| Selected characteristics of the study cohort | |
|---|---|
| Characteristic | Overall |
| Subjects, N | 101 |
| POD, n (%) | 28 (27.7%) |
| TRC, n (%) | 73 (72.3%) |
| Age at FET-PET, median (Q1, Q3) | 59.0 (51.0, 66.0) |
| Dynamic TBRmax, median (Q1, Q3) | 2.27 (1.82, 2.80) |
| Dynamic TBRmean, median (Q1, Q3) | 1.90 (1.55, 2.29) |
| Static TBRmax, median (Q1, Q3) | 2.40 (2.06, 2.83) |
| Static TBRmean, median (Q1, Q3) | 1.87 (1.74, 1.98) |
18F-FET PET Brain Metastases: Statistical Analysis
Data preparation, descriptive analysis, and diagnostic performance
1 Analysis objectives
The primary objective is to assess how accurately \(^{18}\)F-FET PET differentiates tumor progression (POD) from treatment-related change (TRC) in previously treated brain metastases. The reference diagnosis is the variable Truth. The four prespecified primary PET predictors are dynamic TBRmax, dynamic TBRmean, static TBRmax, and static TBRmean.
The diagnostic outcome is coded with TRC as the reference level and POD as the positive class.
2 Study population and descriptive statistics
2.1 Cohort characteristics
The primary purpose of this table is to describe the analysis cohort. Because many imaging variables are skewed, continuous measures are summarized using median (Q1, Q3).
2.2 Primary PET measures by POD/TRC status
| Primary PET measurements by reference diagnosis | ||
|---|---|---|
| Reference diagnosis | N | Median (Q1, Q3) |
| Dynamic TBRmax | ||
| TRC | 72 | 2.08 (1.72, 2.50) |
| POD | 28 | 2.86 (2.25, 3.51) |
| Dynamic TBRmean | ||
| TRC | 72 | 1.82 (1.50, 2.22) |
| POD | 28 | 2.28 (1.86, 2.88) |
| Static TBRmax | ||
| TRC | 73 | 2.24 (1.93, 2.63) |
| POD | 28 | 2.96 (2.55, 3.54) |
| Static TBRmean | ||
| TRC | 73 | 1.78 (1.72, 1.93) |
| POD | 28 | 1.98 (1.89, 2.10) |
2.3 Distribution of PET measures by reference diagnosis
These displays are descriptive. The principal inferential target is diagnostic discrimination, quantified by the ROC AUC, rather than a separate hypothesis test of POD-versus-TRC location for each PET measure.
3 Primary diagnostic-performance analysis
For each PET measure, the ROC curve is estimated with POD as the positive condition. AUC confidence intervals use DeLong’s method. The operating threshold is selected by maximizing Youden’s index. Sensitivity and specificity are calculated at that threshold.
| Measure | N | POD / TRC | AUC (95% CI) | Cutoff | Sensitivity (95% CI) | Specificity (95% CI) |
|---|---|---|---|---|---|---|
| Dynamic TBRmax | 100 | 28 / 72 | 0.764 (0.659, 0.870) | 2.75 | 57.1% (37.2, 75.5) | 84.7% (74.3, 92.1) |
| Dynamic TBRmean | 100 | 28 / 72 | 0.734 (0.623, 0.844) | 2.34 | 50.0% (30.6, 69.4) | 86.1% (75.9, 93.1) |
| Static TBRmax | 101 | 28 / 73 | 0.819 (0.735, 0.902) | 2.35 | 92.9% (76.5, 99.1) | 61.6% (49.5, 72.8) |
| Static TBRmean | 101 | 28 / 73 | 0.820 (0.739, 0.901) | 1.88 | 89.3% (71.8, 97.7) | 67.1% (55.1, 77.7) |