{"id":30250402,"url":"https://github.com/deepramazumder/mri-based-dementia-prediction","last_synced_at":"2025-08-15T09:39:56.278Z","repository":{"id":256644611,"uuid":"855081519","full_name":"DeepraMazumder/MRI-Based-Dementia-Prediction","owner":"DeepraMazumder","description":"A Machine Learning project predicting dementia progression from MRI data using SVM, One-vs-Rest and One-vs-One classifiers","archived":false,"fork":false,"pushed_at":"2024-09-12T14:59:31.000Z","size":469,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-05T09:05:50.336Z","etag":null,"topics":["alzheimers","dementia","mri-data","one-vs-one","one-vs-rest","svm"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DeepraMazumder.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-09-10T09:19:06.000Z","updated_at":"2025-07-03T05:01:03.000Z","dependencies_parsed_at":"2024-09-12T07:09:54.034Z","dependency_job_id":"fdcc28bb-a823-4757-93f9-e29c7fdfcada","html_url":"https://github.com/DeepraMazumder/MRI-Based-Dementia-Prediction","commit_stats":null,"previous_names":["deepramazumder/mri-based-dementia-progression-prediction","deepramazumder/mri-based-dementia-prediction"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/DeepraMazumder/MRI-Based-Dementia-Prediction","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepraMazumder%2FMRI-Based-Dementia-Prediction","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepraMazumder%2FMRI-Based-Dementia-Prediction/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepraMazumder%2FMRI-Based-Dementia-Prediction/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepraMazumder%2FMRI-Based-Dementia-Prediction/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DeepraMazumder","download_url":"https://codeload.github.com/DeepraMazumder/MRI-Based-Dementia-Prediction/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepraMazumder%2FMRI-Based-Dementia-Prediction/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270552674,"owners_count":24605570,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-15T02:00:12.559Z","response_time":110,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["alzheimers","dementia","mri-data","one-vs-one","one-vs-rest","svm"],"created_at":"2025-08-15T09:39:53.310Z","updated_at":"2025-08-15T09:39:56.263Z","avatar_url":"https://github.com/DeepraMazumder.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MRI-Based-Dementia-Progression-Prediction\n\n## Project Overview\nThe **MRI-Based-Dementia-Progression-Prediction** project aims to predict the progression of dementia in patients based on MRI data and other clinical features. It applies machine learning techniques, including **One-vs-Rest (OvR)** and **One-vs-One (OvO)** classifiers, as well as **Support Vector Machines (SVM)**, to distinguish between three groups: *NonDemented*, *Demented*, and *Converted*. The project focuses on utilizing brain MRI imaging as a key input to predict if a patient will progress from mild cognitive impairment to dementia.\n\nThe dataset used for this project consists of longitudinal MRI data of 150 subjects, aged 60 to 96, with over 370 imaging sessions. These subjects include both non-demented and demented individuals, providing a comprehensive dataset for training and evaluation.\n\n## Installation\nTo run the project locally, follow these steps:\n\n1. Clone the repository:\n   - `git clone https://github.com/your-username/MRI-Based-Dementia-Progression-Prediction.git`\n\n2. Navigate to the project directory:\n   - `cd MRI-Based-Dementia-Progression-Prediction`\n\n3. Install the required dependencies:\n   - `pip install --upgrade -r requirements.txt`\n\n## Dataset\nThe dataset consists of the following key features:\n\n- **Subject ID**: Unique identifier for each subject.\n- **MRI ID**: Unique identifier for each MRI exam.\n- **Group**: Target variable with three labels (*NonDemented*, *Demented*, *Converted*).\n- **Visit**: Visit order.\n- **MR Delay**: Time delay between MRI sessions.\n- **M/F**: Gender (Male or Female).\n- **MMSE**: Mini-Mental State Examination score (0–30).\n- **CDR**: Clinical Dementia Rating (0–2).\n- **eTIV**: Estimated total intracranial volume (mm³).\n- **nWBV**: Normalized whole-brain volume (as a percentage).\n- **ASF**: Atlas scaling factor.\n\n## Exploratory Data Analysis (EDA)\nThe project explores the dataset through various visualizations and statistics:\n\n- **Histogram Distributions**: Visualizes the distribution of key clinical features such as MMSE, CDR, and brain volumes.\n- **Age Distribution**: Analyzes the age range of subjects.\n- **Dementia Frequency**: Investigates the number of subjects diagnosed with dementia and their progression over time.\n- **Correlation Heatmap**: Displays correlations between the clinical and MRI features.\n\n## Pre-processing and Feature Engineering\n- **Data Cleaning**: Removing unwanted columns, handling null values, and encoding categorical variables.\n- **Feature Scaling**: Scaling MRI-derived volumes and clinical features.\n- **Target Variable Encoding**: Encoding the group labels (*NonDemented*, *Demented*, *Converted*) for model training.\n\n## Modeling\n\n### **One-vs-Rest Classifier (OvR)**\n\n- Trained an OvR classifier for multi-label classification.\n- Evaluated the performance using **accuracy**, **precision**, **recall**, **F1-score** and **confusion matrix**.\n- Computed the **ROC-AUC** for each class and visualized the ROC curve.\n\n### **One-vs-One Classifier (OvO)**\n\n- Trained an OvO classifier for multi-label classification.\n- Evaluated the performance using **accuracy**, **precision**, **recall**, **F1-score** and **confusion matrix**.\n- Computed the **ROC-AUC** for each class and visualized the ROC curve.\n\n### **SVM Classifier (OvR)**\n\n- Trained a SVM classifier for multi-label classification.\n- Evaluated the performance using **accuracy**, **precision**, **recall**, **F1-score** and **confusion matrix**.\n- Computed the **ROC-AUC** for each class and visualized the ROC curve.\n\n## **Results**\nThe project evaluated different classification strategies:\n\n- **One-vs-Rest Classifier**:\n  - **Accuracy**: 89%\n  - **Precision**: 90%\n  - **Recall**: 89%\n  - **F1 Score**: 85%\n  \n- **One-vs-One Classifier**:\n  - **Accuracy**: 87%\n  - **Precision**: 86%\n  - **Recall**: 87%\n  - **F1 Score**: 87%\n\n- **SVM Classifier**:\n  - **Accuracy**: 87%\n  - **Precision**: 86%\n  - **Recall**: 87%\n  - **F1 Score**: 87%\n  \n## Contributing\nContributions are welcome! If you'd like to contribute to the project, please follow these steps:\n\n1. Fork the repository.\n2. Create a new branch (`git checkout -b feature-branch`).\n3. Commit your changes (`git commit -m 'Add new feature'`).\n4. Push to the branch (`git push origin feature-branch`).\n5. Create a pull request.\n\n---\n\n## License\nThis project is licensed under the MIT License. See the [LICENSE](LICENSE) file for more details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepramazumder%2Fmri-based-dementia-prediction","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeepramazumder%2Fmri-based-dementia-prediction","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepramazumder%2Fmri-based-dementia-prediction/lists"}