| Characteristic | Overall N = 2811 |
UTSW N = 511 |
MGB N = 251 |
NYU N = 431 |
Stanford N = 531 |
Michigan N = 591 |
UW N = 501 |
|---|---|---|---|---|---|---|---|
| Age, years | 65 (56, 71) | 67 (58, 74) | 61 (54, 67) | 64 (51, 71) | 65 (56, 74) | 63 (56, 70) | 66 (53, 70) |
| Sex | |||||||
| Female | 89 (31.7%) | 13 (25.5%) | 6 (24.0%) | 13 (30.2%) | 27 (50.9%) | 20 (33.9%) | 10 (20.0%) |
| Male | 192 (68.3%) | 38 (74.5%) | 19 (76.0%) | 30 (69.8%) | 26 (49.1%) | 39 (66.1%) | 40 (80.0%) |
| Clinical T stage | |||||||
| T1b | 188 (66.9%) | 32 (62.7%) | 12 (48.0%) | 25 (58.1%) | 28 (52.8%) | 50 (84.7%) | 41 (82.0%) |
| T2 | 93 (33.1%) | 19 (37.3%) | 13 (52.0%) | 18 (41.9%) | 25 (47.2%) | 9 (15.3%) | 9 (18.0%) |
| WHO/ISUP grade | |||||||
| 1 | 6 (2.6%) | 1 (2.3%) | 2 (8.7%) | 2 (6.3%) | 0 (0.0%) | 0 (0.0%) | 1 (2.2%) |
| 2 | 95 (41.1%) | 22 (50.0%) | 7 (30.4%) | 21 (65.6%) | 16 (44.4%) | 10 (19.6%) | 19 (42.2%) |
| 3 | 88 (38.1%) | 14 (31.8%) | 8 (34.8%) | 7 (21.9%) | 12 (33.3%) | 33 (64.7%) | 14 (31.1%) |
| 4 | 42 (18.2%) | 7 (15.9%) | 6 (26.1%) | 2 (6.3%) | 8 (22.2%) | 8 (15.7%) | 11 (24.4%) |
| Unavailable | 50 | 7 | 2 | 11 | 17 | 8 | 5 |
| AJCC stage | |||||||
| I | 129 (46.1%) | 24 (47.1%) | 9 (36.0%) | 12 (27.9%) | 15 (28.8%) | 40 (67.8%) | 29 (58.0%) |
| II | 28 (10.0%) | 6 (11.8%) | 6 (24.0%) | 3 (7.0%) | 7 (13.5%) | 6 (10.2%) | 0 (0.0%) |
| III | 111 (39.6%) | 19 (37.3%) | 7 (28.0%) | 28 (65.1%) | 24 (46.2%) | 13 (22.0%) | 20 (40.0%) |
| IV | 12 (4.3%) | 2 (3.9%) | 3 (12.0%) | 0 (0.0%) | 6 (11.5%) | 0 (0.0%) | 1 (2.0%) |
| Unavailable | 1 | 0 | 0 | 0 | 1 | 0 | 0 |
| Histologic necrosis | |||||||
| Absent | 166 (59.3%) | 38 (74.5%) | 1 (4.0%) | 29 (67.4%) | 29 (54.7%) | 38 (65.5%) | 31 (62.0%) |
| Present | 114 (40.7%) | 13 (25.5%) | 24 (96.0%) | 14 (32.6%) | 24 (45.3%) | 20 (34.5%) | 19 (38.0%) |
| Unavailable | 1 | 0 | 0 | 0 | 0 | 1 | 0 |
| Rhabdoid features | |||||||
| Absent | 233 (92.1%) | 42 (89.4%) | 23 (92.0%) | 41 (95.3%) | 26 (89.7%) | 56 (94.9%) | 45 (90.0%) |
| Present | 20 (7.9%) | 5 (10.6%) | 2 (8.0%) | 2 (4.7%) | 3 (10.3%) | 3 (5.1%) | 5 (10.0%) |
| Unavailable | 28 | 4 | 0 | 0 | 24 | 0 | 0 |
| Sarcomatoid features | |||||||
| Absent | 252 (93.7%) | 46 (93.9%) | 24 (96.0%) | 42 (97.7%) | 36 (83.7%) | 56 (94.9%) | 48 (96.0%) |
| Present | 17 (6.3%) | 3 (6.1%) | 1 (4.0%) | 1 (2.3%) | 7 (16.3%) | 3 (5.1%) | 2 (4.0%) |
| Unavailable | 12 | 2 | 0 | 0 | 10 | 0 | 0 |
| 1 Median (Q1, Q3); n (%) | |||||||
Central non-enhancement on CT and histologic necrosis in renal masses
Multicenter reader analysis
Statistical analysis
