Projects:MGH-HeadAndNeck-RT - Revision history

Ygao at 01:02, 16 November 2013

2013-11-16T01:02:52Z

Ygao at 16:11, 12 January 2012

2012-01-12T16:11:15Z

Ivan.kolesov at 18:34, 23 March 2011

2011-03-23T18:34:38Z

Ivan.kolesov at 18:30, 23 March 2011

2011-03-23T18:30:44Z

Ivan.kolesov at 18:28, 23 March 2011

2011-03-23T18:28:28Z

Ivan.kolesov at 18:28, 23 March 2011

2011-03-23T18:28:11Z

Ivan.kolesov at 18:26, 23 March 2011

2011-03-23T18:26:06Z

Ivan.kolesov at 18:25, 23 March 2011

2011-03-23T18:25:00Z

Ivan.kolesov at 18:22, 23 March 2011

2011-03-23T18:22:16Z

Ivan.kolesov at 17:51, 23 March 2011

2011-03-23T17:51:29Z

@@ Line 1: / Line 1: @@
-  Back to [[Algorithm:BU|Boston University Algorithms]]
+  Back to [[Algorithm:Stony Brook|Stony Brook University Algorithms]]
 __NOTOC__
 = Adaptive Radiotherapy for head, neck and thorax =

@@ Line 1: / Line 1: @@
-  Back to [[Algorithm:GATech|Georgia Tech Algorithms]]
+  Back to [[Algorithm:BU|Boston University Algorithms]]
 __NOTOC__
 = Adaptive Radiotherapy for head, neck and thorax =

← Older revision		Revision as of 18:34, 23 March 2011
Line 14:		Line 14:

	== Current State of Work ==		== Current State of Work ==
−		+	We have gathered a sample data set; currently, we are registering the scan to create a united patient model. This model will localize structures and constrain shape. Additionally, we are investigation interaction approaches for registration and segmentation that will "put the user in the loop" but greatly reduce the work compared to manual approaches.
−	~~Currently~~, we are ~~collecting patient~~ scan ~~with physician drawn label maps~~ to ~~build the~~ model ~~for~~ shape ~~analysis~~. ~~In parallel~~, ~~synthetic data is being used to develop/test~~ the ~~algorithm used to calculate~~ the ~~likelihood metric and~~ the ~~likely location of a structure given previously segmented structures. The graph cut implementation is read~~ to ~~accept the unsigned distance map as prior information~~.

@@ Line 9: / Line 9: @@
 Initial experiments show that bony structures such as the mandible can be segmented accurately with a variational active contour. However, for soft tissue such as the brain stem, the intensity profile does not contain sufficient information for reasonably accurate segmentation. To deal with "soft boundaries" infinite dimensional active contours must be constrained by using shape priors and/or interactive user input. One way to constrain a segmentation is shown in our work in MTNS; there, known spatial relationships between structures is exploited. First, a structure we are confident in will be segmented. Using probabilistic PCA a metric used to describe how likely the structure whose segmentation we have obtained is; this metric is essentially a description of how confident we are in the correct segmentation. Then, the location of this structure will be used as prior information(it becomes a landmark) to segment a more difficult structure. Iteratively, the nth structure to be segmented will have n-1 priors do draw information from with a confidence metric for each prior. The likely location of the nth structure, calculated as described above, will serve as an input to constrain an active contours algorithm. Additionally, we have had excellent results when constraining structures of the eye to simple geometrical shapes such as ellipses and tubular to limit the number of free parameter. A sample segmentation of the eye ball is shown below.
-* [[Image:3D_eye.png | Eye Seg| 250px]] Segmentation of the eye ball.
+* [[Image:Model3D_upTrans.png | Rel Pred| 250px]] Prediction of mandible location(red) give a brainstem(yellow) and larynx(blue) segmentation; ground truth segmenation is green.
 * [[Image:3D_eye.png | Eye Seg| 250px]] Segmentation of the eye ball.

@@ Line 11: / Line 11: @@
 * [[Image:3D_eye.png | Eye Seg| 250px]] Segmentation of the eye ball.
 * [[Image:3D_eye.png | Eye Seg| 250px]] Segmentation of the eye ball.
-[[File:3D_eye.png|200px|thumb|left|Segmentation of the eye ball.]]
 == Current State of Work ==

← Older revision		Revision as of 18:28, 23 March 2011
Line 9:		Line 9:
	Initial experiments show that bony structures such as the mandible can be segmented accurately with a variational active contour. However, for soft tissue such as the brain stem, the intensity profile does not contain sufficient information for reasonably accurate segmentation. To deal with "soft boundaries" infinite dimensional active contours must be constrained by using shape priors and/or interactive user input. One way to constrain a segmentation is shown in our work in MTNS; there, known spatial relationships between structures is exploited. First, a structure we are confident in will be segmented. Using probabilistic PCA a metric used to describe how likely the structure whose segmentation we have obtained is; this metric is essentially a description of how confident we are in the correct segmentation. Then, the location of this structure will be used as prior information(it becomes a landmark) to segment a more difficult structure. Iteratively, the nth structure to be segmented will have n-1 priors do draw information from with a confidence metric for each prior. The likely location of the nth structure, calculated as described above, will serve as an input to constrain an active contours algorithm. Additionally, we have had excellent results when constraining structures of the eye to simple geometrical shapes such as ellipses and tubular to limit the number of free parameter. A sample segmentation of the eye ball is shown below.		Initial experiments show that bony structures such as the mandible can be segmented accurately with a variational active contour. However, for soft tissue such as the brain stem, the intensity profile does not contain sufficient information for reasonably accurate segmentation. To deal with "soft boundaries" infinite dimensional active contours must be constrained by using shape priors and/or interactive user input. One way to constrain a segmentation is shown in our work in MTNS; there, known spatial relationships between structures is exploited. First, a structure we are confident in will be segmented. Using probabilistic PCA a metric used to describe how likely the structure whose segmentation we have obtained is; this metric is essentially a description of how confident we are in the correct segmentation. Then, the location of this structure will be used as prior information(it becomes a landmark) to segment a more difficult structure. Iteratively, the nth structure to be segmented will have n-1 priors do draw information from with a confidence metric for each prior. The likely location of the nth structure, calculated as described above, will serve as an input to constrain an active contours algorithm. Additionally, we have had excellent results when constraining structures of the eye to simple geometrical shapes such as ellipses and tubular to limit the number of free parameter. A sample segmentation of the eye ball is shown below.

