Correction to: A predictive model for distinguishing radiation necrosis from tumour progression after gamma knife radiosurgery based on radiomic features from MR images

Correction to: A predictive model for distinguishing radiation necrosis from tumour progression after gamma knife radiosurgery based on radiomic features from MR images Zijian Zhang 0 1 2 3 4 5 Jinzhong Yang 0 1 2 3 4 5 Angela Ho 0 1 2 3 4 5 Wen Jiang 0 1 2 3 4 5 Jennifer Logan 0 1 2 3 4 5 Xin Wang 0 1 2 3 4 5 Paul D. Brown 0 1 2 3 4 5 Susan L. McGovern 0 1 2 3 4 5 Nandita Guha-Thakurta 0 1 2 3 4 5 Sherise D. Ferguson 0 1 2 3 4 5 Xenia Fave 0 1 2 3 4 5 Lifei Zhang 0 1 2 3 4 5 Dennis Mackin 0 1 2 3 4 5 Laurence E. Court 0 1 2 3 4 5 Jing Li 0 1 2 3 4 5 0 University of Houston , Houston, TX , USA 1 Department of Radiation Physics, The University of Texas MD Anderson Cancer Center , Unit 1420, 1515 Holcombe Blvd, Houston, TX 77030 , USA 2 Central South University Xiangya Hospital , Changsha, Hunan , China 3 Department of Neurosurgery, The University of Texas MD Anderson Cancer Center , Unit 1420, 1515 Holcombe Blvd, Houston, TX 77030 , USA 4 Department of Diagnostic Radiology, The University of Texas MD Anderson Cancer Center , Unit 1420, 1515 Holcombe Blvd, Houston, TX 77030 , USA 5 Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center , Unit 1420, 1515 Holcombe Blvd, Houston, TX 77030 , USA correction has therefore been made in the original: The presentation of Table 2 was incorrect. The corrected table is given below. The original article has been corrected. Radiomic features used in this study Direct intensity and intensity histogram [112]* Grey level co-occurrence matrix [132] Grey level run length matrix [11] Energy** Inter-quartile range Auto correlation** Grey level non-uniformity Global entropy Kurtosis Cluster prominence** High grey level run emphasis** Global max Mean absolute deviation Cluster shade** Low grey level run emphasis Global mean Median absolute deviation Cluster tendency** Long-run emphasis Global median Percentile Contrast** Long-run high grey level emphasis Global min Percentile area Correlation Long-run low grey level emphasis Global standard deviation Quantile Difference entropy Short-run emphasis Global uniformity Range Dissimilarity Short-run high grey level emphasis** Local entropy max Skewness Energy Short-run low grey level emphasis Local entropy mean Gaussian fit amplitude Entropy Run length non-uniformity Local entropy median Gaussian fit area Homogeneity Run percentage Local entropy min Gaussian fit mean Information measure correlation Local entropy standard deviation Gaussian fit standard deviation Inverse different moment norm Local range max Histogram area Inverse different norm Local range mean Local standard deviation median Inverse variance Local range median Local standard deviation min Max probability Local range min Local standard deviation standard Sum average Local range standard deviation deviation Sum entropy Local standard deviation max Root mean square Sum variance** Local standard deviation mean Variance** Variance** Geometric shape [14] Compactness Convex Convex hull volume Mass Max 3D-diameter Mean breadth Roundness Spherical disproportion Sphericity Surface area Surface area density Orientation Neighbourhood grey-tone difference matrix [10] Busyness Coarseness Complexity Contrast Texture strength Histogram of oriented gradients [6] Inter-quartile range Kurtosis Mean absolute deviation Median absolute deviation Range Skewness** *Numbers of features selected from each category are shown in brackets (total = 285 features) **Radiomic features selected for feature modelling by using concordance correlation coefficients (total = 43 features) (...truncated)