plot_intensity_slice

Note

This page is a reference documentation. It only explains the function signature, and not how to use it. Please refer to the Habitat Guide and Python API guide (v2.0) for usage.

plot_intensity_slice(image: object, *, before: object | None = None, roi_mask: object | None = None, axis: int | None = None, index: int | None = None, cmap: str = 'gray', title: str | None = None, image_label: str = 'Processed', before_label: str = 'Original', direction: Sequence[float] | None = None, spacing: Sequence[float] | None = None, display_convention: DisplayConvention = 'radiological', roi_contour: bool = False, colorbar: ColorbarSpec = True, colorbar_label: str = 'Intensity', before_colorbar_label: str = 'Intensity', before_cmap: str | None = None, symmetric_clim: bool = False, crop_to: str = 'none', crop_pad: int = 6) → Figure[source]

Display a whole-FOV greyscale anatomy / intensity slice.

Use this for image-preprocessing teaching figures. Do not use plot_voxel_texture_slice() for MR/CT intensities: that plotter is a voxel-texture map viewer (sequential colormap, ROI crop).

Pass before= for a two-panel original | processed figure when both volumes share a grid (z-score, N4, histogram, CLAHE). After resample / reorient the grid often changes — omit before and show the processed volume alone.

Each panel is windowed independently in native units: drop a dominant low-end histogram mode (air / padding), then the 2nd–90th percentiles of the remaining tissue. The colorbar shows those same limits, so a z-score (approximately \(N(0,1)\)) is distinguishable from raw MR/CT intensity even when cmap='gray' greyscale contrast looks similar. Do not share vmin/vmax across a z-score before/after pair: that would hide the affine change again.

roi_mask is drawn only when roi_contour=True, and then only as a cyan outline on the anatomy. Outside-ROI voxels stay visible. Whole-image steps should omit the mask.

Parameters:

  • image – Processed (or only) intensity volume. Array or ImageVolume.

  • before – Optional original volume, same shape as image.

  • roi_mask – Optional ROI (> 0 inside). Contour overlay only; never used to crop the display.

  • axis – If set, draw only this NumPy axis (0, 1, or 2). Default for 3D is a single axial-like panel (axis=0).

  • index – Slice index along axis; auto (anatomy mass / densest ROI) when omitted.

  • cmap – Matplotlib colormap. Default "gray" for MR/CT anatomy.

  • title – Optional figure title (ASCII-sanitised).

  • image_label – Right-hand (or only) panel title.

  • before_label – Left-hand panel title when before is set.

  • direction – Optional SimpleITK direction cosines (9 floats).

  • spacing – Optional SimpleITK voxel spacing (x, y[, z]) in mm.

  • display_convention – "radiological" (default), "neurological", or "native".

  • roi_contour – When True and roi_mask is set, outline the ROI on every anatomy panel.

  • colorbar – Draw an independent colorbar per panel (default True). Pass False to hide it, or a mapping of colorbar style kwargs (shrink, pad, fraction, aspect, ticks, label, …) to override the short default bar.

  • colorbar_label – Colorbar label for the processed (or only) panel.

  • before_colorbar_label – Colorbar label for the original panel when before is set.

  • before_cmap – Colormap for the original panel. Defaults to cmap. Use "gray" with cmap="RdBu_r" so a z-score panel can show signed values while anatomy stays greyscale.

  • symmetric_clim – When True, the processed (or only) panel is windowed symmetrically about zero. Use this for z-score so the colorbar reads as [-a, a] rather than an asymmetric percentile window that hides the signed scale.

  • crop_to – "none" (default) keeps the full field of view, as whole-image preprocessing teaching requires. "roi" zooms every panel to the bounding box of roi_mask so a small lesion fills the frame. Display-only zoom: values, spacing and orientation are unchanged.

  • crop_pad – Voxels of anatomical context kept around the bounding box when crop_to="roi" (default 6).

Returns:

A matplotlib Figure. The caller owns persistence / display.

Raises:

Examples using habit.viz.plot_intensity_slice

Quickstart: Python API

Quickstart: Python API