TABLE 2.
The high-frequency features selected by cross-validation with different methods.
| Two-sample t-test, autocorrelation, and Fisher score |
Two-sample t-test, autocorrelation, and Lasso |
Two-sample t-test, autocorrelation, and mRMR |
|||||||||
| Feature (ID) | Times | Brain region | R | Feature (ID) | Times | Brain region | R | Feature (ID) | Times | Brain region | R |
| LZHGE (6486) | 500 | Cingulum_Post_L | 1/2 | Busyness (26056) | 468 | Frontal_Mid_Orb_R | 2 | LZHGE (6486) | 495 | Cingulum_Post_L | 1/2 |
| LZHGE (6529) | 500 | Cingulum_Post_R | 1/2 | Homogeneity (24775) | 467 | Vermis_7 | 3/2 | LZHGE (6529) | 488 | Cingulum_Post_R | 1/2 |
| LZHGE (11474) | 500 | Cingulum_Post_L | 2/3 | Variance (27442) | 430 | Parietal_Sup_L | 2 | LZHGE (11517) | 486 | Cingulum_Post_R | 2/3 |
| LZHGE (11517) | 500 | Cingulum_Post_R | 2/3 | Contrast (14273) | 419 | Cerebelum_6_R | 2/3 | ZSN (27076) | 445 | Occipital_Sup_R | 2 |
| Variance (27442) | 480 | Parietal_Sup_L | 2 | Complexity (9287) | 402 | Cerebelum_6_R | 1/2 | LZHGE (11474) | 441 | Cingulum_Post_L | 2/3 |
| LZLGE (24803) | 447 | Vermis_7 | 3/2 | Coarseness (6489) | 399 | Cingulum_Post_L | 1/2 | Variance (27442) | 441 | Parietal_Sup_L | 2 |
| Strength (18834) | 428 | Temporal_Inf_R | 1 | Kurtosis (7485) | 397 | Parietal_Sup_L | 1/2 | SZLGE (11471) | 420 | Cingulum_Post_L | 2/3 |
| Coarseness (6489) | 423 | Cingulum_Post_L | 1/2 | Busyness (26314) | 394 | Cingulum_Ant_R | 2 | SZLGE (18179) | 398 | Temporal_Mild_L | 1 |
| ZSN (27076) | 423 | Occipital_Sup_R | 2 | LZHGE (11517) | 391 | Cingulum_Post_R | 2/3 | Coarseness (6489) | 339 | Cingulum_Post_L | 1/2 |
| GLN (16497) | 420 | Cingulum_Post_R | 1 | Kurtosis (5292) | 383 | Frontal_Mid_R | 1/2 | ZSV (28977) | 320 | Cerebelum_Crus2_R | 2 |
Under the sample disturbance of five-fold cross-validation, we carried out three different kinds of composite function disturbances separately to screen features in the training dataset and repeated the process 100 times. We calculated the number of occurrences of each retained feature, ranging from 0 to 500, and listed the top 10 most frequently appearing features here; they all originated from the sMRI modality. Three stable high-frequency features were verified, and their identification numbers were 11517, 27442, and 6489. The kurtosis feature belongs to the “global” category; the homogeneity and variance features belong to the “gray-level co-occurrence matrix” category; the GLN, ZSN, LZHGE, SZLGE, LZLGE, and ZSV features belong to the “gray-level size zone matrix” category; and the strength, coarseness, busyness, complexity, and contrast features belong to the “neighborhood gray-tone difference matrix” category. Notably, the variance and contrast features could also originate from the “global” and “gray-level co-occurrence matrix” category, respectively. The “R” represents weights to bandpass sub-bands in wavelet filtering. Lasso, least absolute shrinkage and selection operator; mRMR, max-relevance and min-redundancy; ID, identify number; sMRI, structural magnetic resonance imaging; L, left; R, right; Post, posterior; Sup, superior; Inf, inferior; Mid, middle; Orb, orbital; Ant, anterior; GLN, gray-level nonuniformity; ZSN, zone-size nonuniformity; LZHGE, large zone high-gray-level emphasis; SZLGE, small zone low gray-level emphasis; LZLGE, large zone low-gray-level emphasis; ZSV, zone-size variance.