├── Metrics
│ ├── dice_score.py
│ └── evaluate.py
├──utils
| └── data_loader.py
├── train.py
├── model_config.json
└── run.py
Automatic MRI brain tumor segmentation is of vital importance for the disease diagnosis, monitoring, and treatment planning. We present a method for classification and segmentation of brain tumors based on deep learning analysis of brain contrast T1ce (t1ce) MR images. To achieve this goal, three different deep learning networks are investigated, i.e., VAE and Unet with attention, Z-net, and DeepLabv3+ models. Experiments are performed on the Brain Tumor Segmentation (BraTS 2020) Challenge, composed of 369 brain MRI volumes, each with 155 cross-sections. Using the available computational resources, the Unet with VAE network achieves the highest Dice Similarity Coefficients (DSC) of the three investigated CNNs
