Related Experiment Video
Updated: Apr 7, 2026
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
Published on: June 9, 2018
3D Texture Analysis of Heterogeneous MRI Data for Diagnostic Classification of Childhood Brain Tumours
Ahmed E Fetit1, Jan Novak2, Daniel Rodriguez3
1Institute of Digital Healthcare, WMG, University of Warwick, Coventry, UK.
Insights
Three-dimensional Texture Analysis (3D TA) effectively classifies childhood brain tumors using MRI scans. This multicenter study shows 3D TA offers reliable diagnostic information beyond human vision for pediatric brain tumor detection.
Area of Science:
- Medical Imaging
- Oncology
- Radiology
Background:
- Childhood brain tumors are the most common solid tumors in children, accounting for 27% of pediatric cancers.
- Medulloblastoma, pilocytic astrocytoma, and ependymoma are the most frequent posterior fossa tumors.
- Texture Analysis (TA) quantifies image features beyond human visual perception, potentially aiding radiological assessments.
Purpose of the Study:
- To investigate the efficacy of 3D Texture Analysis (TA) for diagnosing common childhood brain tumors.
- To conduct a multicenter study evaluating 3D TA on conventional Magnetic Resonance Imaging (MRI) data.
- To assess the performance of 3D TA across different hospital data and MRI scanner variations.
Main Methods:
- Utilized pre-contrast T1 and T2-weighted MRI series from 121 children with medulloblastoma, pilocytic astrocytoma, or ependymoma.
- Extracted 3D textural features using first, second, and higher-order statistical methods.
- Trained and validated a support vector machine (SVM) classifier with leave-one-out cross-validation (LOOCV).
Main Results:
- 3D Texture Analysis (TA) demonstrated good overall performance in diagnostic classification.
- The efficacy of 3D TA was validated across multicenter data acquired from various manufacturers and magnetic field strengths.
- Texture Analysis provides quantifiable data that can supplement radiologist assessments.
Conclusions:
- 3D Texture Analysis (TA) is a promising tool for the diagnostic classification of pediatric brain tumors.
- The multicenter validation confirms the robustness and generalizability of 3D TA using conventional MRI.
- This quantitative imaging approach has the potential to improve diagnostic accuracy in pediatric neuro-oncology.
Abstract:
Brain tumours are the most frequently occuring solid tumours affecting childhood, representing 27% of all cancers. The most common posterior fossa tumours are medulloblastoma, pilocytic astrocytoma and ependymoma. Texture Analysis (TA) of Magnetic Resonance Imaging (MRI) aims to represent pixel distributions, intensities and dependencies using mathematically defined features. Such features could potentially provide quantifiable information that is beyond the human vision capabilities, and hence be used to supplement qualitative assessments conducted by radiologists. The primary aim of this study was to carry out a multicentre investigation on the efficacy of 3D TA for diagnostic classification of childhood brain tumours, using conventional MRI images. The data used had been acquired at three different hospitals and consisted of pre-contrast T1 and T2-weighted MRI series, obtained from 121 children diagnosed with medulloblastoma, pilocytic astrocytoma and ependymoma. Using 3D textural features, based on first, second and higher order statistical methods, a support vector machine (SVM) classifier was trained and tested using the leave-one-out cross-validation (LOOCV) approach. An essential outcome of this study is that 3D TA demonstrated a good overall performance, when used on data acquired from a number of centres and using scanners made by different manufacturers and at different magnetic field strengths.
