clinicadl.data.datasets.Dataset

class clinicadl.data.datasets.Dataset

Abstract class for ClinicaDL datasets, which inherits from torch.utils.data.Dataset, to work with 3D neuroimaging data.

To work properly with ClinicaDL, all datasets must inherit from this class.

See also

BidsDataset

A Dataset to read data organized in a BIDS.

property df: DataFrame

A DataFrame containing metadata on the images present in the dataset.

Each image must have its associated line in the DataFrame, which must contain at least the columns “participant_id” and “session_id”, with the ids (strings) of the participant and the session.

Example

participant_id  session_id   age   sex   diagnosis
sub-001         ses-M000     55.0  M     CN
sub-001         ses-M003     55.0  M     AD
sub-002         ses-M000     62.0  F     MCI
sub-002         ses-M003     62.0  F     AD
sub-003         ses-M000     67.0  F     CN

abstract eval() → None

Sets the dataset to evaluation mode.

For example, disabling data augmentation in the transformation pipeline.

abstract train() → None

Sets the dataset to training mode.

For example, enabling data augmentation in the transformation pipeline.

get_participant_session_couples() → set[tuple[str, str]]

Retrieves all (participant, session) pairs in the dataset.

Returns:

set[tuple[str, str]] – The set of (participant, session).

subset(participants_sessions: Path | str | DataFrame | Iterable[tuple[str, str]]) → Self

To get a subset of the dataset from a list of (participant, session) pairs.

Parameters:

data (Union[DataFrameType, Sequence[tuple[str, str]]]) –

Can be either:

• a sequence of (participant, session);

• a pandas.DataFrame (or a path to a TSV file containing the dataframe) with the list of (participant, session) pairs to extract. This list must be passed via two columns named "participant_id" and "session_id" (other columns won’t be considered).

Returns:

Self – A subset of the original dataset, restricted to the (participant, session) pairs mentioned in data.

abstract get_sample_info(idx: int, column: str) → Any

Retrieves information on a given sample in the metadata DataFrame. The information corresponds to the information on the image the sample was extracted from.

Parameters:

• idx (int) – The index of the sample in the dataset.

• column (str) – The information to look for, i.e. a column of df.

Returns:

Any – The value of the column for this sample.

abstract __len__() → int

Computes the total number of samples in the dataset.

Returns:

int – Total number of samples in the dataset, i.e. the number of images times the number of samples per image.

abstract __getitem__(idx: int) → SampleT

Retrieves the sample at a given index.

Parameters:

idx (int) – Index of the sample in the dataset.

Returns:

Union[Sample, Sequence[Sample], dict[Any, Sample]] – A structured output containing the processed data and metadata, as a Sample, or a sequence or dictionary of samples.