CIBC:Seg3D2:Reference

From SCIRun Documentation Wiki
Jump to navigation Jump to search

Seg3D Reference

Tools

The tools in this section are useful functions in formatting and segmenting data, but are not usually considered filters. The formatting tools can be used on either mask or image data, and can generally be performed on more than one layer at once. The remaining tools are for segmentation.

  • Copy/Paste:
    • This tool allows the user to copy and paste data from one mask to another.
  • Crop:
    • The crop tool will crop one or more layer to a specified size.
  • Flip/Rotate:
    • The Flip/Rotate tool will flip or rotate 90 degrees one or more layer around a specified axis.
  • Invert:
    • This tool will invert the data in a layer to its minimum and maximum, making a negative of the input data.
  • Measure:
    • The measure tool will calculate the distance between two points chosen in the viewer windows.
  • Pad:
    • The pad tool a tool that allows the user to pad one or more volumes.
  • Paint Brush:
    • The paint brush tool a tool that allows full manual creating and editing of mask layers.
  • Select Points:
    • Select and export a set of points.
  • Point Set Registration:
    • The point set registration tool will register one mask layer to another mask layer.
  • Polyline:
    • The polyline tool allows the user to define a region of the layer to modify by adding or erasing the data in the region defined by the polyline.
  • Resample:
    • The resample tool allows the user to resample one or more volumes to change the resolution.
  • Speedline:
    • The speedline tool is similar to the polyline tool in that you use lines to identify a region to segment, but the speedline tool attempts to alter that path between set points to find edges in the image data.
  • Threshold:
    • The threshold tool generates a mask label from an image data volume and the value range to select.
  • Transform:
    • The transform tool can be used to translate and scale one or more layers.

Large Volume Tools

  • Extract Data Layer:
    • Select one of the levels of detail from the large data volume and convert it into a normal data layer.

Mask Filters

The filters listed in the Mask Filters menu all use mask layers as inputs. These filters, with one exception (Connected Component Size) also produce a new or replaced mask layer. These tools are simple, yet effective in manipulating mask layer data and can be used in conjunction with the threshold tool at others to create very accurate and nice looking segmentations.

  • Boolean AND:
    • The boolean AND filter find the intersection of two masks.
  • Boolean OR:
    • The boolean OR filter produces the union of two masks.
  • Boolean Remove:
    • The boolean REMOVE filter removes the intersecting region of two masks from the first.
  • Boolean XOR:
    • The boolean XOR filter produces the unique regions of two masks.
  • Connected Components Filter:
    • The connected component filter finds connected data regions in a mask layer that are coincident to the defined seed points.
  • Connected Component Size Filter:
    • The connected component size filter is similar to the connected component filter, but will return a image data layer labeling each connected region with a data value corresponding to its size (logarithmic or linear scale).
  • Fast Binary Dilate ->Erode:
    • The fast binary dilate -> erode filter will make a label mask bigger (dilate) or smaller (erode).
  • Fill Holes:
    • The fill holes filter can be used to fill unmarked regions which are surrounded by a data in a mask layer.
  • Smooth Binary Dilate -> Erode:
    • The fast binary dilate -> erode filter will make a label mask bigger (dilate) or smaller (erode).

Data Filters

The filters listed in the Data Filters menu all use data layers as inputs. Most of these filters also produce a new or replaced data layer as the output. These most of these tools are manipulating image data, such as smoothing and noise reduction, but two of the filters (Neighborhood Connected and Otsu Threshold) generate segmentations (mask layers) based on the data in the data layer.

  • Arithmetic Filter:
    • The arithmetic filter allows the user to run basic arithmetic and boolean operations on both image and mask data on a pixel by pixel basis.
  • Gaussian Blur:
    • The Gaussian blur filter performs a smoothing on the data layer using a discrete Gaussian kernel.
  • Mask Data Filter:
    • The mask data filter will use the second input of a mask layer to selectively discard (retain) data in a data layer.
  • Mean Filter:
    • The mean filter performs a smoothing on the data layer using a discrete step function kernel.
  • Median Filter:
    • The median filter is a non-linear filter that will reduce noise (speckle), but may also preserve or enhance sharp boundaries.
  • Neighborhood Connected Filter:
    • The neighborhood connected filter is like a combination of the threshold tool and the connected component filter.
  • Otsu Threshold Filter:
    • The Otsu threshold filter attempts to cluster data values in a data layer based upon how similar they are and create mask layers identifying the regions of similar data.

Advanced Filters

The filters listed in the Advance Filters menu are of various types and purpose. Filters in this menu either require advanced computational techniques, have multiple parameters, require larger compute times, or a combination of these. Some of these filter require multiple input of both mask and data layers and may require careful tuning of the parameters to work with different sources of image data. However, the user should not be discouraged as most of the filters are actually quite easy to use. This section should explain these filters with the intent to reduce the guess work as much as possible.

  • Canny Edge Filter:
    • This filter will output the pixels that are edges in a mask layer.
  • Confidence Connected Filter:
    • The confidence connected filter will find connected pixels in a data volume that are statistically similar to pixels surrounding the user defined seed points and output them as a mask layer.
  • Curvature Anisotropic Diffusion:
    • The curvature anisotropic diffusion performs anisotropic diffusion on a data layer using the modified curvature diffusion equation (MCDE).
  • Distance Map:
    • The distance map filter will calculate the distance to the surface of a mask for every pixel in the volume.
  • Gradient Anisotropic Diffusion Filter
    • The gradient anisotropic diffusion performs anisotropic diffusion on a data layer and uses an additional edge enhancing step to preserve useful features.
  • Gradient Magnitude Filter:
    • The gradient magnitude filter will calculate the gradient magnitude of a data layer and output a new or replaced data layer containing the gradient magnitude.
  • Histogram Equalization Filter:
    • The histogram equalization filter will compute the histogram of the data image layer and attempt to transform the image so that the histogram is as flat as possible.
  • Intensity Correction Filter:
    • The intensity correction filter attempts to make the intensity over the data layer homogenous.
  • Segmentation Level Set:
    • The segmentation level set filter is an iterative segmentation filter that uses a seed volume to find the regions in a data volume that are similar to the original seed.
Retrieved from "http://scirundocwiki.sci.utah.edu/SCIRunDocs/index.php?title=CIBC:Seg3D2:Reference&oldid=9493"