https://github.com/nikhilroxtomar/brain-tumor-segmentation-using-unetr-in-tensorflow

This repository demonstrates the utilization of UNETR for brain tumor segmentation.
https://github.com/nikhilroxtomar/brain-tumor-segmentation-using-unetr-in-tensorflow

brain-tumor-segmentation medical-image-segmentation unet unetr unetr-segmentation

Last synced: 4 months ago
JSON representation

This repository demonstrates the utilization of UNETR for brain tumor segmentation.

• Host: GitHub
• URL: https://github.com/nikhilroxtomar/brain-tumor-segmentation-using-unetr-in-tensorflow
• Owner: nikhilroxtomar
• License: apache-2.0
• Created: 2024-02-23T08:31:07.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-02-23T08:44:47.000Z (about 1 year ago)
• Last Synced: 2024-11-16T06:27:59.823Z (6 months ago)
• Topics: brain-tumor-segmentation, medical-image-segmentation, unet, unetr, unetr-segmentation
• Language: Python
• Homepage:
• Size: 1.25 MB
• Stars: 3
• Watchers: 2
• Forks: 7
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Brain-Tumor-Segmentation-using-UNETR-in-TensorFlow

This repository demonstrates the utilization of UNETR for brain tumor segmentation.

## Architecture

| ![The block diagram of the Original UNETR model.](figures/unetr_architecture.png) |

| :--: |

| *The block diagram of the Original UNETR model.* |

## Dataset

The dataset contains 3064 pairs of MRI brain images and their respective binary mask indicating tumor.


 


Download the dataset: [Brain Tumor Segmentation](https://www.kaggle.com/datasets/nikhilroxtomar/brain-tumor-segmentation)




Original Dataset: [Brain Tumor Segmentation](https://figshare.com/articles/dataset/brain_tumor_dataset/1512427)

## Results

The sequence in the images below is `Input Image`, `Ground Truth` and `Prediction`. 
 


| ![](results/2.png) |

| :--: |

| ![](results/6.png) |

| ![](results/19.png) |

| ![](results/21.png) |

| ![](results/68.png) |

## How to improve

- Train on more epochs.

- Increase the input image resolution.

- Apply data augmentation.

## Contact

For more follow me on:

-  YouTube 

-  Facebook 

-  Twitter 

-  Instagram 

-  Telegram