Development and Implementation of an Advanced Brain Tumor Detection Algorithm Utilizing MATLAB for Enhanced Diagnostic Accuracy
Brain tumors present a significant challenge due to their complex structure and the need for accurate, timely detection. Our algorithm improves identification, enhancing treatment outcomes and reducing mortality rates. Using a dataset of 3064 CT images from 233 patients (including gliomas, meningiomas, and pituitary tumors), we applied preprocessing techniques like histogram equalization and skull removal, followed by segmentation with morphological operations.
We extracted 35 features (e.g., auto-correlation, entropy) and used WEKA for feature selection and classification, achieving ~93% accuracy with classifiers like BayesNet, Bagging, and Logistic Regression. This project highlights the potential of advanced image processing and machine learning to create reliable, automated diagnostic tools, supporting doctors in making informed decisions and improving patient care.
You can check the project on my LinkedIn profile or you can check it with the Github link below.
GitHub: Github Project