Categorical variables were summarized as counts and percentages, and continuous variables as medians and interquartile ranges. Following the multireader, multicase approach described by Obuchowski and Bullen (2022), we analyzed each radiologist’s assessment and included random intercepts for site, reader within site, and mass within site. We estimated the sensitivity and specificity of central non-enhancement (CNE) for histologic necrosis using a logistic mixed-effects model, as in the multicenter renal-mass study by Schieda et al. (2022). Linear mixed-effects models related the volumetric CNE-to-mass ratio and subjective CNE percentage to histologic percent necrosis. We adjusted separately for the same reader’s longest tumor diameter and tumor volume. We assessed reader agreement using Cohen’s κ for CNE presence and single-reader absolute-agreement intraclass correlation coefficients (ICCs) for CNE extent. Secondary analyses examined WHO/ISUP grade, AJCC stage, and rhabdoid and sarcomatoid features. We report 95% confidence intervals (CIs). P-values less than 0.05 were considered statistically significant. Analyses were performed using R 4.6.2.
Results
Study cohort
The six institutions contributed 281 surgically resected cT1b or cT2 masses in 281 patients. Both local radiologists assessed each mass. Histologic necrosis status was known for 280 masses, including 114 with necrosis. A numeric percentage was available for 269 masses. Reports documenting necrosis without a percentage contributed to the binary analysis. A missing pathology result was excluded from the corresponding analysis.
Detection of histologic necrosis
Readers called CNE in 202/227 readings of masses with histologic necrosis and 232/330 readings of masses without histologic necrosis. Table 2 gives the model-based estimates.
| Adjustment | Masses | Readings | Sensitivity, % | False-positive rate, % | Specificity, % | Difference, pp |
|---|---|---|---|---|---|---|
| Unadjusted | 280 | 557 | 87.5 (76.4, 96.2) | 73.9 (59.7, 86.7) | 26.1 (13.3, 40.3) | 13.6 (4.5, 22.0) |
| Diameter | 280 | 556 | 84.2 (71.0, 92.0) | 76.9 (63.4, 86.4) | 23.1 (13.6, 36.6) | 7.3 (-1.3, 15.9) |
| Volume | 280 | 556 | 83.8 (70.1, 91.9) | 77.1 (63.2, 86.8) | 22.9 (13.2, 36.8) | 6.7 (-1.7, 15.1) |
The difference is sensitivity minus the false-positive rate, in percentage points (pp). Unadjusted intervals are from a parametric bootstrap. Size-adjusted intervals use the observed information and delta method after standardizing both probabilities to the same distribution of reader-measured tumor size.
| Adjustment | Masses | Readings | OR (95% CI) |
|---|---|---|---|
| Unadjusted | 269 | 535 | 1.19 (0.64, 2.21) |
| Diameter | 269 | 534 | 0.56 (0.30, 1.07) |
| Volume | 269 | 534 | 0.54 (0.29, 1.01) |
A sensitivity analysis standardized the within-site call rates to the observed distribution of masses across the six sites. The estimated probability of a positive CNE call was 87.2% in masses with histologic necrosis and 73.4% in masses without it.
