Vision Transformer

Spread sheet including Results and related works is available in here.

Dataset

Dataset is available in here.

1. Training: 3D MRI images from 369 patients (Height=240, Width=240, Depth=155)
   • Images: 4 modalities
   • Masks: 4 classes(0, 1, 2, and 4)

2. Validation: 3D MRI images from 125 patients (Height=240, Width=240, Depth=155)
   • Images: 4 modalities

Models

1. SwinUNETR

2. UNETR

3. UNET

Metrics

1. Dice Loss

Requirements

• git+https://github.com/Project-MONAI/MONAI#egg.gitmonai@0.8.1+271.g07de215c
• torch
• nibabel
• tqdm
• einops
• numpy
• SimpleITK

Install the requirements using command below:

pip install -r requirements.txt 

Run

python scripts.main --model swinunetr --epochs 10 --batch_size 2

References

• 3D Medical Image Segmentation