CHICAGO - Nov 26, 2025 - GE HealthCare (Nasdaq: GEHC) announced today that it has received FDA Premarket Authorization for Pristina Recon DL, an advanced 3D mammography image reconstruction technology. Powered by deep learning, Pristina Recon DL sets a new standard in image definition and sharpness.
Breast cancer remains one of the most common cancers among women, with one in eight expected to face a diagnosis in their lifetime[2] and an estimated 1.1 million breast cancer–related deaths projected annually by 2050. As the burden of disease continues to rise, the advancement of AI-powered technologies holds remarkable promise in supporting early detection, accurate diagnosis and helping elevate the quality of care.
Pristina Recon DL leverages two deep learning models working in sequence to enable separation of meaningful signal from noise. The first model reconstructs high fidelity 3D volumes with greater purity – minimizing artifacts and perceived noise1. The second model is trained to enhance the visualization of clinically relevant information in the DL synthesized 2D view.
Ad Statistics
Times Displayed: 344592
Times Visited: 21056 MIT labs, experts in Multi-Vendor component level repair of: MRI Coils, RF amplifiers, Gradient Amplifiers Contrast Media Injectors. System repairs, sub-assembly repairs, component level repairs, refurbish/calibrate. info@mitlabsusa.com/+1 (305) 470-8013
Deep learning models reconstruct images with scientific precision
Pristina Recon DL is an enhancement to GE HealthCare’s Pristina ViaTM system. It is the first mammography technology to use deep learning in combination with iterative reconstruction to provide outstanding digital breast tomosynthesis (DBT) image quality without compromising on patient dose. Pristina Via with Recon DL[3] utilizes NVIDIA RTX accelerated computing technology to execute its advanced image reconstruction, delivering fast and accurate images in the exam room and for clinical diagnosis.
“Pristina Recon DL was born out of a deep commitment to our customers – listening closely to their feedback and working hand-in-hand with radiologists to enhance image quality and clarity,” said Jyoti Gupta, PhD, President and CEO, Women’s Health and X-ray at GE HealthCare. “By applying advanced deep learning technologies, we’re shaping the future of breast imaging – one defined by uncompromised image quality, faster workflows, and greater confidence in early cancer detection.”
A recent study showed that Pristina Recon DL overall image quality was preferred by breast radiologists in 99.1% of the image reviews compared to previous DBT reconstruction.[4] It also offers superior performance in the detection of microcalcification clusters and masses, demonstrated in a trial with modeled clinical data.[5]
