torch_em.data.datasets.medical.acouslic_ai
The Acouslic AI dataset contains annotations for fetal segmentation in ultrasound images.
This dataset is from the challenge: https://acouslic-ai.grand-challenge.org/. Please cite the challenge if you use this dataset for your publication.
1"""The Acouslic AI dataset contains annotations for fetal segmentation in ultrasound images. 2 3This dataset is from the challenge: https://acouslic-ai.grand-challenge.org/. 4Please cite the challenge if you use this dataset for your publication. 5""" 6 7import os 8from glob import glob 9from natsort import natsorted 10from typing import Tuple, Union, List 11 12from torch.utils.data import Dataset, DataLoader 13 14import torch_em 15 16from .. import util 17 18 19URL = "https://zenodo.org/records/11005384/files/acouslic-ai-train-set.zip" 20CHECKSUM = "187602dd243a3a872502b57b8ea56e28c67a9ded547b6e816b00c6d41f8b8767" 21 22 23def get_acouslic_ai_data(path: Union[os.PathLike, str], download: bool = False) -> str: 24 """Download the Acouslic AI dataset. 25 26 Args: 27 path: Filepath to a folder where the data is downloaded for further processing. 28 download: Whether to download the data if it is not present. 29 30 Returns: 31 Filepath where the data is downlaoded. 32 """ 33 data_dir = os.path.join(path, "data") 34 if os.path.exists(data_dir): 35 return data_dir 36 37 os.makedirs(path, exist_ok=True) 38 39 zip_path = os.path.join(path, "acouslic-ai-train-set.zip") 40 util.download_source(path=zip_path, url=URL, download=download, checksum=CHECKSUM) 41 util.unzip(zip_path=zip_path, dst=data_dir, remove=False) 42 43 return data_dir 44 45 46def get_acouslic_ai_paths(path: Union[os.PathLike, str], download: bool = False) -> Tuple[List[str], List[str]]: 47 """Get paths to the Acouslic AI data. 48 49 Args: 50 path: Filepath to a folder where the data is downloaded for further processing. 51 download: Whether to download the data if it is not present. 52 53 Returns: 54 List of filepaths for the image data. 55 List of filepaths for the label data. 56 """ 57 data_dir = get_acouslic_ai_data(path=path, download=download) 58 59 image_paths = natsorted(glob(os.path.join(data_dir, "images", "stacked_fetal_ultrasound", "*.mha"))) 60 gt_paths = natsorted(glob(os.path.join(data_dir, "masks", "stacked_fetal_abdomen", "*.mha"))) 61 62 return image_paths, gt_paths 63 64 65def get_acouslic_ai_dataset( 66 path: Union[os.PathLike, str], 67 patch_shape: Tuple[int, ...], 68 resize_inputs: bool = False, 69 download: bool = False, 70 **kwargs 71) -> Dataset: 72 """Get the Acouslic AI dataset for fetal segmentation. 73 74 Args: 75 path: Filepath to a folder where the data is downloaded for further processing. 76 patch_shape: The patch shape to use for training. 77 resize_inputs: Whether to resize inputs to the desired patch shape. 78 download: Whether to download the data if it is not present. 79 kwargs: Additional keyword arguments for `torch_em.default_segmentation_dataset`. 80 81 Returns: 82 The segmentation dataset. 83 """ 84 image_paths, gt_paths = get_acouslic_ai_paths(path=path, download=download) 85 86 if resize_inputs: 87 resize_kwargs = {"patch_shape": patch_shape, "is_rgb": False} 88 kwargs, patch_shape = util.update_kwargs_for_resize_trafo( 89 kwargs=kwargs, patch_shape=patch_shape, resize_inputs=resize_inputs, resize_kwargs=resize_kwargs 90 ) 91 92 return torch_em.default_segmentation_dataset( 93 raw_paths=image_paths, 94 raw_key=None, 95 label_paths=gt_paths, 96 label_key=None, 97 patch_shape=patch_shape, 98 **kwargs 99 ) 100 101 102def get_acouslic_ai_loader( 103 path: Union[os.PathLike, str], 104 batch_size: int, 105 patch_shape: Tuple[int, ...], 106 resize_inputs: bool = False, 107 download: bool = False, 108 **kwargs 109) -> DataLoader: 110 """Get the Acouslic AI dataloader for fetal segmentation. 111 112 Args: 113 path: Filepath to a folder where the data is downloaded for further processing. 114 batch_size: The batch size for training. 115 patch_shape: The patch shape to use for training. 116 resize_inputs: Whether to resize inputs to the desired patch shape. 117 download: Whether to download the data if it is not present. 118 kwargs: Additional keyword arguments for `torch_em.default_segmentation_dataset` or for the PyTorch DataLoader. 119 120 Returns: 121 The DataLoader. 122 """ 123 ds_kwargs, loader_kwargs = util.split_kwargs(torch_em.default_segmentation_dataset, **kwargs) 124 dataset = get_acouslic_ai_dataset(path, patch_shape, resize_inputs, download, **ds_kwargs) 125 return torch_em.get_data_loader(dataset, batch_size, **loader_kwargs)
URL =
'https://zenodo.org/records/11005384/files/acouslic-ai-train-set.zip'
CHECKSUM =
'187602dd243a3a872502b57b8ea56e28c67a9ded547b6e816b00c6d41f8b8767'
def
get_acouslic_ai_data(path: Union[os.PathLike, str], download: bool = False) -> str:
24def get_acouslic_ai_data(path: Union[os.PathLike, str], download: bool = False) -> str: 25 """Download the Acouslic AI dataset. 26 27 Args: 28 path: Filepath to a folder where the data is downloaded for further processing. 29 download: Whether to download the data if it is not present. 30 31 Returns: 32 Filepath where the data is downlaoded. 33 """ 34 data_dir = os.path.join(path, "data") 35 if os.path.exists(data_dir): 36 return data_dir 37 38 os.makedirs(path, exist_ok=True) 39 40 zip_path = os.path.join(path, "acouslic-ai-train-set.zip") 41 util.download_source(path=zip_path, url=URL, download=download, checksum=CHECKSUM) 42 util.unzip(zip_path=zip_path, dst=data_dir, remove=False) 43 44 return data_dir
Download the Acouslic AI dataset.
