Table 1. Values of variables for logistic regression analysis

S/L ratio, the long-to-short axis ratio.

Table 2. Characteristics of patients

IQR, inter-quartile range.

Table 3. Characteristics of lymph nodes

IQR, inter-quartile range; S/L ratio, the long-to-short axis ratio.

Table 4. Best performance of six deep-learning algorithms Table 5. ResNet-50 and final diagnosis of lymph nodes Table 6. Diagnostic ability of all the modalities

AUC, area under the curve; PPV, positive predictive value; NPV, negative predictive value.

Table 7. Paired comparison of ROC curves

ROC, receiver operating characteristic; AUC, area under the curve; CI, confidence interval.