|
--- |
|
'[object Object]': null |
|
language: |
|
- en |
|
--- |
|
|
|
<h1 align="center">SwinUNETR</h1> |
|
|
|
_Trained by Margerie Huet Dastarac_ <br> |
|
_Training date: November2023_ |
|
|
|
## 1. Task Description |
|
Segmentation of the body on the CT scan on a datasheet of 60 oropharyngeal patients. This model can be used to clean CT scans by setting voxels value outside of the body contour to air, a typical preprocessing step for other networks. |
|
|
|
## 2. Model |
|
### 2.1. Architecture |
|
|
|
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65c9dbefd6cbf9dfed67367e/7X1GxxIT2LlpPBdR_tCzt.png) |
|
|
|
_Figure 1: SwinUNETR architecture_ |
|
### 2.2. Input |
|
+ CT |
|
### 2.3. Output |
|
+ BODY |
|
### 2.4 Training details |
|
+ Number of epoch: 300 |
|
+ Loss function: Dice loss |
|
+ Optimizer: Adam |
|
+ Learning Rate: 3e-4 |
|
+ Dropout: No |
|
+ Patch size in voxels: (128,128,128) |
|
+ Data augmentation used: |
|
- RandSpatialCropd |
|
- RandFlipd axis=0 |
|
- RandFlipd axis=1 |
|
- RandFlipd axis=2 |
|
- NormalizeIntensityd |
|
- RandScaleIntensityd factors=0.1 prob=1.0 |
|
## 3. Dataset |
|
+ Location: Head and neck, oropharynx |
|
+ Training set size: 60 |
|
+ Data type: CT scan and body contours |
|
+ Resolution in mm: 3x3x3 |
|
+ Preprocessing |
|
## Performance |
|
+TBD |