BPG is committed to discovery and dissemination of knowledge
Retrospective Study
Copyright: ©Author(s) 2026.
World J Radiol. Sep 28, 2026; 18(9): 124658
Published online Sep 28, 2026. doi: 10.4329/wjr.124658
Table 1 Patient demographic and clinical characteristics
Clinical features
n (%)
Gender
Female26 (52)
Male24 (48)
Age, median (range) (years) 69 (50-84)
≤ 6515 (30)
65-8028 (56)
≥ 817 (14)
Age (mean ± SD)68.56 ± 11.68
Pathological type
Adenocarcinoma39 (78)
Squamous cell carcinoma11 (22)
T stage
T147 (94)
T23 (6)
Smoker
Yes21 (42)
No29 (58)
Table 2 Results of feature selection for pre-microwave ablation computed tomography radiomics predicting 6-month local tumor progression
Image featuresNo progress
Progress
Mean
SD
Mean
SD
Wavelet-HHL/glszm/LALGLE14320.7530365.52108574.87235623.06
Wavelet-LLH/gldm/DE6.140.446.460.33
Wavelet-HLL/glszm/LAHGLE1698565.882731697.109608440.1912803613.18
Table 3 Results of feature selection for post-microwave ablation computed tomography radiomics predicting 6-month local tumor progression
Image featuresNo progress
Progress
Mean
SD
Mean
SD
Wavelet-HHH/glcm/IV0.480.010.490.01
Original/shape/M2DDC43.0517.8767.6039.65
Wavelet-LLL/glcm/MP0.0040.0030.0130.009
Table 4 Comparative performance of five predictive models
Performance measuresModels
Pre-MWA CT radiomics
Pre-MWA CT + clinical
variables
Post-MWA CT radiomics
Post-MWA CT + clinical
variables
Youden0.470.710.710.73
Sensitivity0.600.801.001.00
Specificity0.870.910.710.73
Accuracy0.840.900.740.76
NPV0.950.981.001.00
PPV0.330.500.280.29
True positive3455
False positive641312
True negative39413233
False negative2100
AUC0.6890.8490.8490.907


Write to the Help Desk