Arguments:
- path: Filepath to a folder where the data is downloaded for further processing.
- download: Whether to download the data if it is not present.
Returns:
Filepath where the data is downlaoded.
def
get_acouslic_ai_paths( path: Union[os.PathLike, str], download: bool = False) -> Tuple[List[str], List[str]]:
47def get_acouslic_ai_paths(path: Union[os.PathLike, str], download: bool = False) -> Tuple[List[str], List[str]]: 48 """Get paths to the Acouslic AI data. 49 50 Args: 51 path: Filepath to a folder where the data is downloaded for further processing. 52 download: Whether to download the data if it is not present. 53 54 Returns: 55 List of filepaths for the image data. 56 List of filepaths for the label data. 57 """ 58 data_dir = get_acouslic_ai_data(path=path, download=download) 59 60 image_paths = natsorted(glob(os.path.join(data_dir, "images", "stacked_fetal_ultrasound", "*.mha"))) 61 gt_paths = natsorted(glob(os.path.join(data_dir, "masks", "stacked_fetal_abdomen", "*.mha"))) 62 63 return image_paths, gt_paths
Get paths to the Acouslic AI data.
Arguments:
- path: Filepath to a folder where the data is downloaded for further processing.
- download: Whether to download the data if it is not present.
Returns:
List of filepaths for the image data. List of filepaths for the label data.
def
get_acouslic_ai_dataset( path: Union[os.PathLike, str], patch_shape: Tuple[int, ...], resize_inputs: bool = False, download: bool = False, **kwargs) -> torch.utils.data.dataset.Dataset:
66def get_acouslic_ai_dataset( 67 path: Union[os.PathLike, str], 68 patch_shape: Tuple[int, ...], 69 resize_inputs: bool = False, 70 download: bool = False, 71 **kwargs 72) -> Dataset: 73 """Get the Acouslic AI dataset for fetal segmentation. 74 75 Args: 76 path: Filepath to a folder where the data is downloaded for further processing. 77 patch_shape: The patch shape to use for training. 78 resize_inputs: Whether to resize inputs to the desired patch shape. 79 download: Whether to download the data if it is not present. 80 kwargs: Additional keyword arguments for `torch_em.default_segmentation_dataset`. 81 82 Returns: 83 The segmentation dataset. 84 """ 85 image_paths, gt_paths = get_acouslic_ai_paths(path=path, download=download) 86 87 if resize_inputs: 88 resize_kwargs = {"patch_shape": patch_shape, "is_rgb": False} 89 kwargs, patch_shape = util.update_kwargs_for_resize_trafo( 90 kwargs=kwargs, patch_shape=patch_shape, resize_inputs=resize_inputs, resize_kwargs=resize_kwargs 91 ) 92 93 return torch_em.default_segmentation_dataset( 94 raw_paths=image_paths, 95 raw_key=None, 96 label_paths=gt_paths, 97 label_key=None, 98 patch_shape=patch_shape, 99 **kwargs 100 )
Get the Acouslic AI dataset for fetal segmentation.
Arguments:
- path: Filepath to a folder where the data is downloaded for further processing.
- patch_shape: The patch shape to use for training.
- resize_inputs: Whether to resize inputs to the desired patch shape.
- download: Whether to download the data if it is not present.
- kwargs: Additional keyword arguments for
torch_em.default_segmentation_dataset
.
Returns:
The segmentation dataset.
def
get_acouslic_ai_loader( path: Union[os.PathLike, str], batch_size: int, patch_shape: Tuple[int, ...], resize_inputs: bool = False, download: bool = False, **kwargs) -> torch.utils.data.dataloader.DataLoader:
103def get_acouslic_ai_loader( 104 path: Union[os.PathLike, str], 105 batch_size: int, 106 patch_shape: Tuple[int, ...], 107 resize_inputs: bool = False, 108 download: bool = False, 109 **kwargs 110) -> DataLoader: 111 """Get the Acouslic AI dataloader for fetal segmentation. 112 113 Args: 114 path: Filepath to a folder where the data is downloaded for further processing. 115 batch_size: The batch size for training. 116 patch_shape: The patch shape to use for training. 117 resize_inputs: Whether to resize inputs to the desired patch shape. 118 download: Whether to download the data if it is not present. 119 kwargs: Additional keyword arguments for `torch_em.default_segmentation_dataset` or for the PyTorch DataLoader. 120 121 Returns: 122 The DataLoader. 123 """ 124 ds_kwargs, loader_kwargs = util.split_kwargs(torch_em.default_segmentation_dataset, **kwargs) 125 dataset = get_acouslic_ai_dataset(path, patch_shape, resize_inputs, download, **ds_kwargs) 126 return torch_em.get_data_loader(dataset, batch_size, **loader_kwargs)
Get the Acouslic AI dataloader for fetal segmentation.
Arguments:
- path: Filepath to a folder where the data is downloaded for further processing.
- batch_size: The batch size for training.
- patch_shape: The patch shape to use for training.
- resize_inputs: Whether to resize inputs to the desired patch shape.
- download: Whether to download the data if it is not present.
- kwargs: Additional keyword arguments for
torch_em.default_segmentation_dataset
or for the PyTorch DataLoader.
Returns:
The DataLoader.