Correction to: Additional value of metabolic parameters to PET/CT-based radiomics nomogram in predicting lymphovascular invasion and outcome in lung adenocarcinoma

Correction to: European Journal of Nuclear Medicine and Molecular Imaging.

https://doi.org/10.1007/s00259-020-04747-5

Figures 1 and 4 are incorrect in the original manuscript. The correct Figs. 1 and 4 are shown below.

Fig. 1

Construction of radiomics signatures (RSs). a, b CT ROI segmentation. c, d PET ROI segmentation. e, f, g Two-dimensional (2D) CT, three-dimensional (3D) CT, and PET features selection using the least absolute shrinkage and selection operator (LASSO) regularization. h, i, j The selected 8 2D CT features, 8 3D CT features, 10 PET features and their coefficients. k, l, m The 2D CT radiomics scores (Rad-scores), 3D CT Rad-scores, and PET Rad-scores for each patient in the training and test sets

Fig. 4

Progression-free survival (PFS) curves according to pathologic LVI status (a) and CT-RNWS-predicted LVI status (b) in the 244 CT-RNWS-predicted cohort. c Forest plot of independent predictors of PFS with a multivariate Cox regression model. LVI, lymphovascular invasion; RNWS, radiomics nomogram with SUVmax; HR, hazard ratio; CI, confidence interval; CA125, carbohydrate antigen 125; CEA, carcinoembryonic antigen; NSE, neuron-specific enolase

Also, In Table 4, “EGFR mutation (± ND)” is not correct, it should be “EGFR mutation (+/-/ ND)”, because “+” and “-” means positive and negative, respectively. The correct Table 4 is shown below:

Table 4 The pathologic and therapeutic factors

The original article has been corrected.