Precision DL, a deep learning-based software which will be available on GE HealthCare’s Omni Legend PET/CT device, reportedly increases the detectability of small, low-contrast lesions by 42 percent.
The Food and Drug Administration (FDA) has granted 510(k) clearance for Precision DL (GE HealthCare), an artificial intelligence (AI)-enabled image processing software, which may offer significant improvements in contrast-to-noise ratio (CNR), the accuracy of feature quantification, and the diagnosis of small lesions on positron emission tomography (PET)/ computed tomography (CT).
Engineered with a deep neural network trained on thousands of images via multiple reconstruction methods, Precision DL will be accessible through the Omni Legend PET/CT device (GE HealthCare).
The company said Precision DL offers a variety of imaging enhancement benefits including:
• an average 42 percent increase in the detection of small, low-contrast lesions;
• an average 23 percent improvement in CNR; and
• a 14 percent improvement in the accuracy of feature quantification.
“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 outcomes,” noted Flavio Forrer, M.D., Ph.D., the chairman of nuclear medicine at Kantonsspital St. Gallen in Switzerland.
(Editor’s note: For related content, see “GE Healthcare Launches Omni Legend PET/CT System at EANM Congress.”)
CT Study: AI Algorithm Comparable to Radiologists in Differentiating Small Renal Masses
May 14th 2024An emerging deep learning algorithm had a lower AUC and sensitivity than urological radiologists for differentiating between small renal masses on computed tomography (CT) scans but had a 21 percent higher sensitivity rate than non-urological radiologists, according to new research.
What a New Meta-Analysis Reveals About Fractional Flow Reserve Assessment with Computed Tomography
May 13th 2024While acknowledging variable accuracy overall with CT-derived fractional flow reserve (FFR-CT) values, researchers found that the accuracy rate increased to 90 percent for FFR-CT values greater > 0.90 and < 0.49.
MRI-Based Deep Learning Algorithm Shows Comparable Detection of csPCa to Radiologists
May 8th 2024In a study involving over 1,000 visible prostate lesions on biparametric MRI, a deep learning algorithm detected 96 percent of clinically significant prostate cancer (csPCa) in comparison to a 98 percent detection rate for an expert genitourinary radiologist.