摘要：Correction to:
Scientific Reports 10.1038/s41598-021-96600-4, published online 03 September 2021
The original version of this Article contained an error in the order of the Figures. Figures 1, 2, 3, 4 and 5 were published as Figures 5, 1, 2, 3, and 4 respectively.
The original Figures
1,
2,
3,
4 and
5 and accompanying legends appear below.
Figure 1
Apparent diffusion coefficient (ADC) maps of a head and neck cancer patient throughout radiotherapy from the PREDICT-HN prospective clinical trial. (
a) ADC maps are displayed with (top row) the gross tumour volume (GTV) highlighted in colour and (middle row) cropped to the GTV to focus on the region of interest for the radiomic analysis. Change in (
b) the ADC histogram within the GTV is from baseline (TP0), weekly throughout radiotherapy (TP1–TP6) and post-radiotherapy (TP7) with the histogram colour matched to the GTV contour colour.
Figure 2
Linear correlation of apparent diffusion coefficient (ADC) radiomics features between IBEX and PyRadiomics software. Correlation matrices are grouped by feature class such as (
a) intensity histogram (
b) shape (
c) NGTDM (
d–
f) GLCM and (
g) GLRLM with colour representing the Pearson correlation coefficient (r). An ideal correlation matrix would have diagonal elements of highly correlated features (r = 1.0, dark purple) between software packages. A list of shared features between software packages is in Supplementary Tables 2–4.
Figure 3
Summary of linear correlation of apparent diffusion coefficient (ADC) radiomic features between PyRadiomics and (white) MaZda and (purple) IBEX software. The reproducibility threshold (red-dashed line) is defined as greater than a Pearson correlation coefficient of 0.901. This analysis identified a sub-set of reproducible features between IBEX and PyRadiomics from intensity histogram (5/7), shape (4/6), GLCM (neighbourhood 1:4/18, 4:1/18, 7:0/18), GLRLM (0/11) and NGTDM (1/5) categories. The sub-set of reproducible features between MaZda and PyRadiomics is intensity histogram (5/6), shape (2/6), GLCM (neighbourhood 1:3/10, 3:4/10, 7:2/10), GLRLM (3/7).
Figure 4
Comparison of hierarchical clustering of patients with PyRadiomics and IBEX using (
a) all shared features and (
b) a sub-set of reproducible features (
\documentclass[12pt
