From: PET/MR fusion texture analysis for the clinical outcome prediction in soft-tissue sarcoma
Class | Feature number | AUC value |
---|---|---|
No fusion-based features | ||
T1-weighted MR images | 52 | 0.7196 ± 0.0340 |
T2-weighted MR images | 71 | 0.6985 ± 0.0228 |
PET images | 79 | 0.7254 ± 0.0366 |
Image-level fusion based features | ||
T1/PET Image Fusion (0.1) | 85 | 0.7459 ± 0.0414 |
T1/PET Image Fusion (0.2) | 87 | 0.7462 ± 0.0504 |
T1/PET Image Fusion (0.3) | 78 | 0.7533 ± 0.0463 |
T1/PET Image Fusion (0.4) | 83 | 0.7523 ± 0.0420 |
T1/PET Image Fusion (0.5) | 77 | 0.7567 ± 0.0386 |
T1/PET Image Fusion (0.6) | 76 | 0.7619 ± 0.0448 |
T1/PET Image Fusion (0.7) | 75 | 0.7631 ± 0.0432 |
T1/PET Image Fusion (0.8) | 70 | 0.7407 ± 0.0338 |
T1/PET Image Fusion (0.9) | 73 | 0.7306 ± 0.0365 |
T2/PET Image Fusion (0.1) | 90 | 0.7411 ± 0.0442 |
T2/PET Image Fusion (0.2) | 83 | 0.7519 ± 0.0438 |
T2/PET Image Fusion (0.3) | 83 | 0.7503 ± 0.0420 |
T2/PET Image Fusion (0.4) | 75 | 0.7392 ± 0.0328 |
T2/PET Image Fusion (0.5) | 70 | 0.7215 ± 0.0283 |
T2/PET Image Fusion (0.6) | 81 | 0.7084 ± 0.0244 |
T2/PET Image Fusion (0.7) | 72 | 0.7041 ± 0.0226 |
T2/PET Image Fusion (0.8) | 66 | 0.6957 ± 0.0195 |
T2/PET Image Fusion (0.9) | 69 | 0.6885 ± 0.0167 |
Matrix-level fusion based features | ||
T1/PET Matrix Fusion | 90 | 0.7216 ± 0.0355 |
T2/PET Matrix Fusion | 95 | 0.7441 ± 0.0464 |
Feature-level fusion based features | ||
T1/PET Feature Concatenation | 131 | 0.7231 ± 0.0359 |
T2/PET Feature Concatenation | 150 | 0.7126 ± 0.0335 |
T1/PET Feature Average | 85 | 0.7249 ± 0.0318 |
T2/PET Feature Average | 95 | 0.7366 ± 0.0416 |