Table 6.

GLRLM-based radiomic features for real and synthetic T2W for CycleGAN and DC²Anet models.

Features	Real T2W	Synthetic T2W-CycleGAN	Synthetic T2W-DC2Anet	95% CI of Diff
	Mean ± SE	Mean ± SE	Mean ± SE	Real T2W vs. Synthetic T2W-CycleGAN	Real T2W vs. Synthetic T2W-DC2Anet
Grey Level Nonuniformity	73.95 ± 0.58	73.89 ± 0.84	74.66 ± 0.94	−2.821 to 2.937	−3.590 to 2.168
High Grey Level Run Emphasis	60.38 ± 2.3	56.89 ± 2.43	69.63 ± 1.56	−4.241 to 11.21	−16.87 to −1.630 *
Long Run High Grey Level Emphasis	92.88 ± 1.32	92.84 ± 1.95	95.25 ± 1.94	−6.258 to 6.338	−8.670 to 3.926
Long Run Low Grey Level Emphasis	29.69 ± 0.59	28.40 ± 0.60	25.88 ± 0.29	−0.5560 to 3.138	1.973 to 5.667 *
Low Gray Level Run Emphasis	0.62 ± 0.007	0.62 ± 0.006	0.61 ± 0.004	−0.0130 to 0.0300	−0.0068 to 0.0362
Run Length Nonuniformity	53.88 ± 1.57	55.08 ± 1.18	53.63 ± 0.94	−5.690 to 3.296	−4.237 to 4.749
Short Run Emphasis	0.48 ± 0.01	0.50 ± 0.01	0.47 ± 0.01	−0.0579 to 0.0336	−0.0313 to 0.0601

* Significant difference.