Voxel

As explained in Deep Learning with PyTorch, Second Edition

A three-dimensional volume element used to discretize volumetric data.

A voxel is the three-dimensional equivalent of a pixel: it encloses a volume of space and usually sits in a three-dimensional grid. In CT scans, each voxel stores a numeric value that roughly represents the average mass density inside it. section 11.3

Voxels can be cubic, but CT data may use rectangular prisms with different length, width, and height. Their values help distinguish dense bone and metal from air, lung tissue, fat, and other tissue. section 11.3

Working with voxels requires consistent coordinate units. Physical locations measured in millimeters must be transformed into voxel-array addresses—index, row, and column—before extracting data. section 12.4.1

Finding anatomy in a CT array

A candidate nodule location expressed as patient coordinates (X,Y,Z) cannot be used directly as an array index. DICOM or MetaImage header metadata supplies the transformation to voxel coordinates (I,R,C), allowing the corresponding CT region to be sliced. section 12.4.1

Figure 12.5 Using the transformation information to convert a nodule center coordinate in candidate coordinates (X,Y,Z) to an array index (I,R,C)

Trace how transformation information converts a nodule center from patient coordinates into a CT-array address. section 12.4.1

How Deep Learning with PyTorch, Second Edition covers it

How deep it goes

Defines voxel geometry and density values, then explains coordinate transformation without detailing array-slicing implementation.

Examples

Uses CT density visualization, rectangular-prism voxels, and nodule-coordinate conversion as concrete examples.

What it assumes

Assumes familiarity with arrays and pixels while establishing three-dimensional volume, physical units, and medical-image coordinates.

What you can do after

Apply voxel-coordinate transformations to locate anatomy and extract corresponding regions from CT arrays.

How it connects

Connects voxels with pixels, CT scans, patient coordinate systems, array indexing, and DICOM metadata.

liveBookmanning.com

Read Deep Learning with PyTorch, Second Edition on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Geometry for ProgrammersA voxel is a volumetric cell in a regularly sampled three-dimensional grid representing spatial data or material occupancy.

Compare how 2 books explain voxel →

Related concepts

• pixelkind of · A pixel is either a discrete sample carrying visual information at a position in a digital image or a reference unit used to express rendered dimensions.
• segmentation maskequivalent to · A segmentation mask is an image-shaped array that assigns each pixel or spatial element to a class, object, region, or corresponding segmentation value.
• meshcontrasts with · A mesh is a discrete geometric representation composed of interconnected vertices, edges, and faces or other elements covering a shape or region.
• computed tomographyhas part · Computed tomography is an imaging technique that uses multiple X-ray measurements and computational reconstruction to produce cross-sectional or volumetric images.
• 3D imagepart of · A 3D image is a three-dimensional sampled representation of geometry or spatial data arranged as image-like values.
• boolean operationused by · A Boolean operation combines or modifies geometric regions using set-like operations such as union, intersection, and difference.

This explainer was generated by Manning's knowledge graph from the text of Deep Learning with PyTorch, Second Edition. The section links point to the parts of the book it draws on.