Article Figures & Data
Figures
- Fig 1.
A representative 2D FLAIR section for RN (A) and tumor recurrence (E) shown for 2 different primary brain tumor studies. B and F, The original FLAIR images corresponding to RN (A) and tumor recurrence (E). C, D, G, and H, The top 2 texture features corresponding to RN (A) and tumor recurrence (E), respectively. Red represents high feature value, while blue represents a low feature value for a given pixel.
Tables
Characteristic Patient Cohort Training Holdout Primary Metastatic Primary Metastatic No. of patients 22 21 11 4 Women 12 7 2 2 Men 9 15 9 2 Mean age (yr) 52.8 49.5 56.3 52 Age range (yr) (33–75) (37–65) (43–75) (43–58) - Table 2:
Classifier and blinded-reader detection accuracy on the holdout set using FLAIR or FLAIR, Gd-T1WI, and T2WI protocols when availablea
Detection Accuracy (Primary Cases, n = 11) Detection Accuracy (Metastatic Cases, n = 4) Overall Accuracy (n = 15) Expert 1 Expert 2 Radiomics Classifier Expert 1 Expert 2 Radiomics Classifier Expert 1 Expert 2 Radiomics Classifier 36% 54% 91% 50% 50% 50% 47% 53% 80% ↵a The ground truth was established on the basis of the true histopathologic diagnosis of the cases on the holdout set.
Jump to section
Related Articles
Cited By...
- Changes in CT Radiomic Features Associated with Lymphocyte Distribution Predict Overall Survival and Response to Immunotherapy in Non-Small Cell Lung Cancer
- Disorder in Pixel-Level Edge Directions on T1WI Is Associated with the Degree of Radiation Necrosis in Primary and Metastatic Brain Tumors: Preliminary Findings
- Shape Features of the Lesion Habitat to Differentiate Brain Tumor Progression from Pseudoprogression on Routine Multiparametric MRI: A Multisite Study
- Radiomics Approach Fails to Outperform Null Classifier on Test Data
- Comment on "Computer-Extracted Texture Features to Distinguish Cerebral Radionecrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibility Study"
- Reply:
- Reply:
- Regarding "Computer-Extracted Texture Features to Distinguish Cerebral Radionecrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibility Study"
- "Am I about to Lose my Job?!": A Comment on "Computer-Extracted Texture Features to Distinguish Cerebral Radiation Necrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibility Study"