Related Experiment Video
Updated: Aug 12, 2025
09:53
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
Published on: August 16, 2020
7.3K
A Deep Probabilistic Sensing and Learning Model for Brain Tumor Classification With Fusion-Net and HFCMIK
M V S Ramprasad1,2, Md Zia Ur Rahman3, Masreshaw Demelash Bayleyegn4
1Koneru Lakshmaiah Education FoundationK L University Guntur 522302 India.
IEEE Open Journal of Engineering in Medicine and Biology
|January 30, 2023
Summary
This study introduces BTFSC-Net, an artificial intelligence tool for brain tumor classification. It achieves high accuracy in segmenting and classifying tumors using advanced image processing and deep learning techniques.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Accurate brain tumor classification is crucial for effective treatment planning.
- Existing diagnostic methods can be time-consuming and may lack precision.
- Developing automated tools can enhance diagnostic efficiency and accuracy.
Purpose of the Study:
- To implement and evaluate the BTFSC-Net, an AI-based tool for brain tumor classification.
- To assess the performance of BTFSC-Net in image segmentation and tumor classification.
- To compare the efficacy of BTFSC-Net against existing methodologies.
Main Methods:
- Preprocessing of medical images using a hybrid probabilistic wiener filter (HPWF).
- Fusion of MRI and CT images using a deep learning convolutional neural network (DLCNN) with robust edge analysis (REA).
- Segmentation of diseased regions via hybrid fuzzy c-means integrated k-means (HFCMIK) clustering.
- Extraction of hybrid features (texture, color, low-level) using GLCM and RDWT.
- Classification of tumors as malignant or benign using a deep learning probabilistic neural network (DLPNN).
Main Results:
- BTFSC-Net achieved 99.21% accuracy in image segmentation.
- BTFSC-Net demonstrated 99.46% accuracy in tumor classification.
- The AI tool effectively identified tumorous regions and classified tumor types.
Conclusions:
- BTFSC-Net significantly outperforms existing methods in brain tumor diagnosis.
- The developed AI tool shows high potential for clinical application in neuro-oncology.
- The study highlights the effectiveness of integrated AI and advanced image processing techniques.
