Documentation/Nightly/Modules/PETTumorSegmentEditorEffect - Revision history

Chribaue at 17:24, 4 April 2022

2022-04-04T17:24:08Z

Chribaue at 17:15, 4 April 2022

2022-04-04T17:15:26Z

Chribaue: added illustration for interaction styles

2022-04-04T17:00:48Z

added illustration for interaction styles

Chribaue: updated funding sources

2017-06-19T15:21:17Z

updated funding sources

Chribaue: Created page with "{{documentation/versioncheck}} {{documentation/{{documentation/version}}/module-header}}

@@ Line 85: / Line 85: @@
 *Denoise Threshold: Calculates threshold based on median-filtered image.  Use only if scan is very noisy.
 *Linear Cost: Cost function below threshold is linear rather than based on region.  Use only if little/no transition region in uptake.
 <!-- ---------------------------- -->

@@ Line 67: / Line 67: @@
 After changing segmentation options, click "Apply" to update the segmentation result.
 Options:
 *Splitting: Cut off adjacent objects to the target via watershed or local minimum.  Useful for lymph node chains.
 *Assist Centering: Move the center to the highest voxel within a 7 mm range, without being on or next to other object labels.  Improves consistency.
 *Sealing: Close single-voxel gaps in the object or between the object and other objects, if above the threshold.  Useful for lymph node chains.
 *Allow Overwriting: Ignore other object labels.
 Advanced Options:

@@ Line 1: / Line 1: @@
-<noinclude>{{documentation/versioncheck}}</noinclude>
+<noinclude>{{documentation/versioncheck}}
-<!-- ---------------------------- -->
+</noinclude>
 {{documentation/{{documentation/version}}/module-header}}
 <!-- ---------------------------- -->
@@ Line 32: / Line 33: @@
-<!-- ---------------------------- -->
+<!-- ---------------------------- -->{{documentation/{{documentation/version}}/module-section|Tutorial - Basic Tumor and Lymph Node Segmentation}}
 {{documentation/{{documentation/version}}/module-section|Tutorial - Basic Tumor and Lymph Node Segmentation}}
 Step 1) Load PET scan.
@@ Line 49: / Line 51: @@
 <!-- ---------------------------- -->
 {{documentation/{{documentation/version}}/module-section|Segmentation Refinement}}
 In cases where the algorithm was not able to produce the desired segmentation with one click, the user may interactively refine the the segmentation using these three interaction styles:
-* Interaction style "Create new": Create a new segmentation with the same label as the previous segmentation. After selection, click approximately at the center of the new region to segment.
+*Interaction style "Create new": Create a new segmentation with the same label as the previous segmentation. After selection, click approximately at the center of the new region to segment.
-* Interaction style "Global refinement": Choose this option in cases where the whole segmentation appears to be too large or too small. After selection, click on a point the new boundary should go through. This changes the whole boundary of the segmentation.
+*Interaction style "Global refinement": Choose this option in cases where the whole segmentation appears to be too large or too small. After selection, click on a point the new boundary should go through. This changes the whole boundary of the segmentation.
-* Interaction style "Local refinement": Choose this option in cases where most of the segmentation appears correct, but there are local segmentation errors. After selection, click on a point the new boundary should go through. This changes the boundary of the segmentation in the area of the segmentation error.
+*Interaction style "Local refinement": Choose this option in cases where most of the segmentation appears correct, but there are local segmentation errors. After selection, click on a point the new boundary should go through. This changes the boundary of the segmentation in the area of the segmentation error.
-All interaction sytles can be applied several times until the desired segmentation result is obtained.
+All interaction styles can be applied several times until the desired segmentation result is obtained.
 <!-- ---------------------------- -->
@@ Line 66: / Line 69: @@
 Options:
 * Splitting: Cut off adjacent objects to the target via watershed or local minimum.  Useful for lymph node chains.
-* Assist Centering: Move the center to the highest voxel within a 7 mm range, without being on or next to other object labels.  Improves consistency.
+*Splitting: Cut off adjacent objects to the target via watershed or local minimum.  Useful for lymph node chains.
-* Sealing: Close single-voxel gaps in the object or between the object and other objects, if above the threshold.  Useful for lymph node chains.
+*Assist Centering: Move the center to the highest voxel within a 7 mm range, without being on or next to other object labels.  Improves consistency.
-* Allow Overwriting: Ignore other object labels.
+*Sealing: Close single-voxel gaps in the object or between the object and other objects, if above the threshold.  Useful for lymph node chains.
 Advanced Options:
 * Necrotic Region: Prevents cutoff from low uptake.  Use if placing a center inside a necrotic region.
-* Denoise Threshold: Calculates threshold based on median-filtered image.  Use only if scan is very noisy.
+*Necrotic Region: Prevents cutoff from low uptake.  Use if placing a center inside a necrotic region.
-* Linear Cost: Cost function below threshold is linear rather than based on region.  Use only if little/no transition region in uptake.
+*Denoise Threshold: Calculates threshold based on median-filtered image.  Use only if scan is very noisy.
 <!-- ---------------------------- -->
 {{documentation/{{documentation/version}}/module-section|References}}
-* R. R. Beichel, M. Van Tol, E. J. Ulrich, C. Bauer, T. Chang, K. A. Plichta, B. J. Smith, J. J. Sunderland, M. M. Graham, M. Sonka, J. M. Buatti: "Semiautomated Segmentation of Head and Neck Cancers in 18F-FDG PET Scans: A Just-Enough-Interaction Approach", in Medical Physics, 2016. [http://dx.doi.org/10.1118/1.4948679 http://dx.doi.org/10.1118/1.4948679]
 <!-- ---------------------------- -->
 {{documentation/{{documentation/version}}/module-footer}}
 <!-- ---------------------------- -->

@@ Line 9: / Line 9: @@
 {{documentation/{{documentation/version}}/module-introduction-row}}
 Acknowledgments:
-The UIowa [http://imaging.cancer.gov/programsandresources/specializedinitiatives/qin QIN] PET Tumor Segmentation tool was  is funded in part by [http://imaging.cancer.gov/programsandresources/specializedinitiatives/qin/iowa Quantitative Imaging to Assess Response in Cancer Therapy Trials] NIH grant U01-CA140206 and [http://qiicr.org Quantitative Image Informatics for Cancer Research (QIICR)] NIH grant U24 CA180918. <br>
+The UIowa [http://imaging.cancer.gov/programsandresources/specializedinitiatives/qin QIN] PET Tumor Segmentation tool was  is funded in part by [http://imaging.cancer.gov/programsandresources/specializedinitiatives/qin/iowa Quantitative Imaging to Assess Response in Cancer Therapy Trials] NIH grant U01-CA140206 and [http://qiicr.org Quantitative Image Informatics for Cancer Research (QIICR)] NIH grant U24 CA180918, and Graph-based Medical Image Segmentation in 3D and 4D NIH grant R01 EB004640 <br>
 Authors: Christian Bauer (University of Iowa), Markus van Tol (University of Iowa) <br>
 Contributors: Ethan Ulrich (University of Iowa), Andrey Fedorov (SPL), Reinhard Beichel (University of Iowa), John Buatti (University of Iowa)<br>