Skip to content

AshishSara/Visualize-MRI-Data

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 

Repository files navigation

MRI Image Explorer for Medical Diagnosis

This project is designed to provide a user-friendly interface to explore MRI (Magnetic Resonance Imaging) images and their corresponding labels. The primary goal is to facilitate a better understanding of the medical images for clinicians and researchers. The project employs a simple but effective interactive interface where users can choose different slices and channels of the MRI images, helping diagnose and study conditions like tumours. The project uses Python, specifically Jupyter Notebook, and some libraries are specific Jupyter Notebook usage, so be sure to download the software to run the program as intended.

The imaging data was obtained from the following website (https://decathlon-10.grand-challenge.org/), specifically the "Task01_BrainTumour.tar" file and is credited to the following academic paper: https://doi.org/10.1038/s41467-022-30695-9.

I only included 2 of the files in each "Images" and "Label" folder because of the large size of each folder in its originality.

Features Interactive UI: Allows users to select specific files, layers, and channels for MRI images and their corresponding labels. Visual Insights: Renders the selected MRI image slice alongside its labelled version for immediate visual comparison. Customizable: This can easily be extended to include more features like segmentation algorithms, statistical metrics, etc. Technical Stack Python: The core logic is written in Python. Nibabel: For reading the NIfTI-1 format MRI images. Matplotlib: For rendering the MRI image slices. Ipywidgets: To create an interactive UI with sliders and dropdowns. Glob: For file handling. Prerequisites Python 3.x Nibabel Matplotlib Ipywidgets Glob Installation

Screenshots

Screen Shot 2023-10-13 at 10 30 31 PM

Future Work Add machine learning models for feature extraction and prediction. Implement more advanced segmentation algorithms.

Contributing Feel free to fork the project and submit a pull request with your changes!

License This project is licensed under the MIT License

Thank you!

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published