gradio-niivueviewer 0.0.1

Python library for easily interacting with trained machine learning models

gradio_niivueviewer

Python library for easily interacting with trained machine learning models

Installation

pip install gradio_niivueviewer

Usage

import os
import gradio as gr
from gradio_niivueviewer import NiiVueViewer

ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), "../.."))
nii_path = os.path.join(ROOT, "input/FLARE_02510_0000.nii.gz")
seg_path = os.path.join(ROOT, "output/FLARE_02510.nii.gz")

# FLARE22 standard organ labels
FLARE_LABELS = {
    1: "Liver",
    2: "Right Kidney",
    3: "Spleen",
    4: "Pancreas",
    5: "Aorta",
    6: "IVC",
    7: "Right Adrenal",
    8: "Left Adrenal",
    9: "Gallbladder",
    10: "Esophagus",
    11: "Stomach",
    12: "Duodenum",
    13: "Left Kidney",
}

with gr.Blocks(title="NiiVue Medical Image Viewer") as demo:
    gr.Markdown("## NiiVue — FLARE_02510")
    NiiVueViewer(value=[nii_path, seg_path], seg_labels=FLARE_LABELS)

if __name__ == "__main__":
    demo.launch(
        server_port=7870,
        allowed_paths=[os.path.dirname(nii_path), os.path.dirname(seg_path)],
    )

NiiVueViewer

Initialization

name	type	default	description
value	list[str] | None	value = None	List of NIfTI file paths. First path = main volume; second path
seg_labels	dict[int, str] | None	value = None	Mapping of integer label value → display name for the
label	str | I18nData | None	value = None	Label displayed above the component.
every	'Timer | float | None'	value = None	Timer or interval (seconds) to periodically refresh a dynamic value.
inputs	'Component | Sequence[Component] | set[Component] | None'	value = None	Components whose changes trigger a value recalculation.
show_label	bool | None	value = None	Whether to display the label.
container	bool	value = True	Wrap in a padded container.
scale	int | None	value = None	Relative width when placed in a Row.
min_width	int	value = 160	Minimum pixel width.
visible	bool | Literal['hidden']	value = True	Visibility of the component.
elem_id	str | None	value = None	HTML id attribute for the component's root element.
elem_classes	list[str] | str | None	value = None	HTML class(es) for the component's root element.
render	bool	value = True	If False, defer rendering until later.
key	int | str | tuple[int | str, ...] | None	value = None	Stable key for gr.render() re-render identity.
preserved_by_key	list[str] | str | None	value = "value"	Constructor parameters preserved across re-renders.

Events

name	description
change	Triggered when the value of the NiiVueViewer changes either because of user input (e.g. a user types in a textbox) OR because of a function update (e.g. an image receives a value from the output of an event trigger). See .input() for a listener that is only triggered by user input.

User function

The impact on the users predict function varies depending on whether the component is used as an input or output for an event (or both).

• When used as an Input, the component only impacts the input signature of the user function.
• When used as an output, the component only impacts the return signature of the user function.

The code snippet below is accurate in cases where the component is used as both an input and an output.

• As output: Is passed, list of local file paths, or None.
• As input: Should return, list of NIfTI file paths (absolute or relative to cwd).

def predict(
    value: list[str]| None
) -> list[str]| None:
    return value