Photoacoustic and Ultrasound Imaging Combined With AI Used for High-Resolution Breast Imaging

Researchers at the University at Buffalo have developed a new breast imaging system that could dramatically improve cancer detection—without the discomfort of traditional mammograms. Called OneTouch-PAT, the system combines photoacoustic and ultrasound imaging with artificial intelligence to produce high-resolution 3D scans in under a minute, all without painful compression or radiation.

Instead of lying down or undergoing breast squeezing, patients stand and gently press their breast against an imaging window. The device then performs alternating photoacoustic and ultrasound scans, capturing both structural and vascular details. Photoacoustic imaging uses laser pulses to detect blood vessel growth—often a hallmark of tumors—while ultrasound identifies suspicious lesions. The scans are processed by a deep learning algorithm that enhances image clarity and removes noise, offering a clearer view of tumor characteristics.

In early clinical tests involving 61 breast cancer patients and 4 healthy individuals, OneTouch-PAT successfully identified common cancer subtypes, including Luminal A, Luminal B, and Triple-Negative Breast Cancer. Each subtype showed distinct vascular patterns, such as dense blood vessel networks in Luminal cancers and chaotic growth in Triple-Negative cases. These insights could help clinicians not only detect cancer earlier but also classify tumor types more accurately.

OneTouch-PAT may be especially valuable for women with dense breast tissue, where mammograms often fall short. Both ultrasound and photoacoustic imaging are less affected by tissue density, making this system a promising alternative for more inclusive screening. It also reduces operator error by automating the scanning process, ensuring consistency across patients.

While the technology is still in development, the research team—led by Professor Jun Xia—plans to expand testing to include benign lesions and improve data extraction methods. They’re also working to add more sensors and boost imaging speed. Supported by the National Institutes of Health, the project reflects a growing push toward more comfortable, accurate, and accessible breast cancer screening.