This repository contains the code and documentation for my Computer-Aided Diagnosis of Dementia project. The aim of this project is to develop a classification system that can accurately detect different stages of Dementia from a given set of Magnetic Resonance Imaging (MRI) scans. Here, I have explored various Machine Learning Models and evaluated their performance using different evaluation metrics.
The dataset used in this project consists of MRI images of the brain. The dataset is divided into a training set and a test set to effectively train and evaluate the models. It has four classes of images both in training as well as a testing set: Mild Demented, Moderate Demented, Non Demented and Very Mild Demented.
- Kernel Support Vector Machine
- Multilayer Perceptron
- Voting Based Classifier
- Support Vector Machine
- Decision Tree
- Extreme Gradient Boosting
- K Nearest Neighours
- Naïve Bayes
- Logistic Regression
- Random Forest
- Accuracy: ratio of correct number of predictions to total number of predictions.
- Precision: The proportion of true positive predictions out of the total positive predictions.
- Recall: The proportion of true positive predictions out of all actual positive samples.
- F1 Score: The harmonic mean of precision and recall, providing a balance between the two metrics.
Based on the results, we can draw insights into the performance of each model. Further analysis and experimentation can be conducted to fine-tune the models and potentially enhance the overall performance.