waves that allow medical professionals to detect blood vessels that often grow more in cancerous tissues.
Usually, these systems require a record to manually scan the breast or rely on separate devices for photocular visualization and ultrasound imaging.
The OneTouch-Pat combines both scans automatically-in other words, there is no possibility of an operator-with the patient in the same position. The device first performs a photocular scan, followed by ultrasound scan, then repeats this pattern in a scattered manner until the entire chest is covered.
The system then processes the data using a network of deep learning to improve the clarity of the image. Depending on the computing power in this step, this can only take a few minutes. Finally, the research team found that the OneTouch-Pat provides a more thorough and clearer view of breast tumors compared to the operator-dependent ultrasound and ultrasound systems.
For example, his 3D images showed unique vascular patterns from the subtype of cancer. This includes richer and more protruding blood vessels associated with tumor in the lumen A and lumen Cancers and high intensity points corresponding to chaotic and abnormal blood -fitted blood that are often observed in triple negative breast cancers.
OneTouch-pat could be particularly useful for women with dense breast tissue, which are often more difficult to diagnose and at a higher risk. This is due to the fact that the system’s ultrasound component is superior to detecting suspicious lesions, and photoconic imaging records the development of blood vessels around these lesions to provide additional information about possible malignancy and type of tumor. Both techniques are less affected by tissue density.
While the results are very promising, Xia says, more studies are needed in a wider population to continue to validate OneTouch-pat. The team designs additional studies to include benign lesions and improve data export methods. Researchers also aim to add more sensors and more powerful imaging tools for improved accuracy and speed.
Source:
Magazine report:
Zhang, h., et al. (2025). OneTouch automated photocular and ultrasound depiction of the breast in posture. IEEE transactions for medical imaging. Doi.org/10.1109/tmi.2025.3578929.
