Skip to content

FraCorti/U-Net-Brain-tumor-segmentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 

Repository files navigation

U-Net Brain Tumor Segmentation

For the class of Intelligent Systems for Pattern Recognition a U-Net Convolutional Network implemented in Pytorch was used to perform brain tumor segmentation. The model was trained and tested on the Kaggle platform in order to exploit GPU computation.

The dataset was obtained from the Cancer Image Archive, a service that de-identifies and hosts a large archive of medical images of cancer accessible for public download. An analysis was done on the performance achieved by varying the hyperparameters of the model such as the batch size and regarding then use of the Batch Normalization layers. Also, a description of the model architecture used and the theoretical background of CNNs can be found inside the report.

About

Brain Tumor Segmentation project for the ISPR class

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages