HDUNet VMAT
_Trained by Margerie Huet Dastarac ._
_Training date: 06/06/2023 ._
## 1. Task Description
Prediction of the dose distribution with VMAT scanning treatment.
## 2. Model
### 2.1. Architecture
_Figure 1: HDUNet VMAT architecture_
### 2.2. Input
- CT: 3D float matrix
- Target volumes contours and prescription: 3D float matrices: pixel value set with prescription in different targt volumes
- Organs at risks contours: 3D boolean matrices, one per considered organ
### 2.3. Output
### 2.4 Training details
- Number of epoch: 400
- Loss function: MSE loss
- Optimizer: AdamW
- Learning Rate: 0.0001
- Dropout: No
- Patch size in voxels: (128,128,128)
- Data augmentation used:
## 3. Dataset
- Location: Oropharynx
- Training set size: 57
- Resolution in mm: 3x3x3
## Performance
