GE HealthCare’s Precision DL Deep Learning Image Processing Software Earns FDA Nod

GE HealthCare has earned U.S. Food and Drug Administration (FDA) 510(k) clearance of its Precision DL deep learning-based image processing software, which is included in the company’s Effortless Recon DL portfolio.
 
Precision DL offers image quality benefits usually associated with hardware-based time-of-flight (ToF) reconstruction, including, according to GE HealthCare, improved contrast-to-noise ratio, contrast recovery, and quantitative accuracy.
 
The AI-based technology is available on the company’s PET/CT, Omni Legend, which enables faster scan times and small lesion detectability. Combining it with Precision DL transitions ToF tech to higher PET/CT performance and helps clinicians decode coincidence events at fine resolutions for informed diagnoses and treatment planning.
 
“We can’t treat what we don’t see, which is why we require precise image quality to help diagnose, plan treatment for, and monitor disease,” Prof. Flavio Forrer, MD, Ph.D., Chairman of Nuclear Medicine in the Division of Radiology and Nuclear Medicine at Kantonsspital St. Gallen in Switzerland, told the press. “Precision DL enhances image quality – enabling us to spot small lesions, including on images obtained with very low dose injections and short bedtimes, to potentially start treatment and monitoring early, which might result in improved patient outcomes. Additionally, Omni Legend offers a streamlined, simple solution that helps enable technologists to increase efficiency, enhance patient care, and reduce potential radiation exposure to medical staff.”
 
“One of the main advantages of moving fully into the future of AI and deep learning is making state-of-the-art imaging accessible to more practices, across more care areas than ever before,” added Jan Makela, president and CEO, Imaging, GE HealthCare. “Clinicians are seeing the value of applying deep learning technology to enhance image quality with our multi-modality family of Effortless Recon DL applications, which already includes AIR Recon DL for MR, TrueFidelity for CT, and Helix DL for X-ray. Now we are proud to add Precision DL for PET/CT, enabling more precise and personalized care across healthcare systems’ imaging departments.”
 
Precision DL was built with a sophisticated deep neural network trained on thousands of images created with various reconstruction methods, including ToF reconstruction, to provide image quality performance usually associated with hardware-based ToF reconstruction.
 
According to GE HealthCare, using Precision DL can provide 11% improvement average in contrast recovery and 23% improvement on overage contrast-to-noise ratio. It also touts 42% average increase in small, low-contrast detectability and 14% improvement in feature quantification accuracy.