TABLE 5.
Entorhinal cortex texture and volume in classifying NC vs. MCI.
| NC vs. MCI | ROC analysis AUC | 95% CI | P-value |
| Entorhinal cortex | |||
| Texture features | |||
| ASM | 0.618 | 0.563–0.674 | <0.001 |
| Contrast | 0.664 | 0.611–0.718 | <0.001 |
| Correlation | 0.671 | 0.617–0.725 | <0.001 |
| Variance | 0.604 | 0.548–0.660 | <0.001 |
| Sum average | 0.618 | 0.562–0.674 | <0.001 |
| Sum Variance | 0.641 | 0.586–0.695 | <0.001 |
| Entropy | 0.632 | 0.577–0.687 | <0.001 |
| Cluster shade | 0.608 | 0.551–0.666 | <0.001 |
| Volumetric and thickness | |||
| Erc. volume | 0.735 | 0.686–0.784 | <0.001 |
| Erc. thickness | 0.659 | 0.604–0.713 | <0.001 |
| Features combination | |||
| Texture (ASM, correlation, variance, sum average, and cluster shade) | 0.710 | 0.656–0.762 | <0.001 |
| Texture and Erc. volume | 0.740 | 0.689–0.791 | <0.001 |
| Hippocampus | |||
| Hippocampal volume | 0.762 | 0.715–0.809 | <0.001 |
NC, normal controls; MCI, mild cognitive impairment; ROC, receiver operating characteristic; AUC, area under curve, CI, confidence interval; ASM, angular second moment; Erc, entorhinal cortex.