Skip to main content

ophth_algo_utils

Utilities for ophthalmology plugins.

Module​

Functions​

center_text_on_strip​

def center_text_on_strip(    img: Image.Image,    font: ImageFont.FreeTypeFont,    text_width: int,    text_height: int,    text: str,    strip_width: int,    strip_height: int,    color: tuple[int, int, int] = (0, 0, 0),) ‑> PIL.Image.Image:

Center text on image.

Arguments

  • img: The image to draw the text on.
  • font: The font to use for the text.
  • text_width: The width of the text.
  • text_height: The height of the text.
  • text: The text to draw on the image.
  • strip_width: The width of the strip.
  • strip_height: The height of the strip.
  • color: The color of the text. Defaults to black.

draw_no_markers_detected_on_image_strip​

def draw_no_markers_detected_on_image_strip(    img: Image.Image, height: int, width: int,) ‑> PIL.Image.Image:

Draw the "No markers detected" strip on the image.

Arguments

  • img: The image to draw the strip on.
  • height: The height of the image.
  • width: The width of the image.

draw_segmentation_mask_on_orig_image​

def draw_segmentation_mask_on_orig_image(    mask: np.ndarray,    image: PIL.Image.Image,    segmentation_labels: dict[str, int] = {'hypertransmission': 0, 'rpe_disruption': 1, 'is_os_disruption': 2, 'rpe_atrophy': 3, 'neurosensory_retina_atrophy': 4},    segmentation_colors: dict[str, tuple[int, int, int]] = {'hypertransmission': (255, 126, 203), 'rpe_disruption': (255, 214, 0), 'is_os_disruption': (22, 180, 242), 'rpe_atrophy': (96, 219, 0), 'neurosensory_retina_atrophy': (225, 106, 255), 'diffuse_edema': (255, 150, 3), 'serous_rpe_detachment': (77, 22, 220), 'intraretinal_cystoid_fluid': (100, 126, 62), 'subretinal_fluid': (204, 76, 45), 'subretinal_hyperreflective_material__shrm_': (225, 0, 255)},    formatted_segmentation_labels: dict[str, str] = {'hypertransmission': 'Choroidal Hypertransmission', 'rpe_disruption': 'RPE Disruption', 'is_os_disruption': 'EZ Disruption', 'rpe_atrophy': 'RPE Atrophy', 'neurosensory_retina_atrophy': 'Neurosensory Retina Atrophy', 'diffuse_edema': 'Diffuse Edema', 'serous_rpe_detachment': 'Pigment Epithelial Detachment (PED)', 'intraretinal_cystoid_fluid': 'Intraretinal fluid (IRF)', 'subretinal_fluid': 'Subretinal Fluid (SRF)', 'subretinal_hyperreflective_material__shrm_': 'Subretinal Hyperreflective Material (SHRM)'},    color_not_detected: tuple[int, int, int] = (243, 243, 247),) ‑> tuple[PIL.Image.Image, dict[str, tuple[int, int, int]]]:

Draw segmentation mask on original image.

Returns tuple: Tuple containing the image with segmentation mask and a legend mapping class names to colors.

get_data_for_files​

def get_data_for_files(    datasource: FileSystemIterableSource,    filenames: list[str],    file_key_col: str = '_original_filename',    use_cache: bool = True,) ‑> pandas.core.frame.DataFrame:

Retrieve data from a datasource for a given list of files.

The dataframe returned will be sorted to match the ordering of the files in filenames.

get_dataframe_iterator_from_datasource​

def get_dataframe_iterator_from_datasource(    datasource: BaseSource,    data_splitter: Optional[DatasetSplitter] = None,    use_cache: bool = True,) ‑> collections.abc.Iterable[pandas.core.frame.DataFrame]:

Get dataframe iterator from datasource.

Arguments

  • datasource: The datasource to get the dataframe iterator from.
  • data_splitter: The data splitter to use when getting the dataframes.
  • use_cache: Whether to use the cache when getting the dataframes.

Returns An iterable of dataframes from the datasource.

get_imgs_with_segmentation_from_enface_slo​

def get_imgs_with_segmentation_from_enface_slo(    data: pd.DataFrame,    enface_output: np.ndarray,    slos: np.ndarray,    slo_photo_location_prefixes: Optional[SLOSegmentationLocationPrefix] = None,    slo_image_metadata_columns: Optional[SLOImageMetadataColumns] = None,    oct_image_metadata_columns: Optional[OCTImageMetadataColumns] = None,    colour: Union[str, tuple[int, int, int]] = (0, 255, 255),    alpha: float = 0.75,    threshold: float = 0.7,) ‑> list[PIL.Image.Image]:

Get images with segmentation on SLO image from enfaces.

is_file_iterable_source​

def is_file_iterable_source(datasource: BaseSource) ‑> bool:

True iff datasource is a file iterable source (or subclass).

overlay_with_alpha_layer_ga_trial​

def overlay_with_alpha_layer_ga_trial(    img: Image.Image,    overlay: np.ndarray,    colour: Union[str, tuple[int, int, int]] = (255, 0, 0),    alpha: float = 0.8,) ‑> PIL.Image.Image:

Overlay an image with a segmentation.

overlay_with_grey_mask_ga_trial​

def overlay_with_grey_mask_ga_trial(    img: Image.Image, alpha: float = 0.3,) ‑> PIL.Image.Image:

Overlay an image with a segmentation.

parse_mask_json​

def parse_mask_json(    json_data: MaskAltrisBiomarker | MaskSegmentationModel, labels: dict[str, int],) ‑> numpy.ndarray:

Parse segmentation mask(s) from JSON.

Arguments

  • json_data: The model output JSON data for the masks.
  • labels: The segmentation classes to generate masks for mapped to their index in the mask data.

Returns A (num_segmentations, image_height, image_width) array where each (image_height, image_width) subarray is the mask for a different segmentation class.

use_default_rename_columns​

def use_default_rename_columns(    datasource: BaseSource, rename_columns: Optional[typing.Mapping[str, str]] = None,) ‑> Optional[Mapping[str, str]]:

Sets the default columns to include based on the datasource.