torch_em.data.datasets.light_microscopy.ifnuclei

  1"""The IFNuclei dataset contains annotations for nucleus segmentation
  2of immuno and DAPI stained fluorescence images.
  3
  4This dataset is from the publication https://doi.org/10.1038/s41597-020-00608-w.
  5Please cite it if you use this dataset in your research.
  6"""
  7
  8import os
  9from glob import glob
 10from natsort import natsorted
 11from typing import Union, Tuple, List
 12
 13from torch.utils.data import Dataset, DataLoader
 14
 15import torch_em
 16
 17from .. import util
 18
 19
 20URL = "https://www.ebi.ac.uk/biostudies/files/S-BSST265/dataset.zip"
 21CHECKSUM = "8285987ed4d57c46a46a55a33c1c085875ea41f429b59cde31d249741aa07ad1"
 22
 23
 24def get_ifnuclei_data(path: Union[os.PathLike, str], download: bool = False):
 25    """Download the IFNuclei dataset for nucleus segmentation.
 26
 27    Args:
 28        path: Filepath to a folder where the downloaded data will be saved.
 29        download: Whether to download the data if it is not present.
 30    """
 31    data_dir = os.path.join(path, "rawimages")
 32    if os.path.exists(data_dir):
 33        return
 34
 35    os.makedirs(path, exist_ok=True)
 36
 37    zip_path = os.path.join(path, "dataset.zip")
 38    util.download_source(path=zip_path, url=URL, download=download, checksum=CHECKSUM)
 39    util.unzip(zip_path=zip_path, dst=path)
 40
 41
 42def get_ifnuclei_paths(path: Union[os.PathLike, str], download: bool = False) -> Tuple[List[int], List[int]]:
 43    """Get paths to the IFNuclei data.
 44
 45    Args:
 46        path: Filepath to a folder where the downloaded data will be saved.
 47        download: Whether to download the data if it is not present.
 48
 49    Returns:
 50        List of filepaths for the image data.
 51        List of filepaths for the label data.
 52    """
 53    get_ifnuclei_data(path, download)
 54
 55    raw_paths = natsorted(glob(os.path.join(path, "rawimages", "*.tif")))
 56    label_paths = natsorted(glob(os.path.join(path, "groundtruth", "*")))
 57
 58    assert len(raw_paths) == len(label_paths) and len(raw_paths) > 0
 59
 60    return raw_paths, label_paths
 61
 62
 63def get_ifnuclei_dataset(
 64    path: Union[os.PathLike, str], patch_shape: Tuple[int, int], download: bool = False, **kwargs
 65) -> Dataset:
 66    """Get the IFNuclei dataset for nucleus segmentation.
 67
 68    Args:
 69        path: Filepath to a folder where the downloaded data will be saved.
 70        patch_shape: The patch shape to use for training.
 71        download: Whether to download the data if it is not present.
 72        kwargs: Additional keyword arguments for `torch_em.default_segmentation_dataset`.
 73
 74    Returns:
 75        The segmentation dataset.
 76    """
 77    raw_paths, label_paths = get_ifnuclei_paths(path, download)
 78
 79    return torch_em.default_segmentation_dataset(
 80        raw_paths=raw_paths,
 81        raw_key=None,
 82        label_paths=label_paths,
 83        label_key=None,
 84        is_seg_dataset=False,
 85        patch_shape=patch_shape,
 86        **kwargs
 87    )
 88
 89
 90def get_ifnuclei_loader(
 91    path: Union[os.PathLike, str], batch_size: int, patch_shape: Tuple[int, int], download: bool = False, **kwargs
 92) -> DataLoader:
 93    """Get the IFNuclei dataloader for nucleus segmentation.
 94
 95    Args:
 96        path: Filepath to a folder where the downloaded data will be saved.
 97        batch_size: The batch size for training.
 98        patch_shape: The patch shape to use for training.
 99        download: Whether to download the data if it is not present.
100        kwargs: Additional keyword arguments for `torch_em.default_segmentation_dataset` or for the PyTorch DataLoader.
101
102    Returns:
103        The DataLoader.
104    """
105    ds_kwargs, loader_kwargs = util.split_kwargs(torch_em.default_segmentation_dataset, **kwargs)
106    dataset = get_ifnuclei_dataset(path, patch_shape, download, **ds_kwargs)
107    return torch_em.get_data_loader(dataset, batch_size, **loader_kwargs)