AI's Touch Redefines Breast Cancer Detection

A new imaging technology developed by researchers at the University at Buffalo could revolutionize breast cancer screening by detecting tumors in less than a minute—without the discomfort associated with traditional mammography (1^✔ ✔Trusted Source
OneTouch Automated Photoacoustic and Ultrasound Imaging of Breast in Standing Pose

Go to source).

OneTouch-PAT: AI-Powered Photoacoustic and Ultrasound Imaging for Breast Cancer Detection

The experimental system, called OneTouch-PAT, combines photoacoustic and ultrasound imaging to create high-resolution, 3D images powered by artificial intelligence. The breakthrough was detailed in the journal IEEE Transactions on Medical Imaging.

Unlike mammography, which requires painful compression, OneTouch-PAT offers a more comfortable experience. Patients simply stand and gently press their breast against a transparent imaging window while the scan takes place.

The device integrates photoacoustic imaging, which uses laser pulses to heat light-absorbing molecules and generate ultrasound waves, and traditional ultrasound imaging, which detects suspicious lesions. By interleaving both scans automatically, the system eliminates the need for manual operation and reduces operator error.

Deep Learning Reveals Breast Cancer Subtypes

Captured data is processed using a deep learning network, which significantly improves image clarity. The result: sharp, detailed 3D images that reveal tumor characteristics and vascular patterns unique to breast cancer subtypes such as Luminal A, Luminal B, and Triple-Negative Breast Cancer.

In a study involving 61 breast cancer patients and four healthy volunteers, the system successfully identified common breast cancer subtypes and visualized abnormal blood vessel growth associated with tumors.

Luminal A and B tumors showed dense, tumor-associated blood vessels.

Triple-Negative Breast Cancers exhibited chaotic vascular patterns, aiding subtype identification.

Dr. Jun Xia, the study’s lead author and a professor in UB’s Department of Biomedical Engineering, noted: “More work is needed before OneTouch-PAT can be used clinically, but these results are exciting. Our system has the potential to complement existing screening tools and improve early detection.” Breast cancer remains a leading cause of cancer-related deaths worldwide. While mammography is the standard screening tool, it has limitations:

• Painful compression deters some women from regular screening.
• Accuracy decreases in women with dense breast tissue.
• It exposes patients to low-dose radiation.

Ultrasound and MRI can address some of these gaps but come with drawbacks such as high false-positive rates, cost, and limited availability.

OneTouch-PAT offers a painless, radiation-free alternative with rapid imaging capability, making it particularly promising for women with dense breast tissue who are at higher risk of missed diagnoses.

The research team plans to expand studies to larger, more diverse populations and include benign lesions for better diagnostic accuracy. Future improvements will focus on adding more sensors and optimizing data processing to make the system faster and more robust.

Reference:

1. OneTouch Automated Photoacoustic and Ultrasound Imaging of Breast in Standing Pose - (https://ieeexplore.ieee.org/document/11033214/)

Source-Medindia