Erratum to: Eur Radiol

DOI 10.1007/s00330-016-4637-3

The original version of this article, published on 24 October 2016, unfortunately contained a mistake. The following correction has therefore been made in the original publication:

The captions of Fig. 3 and Fig. 4 were interchanged. The correct versions are given below.

Fig. 4
figure 1

Kaplan-Meier survival curves for classification for distinguishing short-term (red curve) from long-term (blue curve) survivors using clinical features like (a) age, (b) gender, (c) Karnofsky Performance Score (KPS), (d) a combination of clinical features (age, gender and KPS) and the top ten peritumoral radiomic features across multi-parametric MRI sequences, as compared to the Kaplan-Meier survival curve obtained from the ‘ground truth’ labels

Fig. 3
figure 2

A single two-dimensional gadolinium (Gd)-T1w MRI slice for two different patients with short- (a) and long- (g) term survival, respectively. The expert-annotated region bounded in green is necrosis; the region bounded in orange is enhancing tumour, while the region bounded in black is oedema. The corresponding per-voxel representations of three Haralick descriptors are shown for entropy (d, j), Correlation (e, k), and Sum Entropy (f, l) features