Skip to main content

Table 6 Image quality quotation on a 3-point scale, for the PET 33, PET33 + SP, PET50, PET50 + SP and PET100 images

From: Clinical and phantom validation of a deep learning based denoising algorithm for F-18-FDG PET images from lower detection counting in comparison with the standard acquisition

  PET33 PET33 + SP PET100 PET50 PET50 + SP PET100 PET100 PET100 + SP
30 patients 110 patients 20 patients (BMI > 30)
Level 1: insufficient quality, interpretation impossible 25 (83.3%) 4 (13.3%) 0 (0%) 18 (16.3%) 0 (0%) 0 (0%) 0 (0%) 0 (0%)
Level 2: insufficient quality but interpretation possible 5 (16.7%) 18 (60%) 5 (16.7%) 90 (81.8%) 17 (15.5%) 16 (14.5%) 8 (40%) 4 (20%)
Level 3: image of good quality 0 (0%) 8 (26.7%) 25(83.3%) 2 (1.8%) 93 (84.5%) 94 (85.5%) 12 (60%) 16 (80%)