Related Experiment Video
Updated: Jan 4, 2026
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
Differentiation Between Benign and Nonbenign Meningiomas by Using Texture Analysis From Multiparametric MRI
Chao Ke1, Haolin Chen2,3,4,5, Xiaofei Lv6
1Department of Neurosurgery and neuro-oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, 510060, China.
Texture analysis of multiparametric MRI can differentiate benign from nonbenign meningiomas. This approach aids in preoperative classification, improving diagnostic accuracy for World Health Organization (WHO) grades I, II, and III tumors.
Area of Science:
- Radiology and Medical Imaging
- Oncology
- Computational Pathology
Background:
- Distinguishing benign (WHO I) from nonbenign (WHO II-III) meningiomas preoperatively is challenging.
- Accurate preoperative grading is crucial for treatment planning and patient management.
Purpose of the Study:
- To assess the feasibility of using multiparametric MRI texture analysis for preoperative differentiation of benign and nonbenign meningiomas.
- To develop and validate a model for improved meningioma classification.
Main Methods:
- Retrospective analysis of 184 training and 79 external validation cohort patients with meningiomas.
- Texture features extracted from T1-weighted, T2-weighted, and contrast-enhanced T1-weighted MRI sequences.
- Combined texture and radiological features used to build multiparametric MRI models.
Main Results:
- The multiparametric MRI texture analysis model achieved high performance in both training and validation cohorts.
- Validation cohort results: AUC 0.83, Accuracy 80%, F1-score 0.77, Sensitivity 0.84, Specificity 0.78.
- This model outperformed single-sequence texture analysis approaches.
Conclusions:
- Multiparametric MRI texture analysis shows promise for preoperative differentiation of benign and nonbenign meningiomas.
- This technique can potentially improve the accuracy of meningioma grading before surgery.
