.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples\03_quantify\plot_06_whole_habitat_radiomics.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_auto_examples_03_quantify_plot_06_whole_habitat_radiomics.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_03_quantify_plot_06_whole_habitat_radiomics.py:


Whole-habitat radiomics
=======================

**Background.** Per-habitat radiomics describes the MRI inside each habitat.
Whole-habitat radiomics instead describes the habitat map itself: the label
image (habitat ids as grey values) is fed to PyRadiomics as the image, and
the whole labelled region as the mask.

**Purpose.** You get one row of features describing the partition (here
first-order ``Mean`` / ``Entropy`` of the labels and ``shape`` features such
as ``Sphericity`` and ``SurfaceArea``), a habitat overlay, and a map of local
label entropy.

**Key terms.**

* **shape feature** -- geometry of the labelled region (e.g. how close it is
  to a sphere, its surface area), independent of intensity.
* **label entropy** -- how mixed the ids are in a small window around each
  voxel; zero inside one uniform habitat, higher where habitats (or the
  background at the tumour edge) meet.
* **habitat / one-step habitats** -- see
  :doc:`/auto_examples/03_quantify/plot_01_volume_fractions` and
  :doc:`/auto_examples/04_designs/plot_02_inside_each_subject`.

Quantify the **shape and spatial distribution of the partition map itself**
using :class:`~habit.habitat_features.WholeHabitatRadiomicsFeatures`.
The habitat label image plays both intensity and mask roles.

.. GENERATED FROM PYTHON SOURCE LINES 32-34

One-step habitats, then whole-map PyRadiomics on the label field.
sphinx_gallery_thumbnail_number = 2

.. GENERATED FROM PYTHON SOURCE LINES 34-72

.. code-block:: Python

    from pathlib import Path
    from typing import Any, Dict

    import matplotlib.pyplot as plt
    import numpy as np

    from habit.contracts import MaskVolume, cohort_from_directory
    from habit.datasets import fetch_demo
    from habit.habitat_features import WholeHabitatRadiomicsFeatures
    from habit.kernels import local_entropy_map
    from habit.recipes import one_step_habitat
    from habit.viz import plot_habitat_overlay, plot_voxel_texture_slice

    DATA = fetch_demo()
    MODALITIES = ("LAP",)
    ROI = "LAP"
    cohort = cohort_from_directory(DATA, modalities=MODALITIES, roi=ROI)[:1]
    result = one_step_habitat(
        modalities=MODALITIES, n_habitats=3, random_seed=0, roi=ROI
    ).fit_predict(cohort)
    subject = cohort[0]
    habitat_map = result.habitat_maps[0]

    params: Dict[str, Any] = {
        "imageType": {"Original": {}},
        "featureClass": {
            "firstorder": ["Mean", "Entropy"],
            "shape": ["Sphericity", "SurfaceArea"],
        },
        # binWidth=1 keeps each integer habitat id in its own grey-level bin.
        "setting": {"binWidth": 1, "voxelArrayShift": 0},
    }
    table = WholeHabitatRadiomicsFeatures(params=params)(subject, habitat_map)
    row = table.frame.iloc[0]
    print("Whole-habitat radiomics:")
    print(row.to_string())
    row





.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    HABIT demo data (cached)
    DATA (preprocessed root): C:\Users\dongm\.habit_data\demo-data-v1\preprocessed

    On-disk inventory of this folder:
      subjects (5): subj001, subj002, subj003, subj004, subj005
      image series: LAP, PVP, delay_3min, pre_contrast
      mask keys:    LAP, PVP, delay_3min, pre_contrast
      example image: images/subj001/delay_3min/WATER__BH_Ax_LAVA_Flex_3min_Series0012.nrrd
      example mask:  masks/subj001/delay_3min/WATER__BH_Ax_LAVA_Flex_10min_Series0017_mask.nrrd

    Your own data must use the same folder tree (change IDs / series names):

      DATA/
        images/<subject_id>/<modality>/<one image file>
        masks/<subject_id>/<roi>/<one mask file>

    Then load it with the same call the demos use:

      cohort = cohort_from_directory(DATA, modalities=("LAP",), roi="LAP")

    Swap DATA / modalities / roi to match your tree. Mask key is often the
    same as one image series (here LAP).