Extent of CNE and histologic necrosis
The volumetric ratio and subjective assessment are both expressed on a 0–100% scale. Each coefficient is the difference in the individual CT measurement, in percentage points, for the stated histologic contrast. Confirmed absence of CNE contributes zero to the all-readings analysis.
| CT measurement | Pathology contrast | Masses | Readings | Unadjusted | Diameter | Volume |
|---|---|---|---|---|---|---|
| Volumetric CNE-to-mass ratio | Per 10 percentage points | 269 | 535 | 2.8 (1.9, 3.8) | 1.8 (0.7, 2.8) [269 masses, 534 reads] | 1.7 (0.7, 2.5) [269 masses, 534 reads] |
| Volumetric CNE-to-mass ratio | Present vs absent | 280 | 557 | 6.2 (2.6, 9.6) | 2.5 (-1.0, 5.8) [280 masses, 556 reads] | 2.4 (-1.2, 6.0) [280 masses, 556 reads] |
| Subjective CNE percentage | Per 10 percentage points | 269 | 535 | 3.3 (2.0, 4.7) | 1.4 (0.1, 2.8) [269 masses, 534 reads] | 1.2 (-0.2, 2.5) [269 masses, 534 reads] |
| Subjective CNE percentage | Present vs absent | 280 | 557 | 10.0 (5.7, 14.6) | 3.7 (-1.1, 8.2) [280 masses, 556 reads] | 3.4 (-1.4, 7.8) [280 masses, 556 reads] |
| CT measurement | Masses | Readings | Unadjusted | Diameter | Volume |
|---|---|---|---|---|---|
| Volumetric CNE-to-mass ratio | 226 | 414 | 3.2 (2.1, 4.3) | 2.4 (1.2, 3.5) | 2.3 (1.2, 3.5) |
| Subjective CNE percentage | 225 | 413 | 3.4 (2.1, 4.9) | 2.3 (0.9, 3.8) | 2.1 (0.6, 3.5) |
A sensitivity analysis resampled whole masses within each site and accounted for each participating radiologist separately. Both unadjusted associations remained positive, with 95% CIs above zero. After adjustment for tumor diameter, the estimated increases per 10 percentage points of histologic necrosis were +1.63 (95% CI, -0.06 to 3.31) percentage points for the volumetric CNE-to-mass ratio and +1.12 (95% CI, -0.88 to 3.04) for the subjective CNE percentage. Both intervals included zero.
Reader agreement
The two readers agreed on the presence of CNE in 240 of 278 masses (86.3%). The overall within-site κ was 0.57 (0.45, 0.67) (95% CI).
| Site | Paired masses | Agreement, n (%) | Cohen’s κ (95% CI) |
|---|---|---|---|
| UTSW | 51 | 43 (84.3%) | 0.51 (0.20, 0.78) |
| MGB | 25 | 25 (100.0%) | NE |
| NYU | 43 | 39 (90.7%) | 0.81 (0.63, 0.95) |
| Stanford | 53 | 45 (84.9%) | 0.00 (CI NE) |
| Michigan | 59 | 50 (84.7%) | 0.64 (0.44, 0.83) |
| UW | 47 | 38 (80.9%) | 0.47 (0.16, 0.73) |
| Overall (within site) | 278 | 240 (86.3%) | 0.57 (0.45, 0.67) |
The overall κ uses site-specific reader marginals to calculate chance agreement. Confidence intervals resample paired masses within site, conditional on the participating readers. NE denotes an inestimable coefficient or interval when one or both readers used a single category.
| CT measurement | Paired masses | Within-site ICC (95% CI) |
|---|---|---|
| Volumetric CNE-to-mass ratio | 198 | 0.78 (0.72, 0.83) |
| Subjective CNE percentage | 199 | 0.77 (0.70, 0.82) |
The ICC describes agreement between readers at the same site. Site-specific mean levels were fitted separately. Confidence intervals account for variation among masses, readers, and repeated measurements through a parametric bootstrap.