		+	* [[Image:3D_eye.png \| Eye Seg\| 250px]] Segmentation of the eye ball.
		+	* [[Image:3D_eye.png \| Eye Seg\| 250px]] Segmentation of the eye ball.
	[[File:3D_eye.png\|200px\|thumb\|left\|Segmentation of the eye ball.]]		[[File:3D_eye.png\|200px\|thumb\|left\|Segmentation of the eye ball.]]

← Older revision		Revision as of 18:25, 23 March 2011
Line 8:		Line 8:

	Initial experiments show that bony structures such as the mandible can be segmented accurately with a variational active contour. However, for soft tissue such as the brain stem, the intensity profile does not contain sufficient information for reasonably accurate segmentation. To deal with "soft boundaries" infinite dimensional active contours must be constrained by using shape priors and/or interactive user input. One way to constrain a segmentation is shown in our work in MTNS; there, known spatial relationships between structures is exploited. First, a structure we are confident in will be segmented. Using probabilistic PCA a metric used to describe how likely the structure whose segmentation we have obtained is; this metric is essentially a description of how confident we are in the correct segmentation. Then, the location of this structure will be used as prior information(it becomes a landmark) to segment a more difficult structure. Iteratively, the nth structure to be segmented will have n-1 priors do draw information from with a confidence metric for each prior. The likely location of the nth structure, calculated as described above, will serve as an input to constrain an active contours algorithm. Additionally, we have had excellent results when constraining structures of the eye to simple geometrical shapes such as ellipses and tubular to limit the number of free parameter. A sample segmentation of the eye ball is shown below.		Initial experiments show that bony structures such as the mandible can be segmented accurately with a variational active contour. However, for soft tissue such as the brain stem, the intensity profile does not contain sufficient information for reasonably accurate segmentation. To deal with "soft boundaries" infinite dimensional active contours must be constrained by using shape priors and/or interactive user input. One way to constrain a segmentation is shown in our work in MTNS; there, known spatial relationships between structures is exploited. First, a structure we are confident in will be segmented. Using probabilistic PCA a metric used to describe how likely the structure whose segmentation we have obtained is; this metric is essentially a description of how confident we are in the correct segmentation. Then, the location of this structure will be used as prior information(it becomes a landmark) to segment a more difficult structure. Iteratively, the nth structure to be segmented will have n-1 priors do draw information from with a confidence metric for each prior. The likely location of the nth structure, calculated as described above, will serve as an input to constrain an active contours algorithm. Additionally, we have had excellent results when constraining structures of the eye to simple geometrical shapes such as ellipses and tubular to limit the number of free parameter. A sample segmentation of the eye ball is shown below.
		+
		+	[[File:3D_eye.png\|200px\|thumb\|left\|alt text]]

	== Current State of Work ==		== Current State of Work ==

@@ Line 7: / Line 7: @@
 = Description =
-Initial experiments show that bony structures such as the mandible can be segmented accurately with a variational active contour. However, for soft tissue such as the brain stem, the intensity profile does not contain sufficient information for reasonably accurate segmentation. To deal with "soft boundaries" infinite dimensional active contours must be constrained by using shape priors and/or interactive user input. They will be included in the following manner. First, a structure we are confident in will be segmented. Using probabilistic PCA a metric used to describe how likely the structure whose segmentation we have obtained is; this metric is essentially a description of how confident we are in the correct segmentation. Then, the location of this structure will be used as prior information(it becomes a landmark) to segment a more difficult structure. Iteratively, the nth structure to be segmented will have n-1 priors do draw information from with a confidence metric for each prior. The likely location of the nth structure, calculated as described above, will serve as an input to a graph cut algorithm, which will perform the optimization, in the form of a distance function. This distance function regulates how easy or difficult it is to cut links between neighbors(in other words, where the segmentation boundary will be drawn).
+Initial experiments show that bony structures such as the mandible can be segmented accurately with a variational active contour. However, for soft tissue such as the brain stem, the intensity profile does not contain sufficient information for reasonably accurate segmentation. To deal with "soft boundaries" infinite dimensional active contours must be constrained by using shape priors and/or interactive user input. One way to constrain a segmentation is shown in our work in MTNS; there, known spatial relationships between structures is exploited. First, a structure we are confident in will be segmented. Using probabilistic PCA a metric used to describe how likely the structure whose segmentation we have obtained is; this metric is essentially a description of how confident we are in the correct segmentation. Then, the location of this structure will be used as prior information(it becomes a landmark) to segment a more difficult structure. Iteratively, the nth structure to be segmented will have n-1 priors do draw information from with a confidence metric for each prior. The likely location of the nth structure, calculated as described above, will serve as an input to constrain an active contours algorithm.
 == Current State of Work ==