Post-reconstruction enhancement of [¹⁸F]FDG PET images with a convolutional neural network.

A test group of 25 patients was used to validate the CNN qualitatively and quantitatively with 5 different image sets per patient: 4 min/bed position, 1.5 min/bed position with and without CNN, and 1 min/bed position with and without CNN. Results Difference in hotspot maximum or peak standardized uptake value between the standard 1.5 min and 1.5 min CNN images fell short of significance.

also in 361 other papers

The 1.5–1 min CNN comparison had higher mean rank by all readers for both noise and contrast, all significant without Bonferroni correction but 3 out of 6 comparisons fell just short of significance with the correction, but 1 min CNN had slightly lower mean SUV max and SUV peak .

also in 102 other papers