This study introduces DeepNeuro, a Python-based deep learning framework designed for easy implementation of neural networks in neuroimaging. The framework enables the creation of deep learning pipelines for data loading, preprocessing, neural network design, training, evaluation, and visualization. It also supports reproducibility by packaging preprocessing functions and facilitates sharing through Docker and Singularity containers with user-friendly interfaces.
Creator
Quantitative Tumor Imaging Lab, Martinos Center
Information
Pediatrics or Adult
Adult
Speciality
Neurology
Modality
Training
MRI data from a total of 60 patients and 127 visits