Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Workflow of RaCaT.

All tasks marked with a * are optional and can be selected by the user.

More »

Fig 1 Expand

Fig 2.

Organization of the class NGTDM features.

The class has as attributes some basic values needed for the calculation of NGTDM features, as well as every NGTDM feature. The functions include the function to create the NGTD matrix, functions that fill and create the output file, and for every feature a function that calculates the feature.

More »

Fig 2 Expand

Table 1.

Files required by RaCaT including their abbreviations that have to be given to the executable.

More »

Table 1 Expand

Fig 3.

Necessary steps for running the executable.

More »

Fig 3 Expand

Table 2.

Implemented feature groups and corresponding abbreviations.

More »

Table 2 Expand

Fig 4.

Example of configuration file.

The user can set the required preprocessing steps, like e.g. re-segmentation by setting the ReSegmentImage parameter from 0 to 1. Other parameters like the number of bind (NrBins) can also be set to any required value.

More »

Fig 4 Expand

Fig 5.

Example of feature output definition file.

If a feature group should not be included in the calculations, the value for the corresponding group has to be set to 0.

More »

Fig 5 Expand

Fig 6.

PET Scan of the NEMA image quality phantom.

The image quality phantom contains six spheres with different diameters. For comparison, the spheres were segmented in the image and morphological features were calculated.

More »

Fig 6 Expand

Table 3.

Morphological features calculated by RaCaT, the expected value, and the percentage differences between these two values for the spheres of the NEMA image quality phantom.

More »

Table 3 Expand

Fig 7.

Maximum intensity projection of Patient 1 (left) and patient 2 (right). The tumors used for feature calculation are marked in the images. Tumors were manually segmented and used for computation of radiomic features.

More »

Fig 7 Expand

Table 4.

Radiomic features extracted from cancer patients.

More »

Table 4 Expand