Related Experiment Video
Updated: Jan 4, 2026
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
7.3K
Automatic Prediction of Meningioma Grade Image Based on Data Amplification and Improved Convolutional Neural Network
Hong Zhu1,2, Qianhao Fang1,2, Hanzhi He1,2
1School of Medical Information, Xuzhou Medical University, Xuzhou, China.
Computational and Mathematical Methods in Medicine
|October 31, 2019
Summary
This study introduces a deep learning model for predicting meningioma grades, improving treatment planning. The novel approach achieves high accuracy in classifying brain tumor images, potentially reducing recurrence.
Area of Science:
- Neuro-oncology
- Medical imaging analysis
- Artificial intelligence in medicine
Background:
- Meningioma is a common brain tumor with WHO-defined grades.
- Accurate preoperative grading is crucial for treatment and prognosis.
- Current methods may lack efficiency or require tissue extraction.
Purpose of the Study:
- To develop a deep learning model for automatic meningioma grade prediction.
- To enhance clinical treatment planning and reduce tumor recurrence.
- To improve the efficiency of meningioma grading.
Main Methods:
- An improved LeNet-5 convolutional neural network (CNN) model was utilized.
- The model operates directly on medical images, avoiding tissue extraction.
- An oversampling technique addressed data insufficiency and imbalance.
Main Results:
- The deep learning model achieved high accuracy (83.33%) in meningioma image classification.
- The method demonstrated effectiveness on large clinical datasets.
- The approach successfully predicted meningioma grades without invasive procedures.
Conclusions:
- The developed deep learning model offers an efficient tool for preoperative meningioma grading.
- This non-invasive method can aid in personalized treatment strategies.
- The model shows promise in improving patient outcomes by reducing recurrence.