Skip to main content
. 2025 Dec 8;16:273. doi: 10.1186/s13244-025-02150-y

Table 3.

Comparison of ADC values and diagnostic performance

With DLR (n = 182) Without DLR (n = 182) p-value
ADC (×10-3 mm2/s) All lesions 1.50 ± 0.56 1.55 ± 0.55 < 0.001
Malignant lesions 1.18 ± 0.25 1.25 ± 0.24 < 0.001
HCC (n = 51) 1.15 ± 0.24 1.22 ± 0.24 < 0.001
CCA (n = 19) 1.21 ± 0.25 1.28 ± 0.27 0.001
LM (n = 30) 1.20 ± 0.26 1.27 ± 0.22 0.051
Benign lesions 1.90 ± 0.58 1.92 ± 0.58 < 0.001
Abscess (n = 12) 1.46 ± 0.19 1.50 ± 0.21 0.032
FNH (n = 18) 1.53 ± 0.21 1.57 ± 0.21 0.001
Adenoma (n = 8) 1.53 ± 0.25 1.56 ± 0.25 0.001
HH (n = 38) 2.08 ± 0.44 2.10 ± 0.44 0.007
Cyst (n = 6) 3.22 ± 0.41 3.26 ± 0.41 0.047
p-value (malignant vs. benign) < 0.001 < 0.001 /

Data are shown as mean values  ±  deviation

ADC apparent diffusion coefficient, DL deep learning reconstruction, HCC hepatocellular carcinoma, CCA cholangiocarcinoma, LM liver metastases, FNH focal nodular hyperplasia, HH hepatic hemangioma, AUC area under the curve, CI confidence interval, PPV positive predictive values, NPV negative predictive values