clinicadl.data.datasets.examples.BidsNeuroEmo

class clinicadl.data.datasets.examples.BidsNeuroEmo(task: str, transforms: ~clinicadl.transforms.handlers.transforms.TransformsHandler = <clinicadl.transforms.handlers.transforms.TransformsHandler object>)[source]

A BidsDataset dataset with fMRI images. Adapted from NeuroEmo: An fMRI Dataset for Emotion Recognition.

The dataset is composed of 5 subjects, with a single session per subject. There are more than 200 timepoints per image.

Parameters:

  • task (str) –

    The data to load. Among:

    • "fe": functional data for the emotion task;

    • "rest": resting-state functional data.

  • transforms (TransformsHandler, default=TransformsHandler()) – Transformation pipeline to apply to the data after loading. The user also specifies here whether to work on images, patches, or slices. See clinicadl.transforms.TransformsHandler.

Examples

>>> from clinicadl.data.datasets.examples import BidsNeuroEmo
>>> bids = BidsNeuroEmo(task="rest")
>>> bids[0].shape
(250, 96, 96, 38)

>>> bids = BidsNeuroEmo(task="fe")
(200, 128, 128, 36)
property download_url: str

The URL where the dataset can be downloaded.

property dir: Path

The directory where the dataset is saved.