Skip to main content

Table 2 The SNR, SUVmax, and TBR of different acquisition durations images with Gaussian and deep learning filter

From: Sub-minute acquisition with deep learning-based image filter in the diagnosis of colorectal cancers using total-body 18F-FDG PET/CT

Parameter

Gaussian filter

Deep learning filter

10S

20S

30S

60S

120S

300S

10S

20S

30S

60S

120S

SNR

           

 Liver

3.3 ± 0.7

4.6 ± 1.0

5.6 ± 1.2

8 ± 1.9

11.1 ± 3.3

17.0 ± 4.4

8.4 ± 4.0

14.7 ± 6.2

18.7 ± 6.7

26.4 ± 8.1

32.8 ± 9.2

 Aorta

3.7 ± 0.9

5.1 ± 1.2

6.2 ± 1.5

8.6 ± 2.2

11.9 ± 3.7

18.8 ± 6.9

11.0 ± 5.2

16.7 ± 6.9

19.4 ± 7.3

24.6 ± 7.5

30.5 ± 12.5

SUVmax

           

 Lesion of CRCs

26.1 ± 14.8

24.0 ± 14.0

23.4 ± 13.9

22.8 ± 14.5

22.3 ± 14.8

21.6 ± 13.9

21.7 ± 13.4

20.4 ± 13.1

19.9 ± 12.9

19.5 ± 13.3

19.1 ± 13.4

 Liver metastases

10.3 ± 6.0

9.6 ± 5.9

9.4 ± 5.8

8.8 ± 5.3

8.5 ± 5.1

8.4 ± 5.2

8.3 ± 5.2

7.8 ± 5.2

7.6 ± 5.0

7.3 ± 4.9

7.2 ± 4.9

TBR

           

 Lesion of CRCs

10.5 ± 5.3

9.7 ± 5.0

9.4 ± 4.9

9.2 ± 5.1

9.0 ± 5.2

8.8 ± 4.9

8.7 ± 4.5

8.2 ± 4.6

8.1 ± 4.5

7.9 ± 4.6

7.8 ± 4.7

 Liver metastases

4.5 ± 2.7

4.2 ± 2.6

3.9 ± 2.3

3.8 ± 2.3

3.7 ± 2.2

3.7 ± 2.2

3.6 ± 2.3

3.9 ± 2.2

3.3 ± 2.2

3.2 ± 2.1

3.2 ± 2.1

TAR

6.5 ± 4.1

6.9 ± 4.4

6.9 ± 4.2

7.1 ± 4.1

7.1 ± 4.2

7.5 ± 4.4

7.4 ± 4.9

7.5 ± 5.0

7.4 ± 5.0

7.2 ± 4.7

7.1 ± 4.6