    Cohort.map[_DefineAndLabelWithinSubject]:   0%|          | 0/1 [00:00<?, ?it/s]
    Cohort.map[_DefineAndLabelWithinSubject]: 100%|██████████| 1/1 [00:01<00:00,  1.29s/it]
    Cohort.map[_DefineAndLabelWithinSubject]: 100%|██████████| 1/1 [00:01<00:00,  1.29s/it]
    Whole-habitat radiomics:
    subject                            subj001
    original_shape_Sphericity         0.719657
    original_shape_SurfaceArea     7141.076123
    original_firstorder_Mean          1.889318
    original_firstorder_Entropy       1.565974

    subject                            subj001
    original_shape_Sphericity         0.719657
    original_shape_SurfaceArea     7141.076123
    original_firstorder_Mean          1.889318
    original_firstorder_Entropy       1.565974
    Name: 0, dtype: object



.. GENERATED FROM PYTHON SOURCE LINES 73-76

Same objects as the table: habitat IDs are the intensity image.
First figure: the partition. Second: local entropy of those discrete
labels (not of the MRI), cropped to the same ROI.

.. GENERATED FROM PYTHON SOURCE LINES 76-108

.. code-block:: Python

    Path("out").mkdir(exist_ok=True)
    image_vol = subject.image(ROI)
    fig_hab = plot_habitat_overlay(
        image_vol,
        habitat_map,
        axis=0,
        crop_to="labels",
        title="habitats",
    )
    fig_hab.savefig("out/whole_habitat_radiomics_overlay.png", dpi=150, bbox_inches="tight")
    plt.show()

    label_intensity: np.ndarray = np.asarray(habitat_map.label_array, dtype=np.float64)
    n_label_bins: int = max(int(label_intensity.max()) + 1, 2)
    # 5x5x5 window; one histogram bin per id (background 0 included).
    entropy = local_entropy_map(label_intensity, kernel_size=5, bins=n_label_bins)
    habitat_roi = MaskVolume.from_geometry(
        (habitat_map.label_array > 0).astype(np.uint8),
        habitat_map.geometry,
        roi_name=ROI,
    )
    fig = plot_voxel_texture_slice(
        entropy,
        anatomy=image_vol,
        roi_mask=habitat_roi,
        axis=0,
        crop_to="roi",
        title="local entropy of habitat labels",
        feature_label="label entropy",
    )
    fig.savefig("out/whole_habitat_radiomics_texture.png", dpi=150, bbox_inches="tight")
    plt.show()



.. rst-class:: sphx-glr-horizontal


    *

      .. image-sg:: /auto_examples/03_quantify/images/sphx_glr_plot_06_whole_habitat_radiomics_001.png
         :alt: habitats
         :srcset: /auto_examples/03_quantify/images/sphx_glr_plot_06_whole_habitat_radiomics_001.png
         :class: sphx-glr-multi-img

    *

      .. image-sg:: /auto_examples/03_quantify/images/sphx_glr_plot_06_whole_habitat_radiomics_002.png
         :alt: local entropy of habitat labels
         :srcset: /auto_examples/03_quantify/images/sphx_glr_plot_06_whole_habitat_radiomics_002.png
         :class: sphx-glr-multi-img


.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    F:\work\habit_project\habit\viz\habitat_overlay.py:806: UserWarning: Display geometry conflict: image/anatomy direction does not match mask/label direction. Using the mask/label direction so coronal/sagittal superior-up follows the labelled anatomy. Pass direction= to override.
      resolved_direction, resolved_spacing = resolve_display_geometry(
    F:\work\habit_project\habit\viz\voxel_texture.py:1019: UserWarning: Display geometry conflict: image/anatomy direction does not match mask/label direction. Using the mask/label direction so coronal/sagittal superior-up follows the labelled anatomy. Pass direction= to override.
      direction, spacing = resolve_display_geometry(





.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 22.960 seconds)


.. _sphx_glr_download_auto_examples_03_quantify_plot_06_whole_habitat_radiomics.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: plot_06_whole_habitat_radiomics.ipynb <plot_06_whole_habitat_radiomics.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: plot_06_whole_habitat_radiomics.py <plot_06_whole_habitat_radiomics.py>`

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: plot_06_whole_habitat_radiomics.zip <plot_06_whole_habitat_radiomics.zip>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_