The pediatric brain tumor dataset will be used for training, validating, and testing the transfer learning approach for increased performance in the classification and segmentation tasks. Even with the problem of structural and tissue differences from child and adult brains, we will attempt the use of selective transfer learned features, domain adaption, and other techniques for this task.
What are the goals of this project?
The of this project is to train a deep learning/CNN algorithm using adult brain MRI data and applying transfer learning techniques towards the classification and segmentation of tumors on the pediatric brain MRI data
The Children's Brain Tumor Network contributed to this project by providing access to the Pediatric Brain Tumor Atlas.