Reader measurements and histologic necrosis
Reader-specific correlations
| Site | Reader | Ratio, N | Ratio, ρ | Subjective %, N | Subjective %, ρ |
|---|---|---|---|---|---|
| UTSW | Reader 1 | 51 | 0.26 | 51 | 0.23 |
| UTSW | Reader 2 | 51 | 0.20 | 51 | 0.26 |
| MGB | Reader 1 | 25 | 0.56 | 25 | 0.33 |
| MGB | Reader 2 | 25 | 0.53 | 25 | 0.50 |
| NYU | Reader 1 | 43 | 0.22 | 43 | 0.21 |
| NYU | Reader 2 | 43 | 0.26 | 43 | 0.33 |
| Stanford | Reader 1 | 44 | 0.25 | 44 | 0.20 |
| Stanford | Reader 2 | 44 | 0.17 | 44 | 0.25 |
| Michigan | Reader 1 | 56 | -0.04 | 56 | -0.01 |
| Michigan | Reader 2 | 56 | -0.09 | 56 | -0.10 |
| UW | Reader 1 | 47 | 0.34 | 47 | 0.38 |
| UW | Reader 2 | 50 | 0.52 | 50 | 0.46 |
Tumor size and the volumetric CNE-to-mass ratio
Figure 5 shows the volumetric CNE-to-mass ratio against tumor diameter and volume for each reading.
CNE and unfavorable pathologic features
Each one-grade increase in WHO/ISUP grade was associated with a 3.1-percentage-point increase in the volumetric CNE-to-mass ratio and a 6.2-percentage-point increase in subjective CNE percentage (Table 9).
| Feature | Assessment | Masses | Readings | Estimate (95% CI) |
|---|---|---|---|---|
| WHO/ISUP grade | Presence of CNE | 231 | 459 | 7.98 (1.43, 44.72) |
| Volumetric ratio | 231 | 459 | 3.1 (0.8, 5.1) | |
| Subjective CNE percentage | 231 | 459 | 6.2 (2.7, 9.7) | |
| AJCC stage | Presence of CNE | 280 | 557 | 1.52 (0.54, 4.28) |
| Volumetric ratio | 280 | 557 | 1.3 (-0.4, 3.0) | |
| Subjective CNE percentage | 280 | 557 | 2.2 (-0.2, 5.0) | |
| Rhabdoid features | Presence of CNE | 253 | 503 | 47.38 (0.35, 6400.46) |
| Volumetric ratio | 253 | 503 | -0.5 (-6.5, 5.9) | |
| Subjective CNE percentage | 253 | 503 | 4.0 (-5.1, 13.1) | |
| Sarcomatoid features | Presence of CNE | 269 | 535 | 71.31 (0.26, 19511.02) |
| Volumetric ratio | 269 | 535 | 4.2 (-2.6, 11.4) | |
| Subjective CNE percentage | 269 | 535 | 6.8 (-3.7, 16.9) |
Readers reported CNE in 36/40 (90%) readings of masses with rhabdoid features and 350/463 (76%) without them. The corresponding proportions for sarcomatoid features were 32/34 (94%) and 383/501 (76%).
Histologic necrosis and unfavorable pathologic features
Documented histologic necrosis was present in 17/20 (85.0%) of masses with rhabdoid features and 84/232 (36.2%) without them. The corresponding proportions for sarcomatoid features were 13/17 (76.5%) and 96/251 (38.2%) (Table 10).
| Feature | Masses with status | Difference in prevalence (95% CI) | Masses with percent | Difference in mean percent (95% CI) |
|---|---|---|---|---|
| WHO/ISUP grade | 231 | 18.2 (11.1, 25.2) | 222 | 3.8 (1.0, 6.7) |
| AJCC stage | 279 | 8.2 (2.9, 13.1) | 268 | 2.1 (0.2, 4.2) |
| Rhabdoid features | 252 | 49.2 (30.9, 66.1) | 249 | 6.3 (-0.8, 14.1) |
| Sarcomatoid features | 268 | 38.6 (15.3, 60.7) | 258 | 6.0 (-2.3, 16.5) |
Summary
Among 281 resected renal masses from 6 centers, the sensitivity of an individual reader’s CNE assessment for histologic necrosis was 87.5% (95% CI, 76.4–96.2) and specificity was 26.1% (95% CI, 13.3–40.3). Readers agreed on CNE presence in 86.3% of evaluable pairs (κ = 0.57). The ICCs were 0.78 for the volumetric CNE-to-mass ratio and 0.77 for subjective CNE percentage. Before adjustment for tumor size, each 10-percentage-point increase in histologic necrosis corresponded to increases of 2.8 and 3.3 percentage points in these two CT measures, respectively.