Projects:RegistrationRegularization - Revision history

Melonakos: /* Publications */

2010-05-11T20:18:17Z

Publications

Melonakos at 20:03, 20 October 2009

2009-10-20T20:03:57Z

Polina: /* Key Investigators */

2009-09-29T18:17:41Z

Key Investigators

Polina: /* Publications */

2009-09-29T18:17:16Z

Publications

Ythomas: /* Key Investigators */

2009-09-10T22:37:46Z

Key Investigators

Melonakos at 13:41, 28 August 2009

2009-08-28T13:41:06Z

Melonakos at 18:09, 26 August 2009

2009-08-26T18:09:13Z

Melonakos at 18:08, 26 August 2009

2009-08-26T18:08:47Z

Melonakos at 17:43, 13 July 2009

2009-07-13T17:43:08Z

Ythomas: /* Publications */

2009-04-23T17:51:14Z

Publications

← Older revision		Revision as of 20:18, 11 May 2010
Line 73:		Line 73:


−	[http://www.na-mic.org/publications/pages/display?search=Projects:RegistrationRegularization&submit=Search&words=all&title=checked&keywords=checked&authors=checked&abstract=checked&sponsors=checked&searchbytag=checked\| NA-MIC Publications Database]	+	[http://www.na-mic.org/publications/pages/display?search=Projects:RegistrationRegularization&submit=Search&words=all&title=checked&keywords=checked&authors=checked&abstract=checked&sponsors=checked&searchbytag=checked\| NA-MIC Publications Database on Optimal Atlas Regularization in Image Segmentation]



	[[Category: Registration]] [[Category:Segmentation]]		[[Category: Registration]] [[Category:Segmentation]]

← Older revision		Revision as of 20:03, 20 October 2009
Line 1:		Line 1:
	Back to [[Algorithm:MIT\|MIT Algorithms]]		Back to [[Algorithm:MIT\|MIT Algorithms]]
		+	__NOTOC__
		+	= Registration Regularization =

	We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. In non-rigid registration, the tradeoff between warp regularization and image fidelity is typically set empirically. In segmentation, this leads to a probabilistic atlas of arbitrary “sharpness”: weak regularization results in well-aligned training images, producing a “sharp” atlas; strong regularization yields a “blurry” atlas. We study the effects of this tradeoff in the context of cortical surface parcellation, but the framework applies to volume registration as well. This is an important question because of the increasingly availability of atlases in public databases and the development of registration algorithms separate from the atlas construction process.		We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. In non-rigid registration, the tradeoff between warp regularization and image fidelity is typically set empirically. In segmentation, this leads to a probabilistic atlas of arbitrary “sharpness”: weak regularization results in well-aligned training images, producing a “sharp” atlas; strong regularization yields a “blurry” atlas. We study the effects of this tradeoff in the context of cortical surface parcellation, but the framework applies to volume registration as well. This is an important question because of the increasingly availability of atlases in public databases and the development of registration algorithms separate from the atlas construction process.

@@ Line 66: / Line 66: @@
 * MIT : [[http://people.csail.mit.edu/ythomas/ | B.T. Thomas Yeo]], Mert Sabuncu, Polina Golland
-* MGH : Rahul Desikan, Bruce Fischl
+* Harvard : Rahul Desikan, Bruce Fischl
 = Publications =

@@ Line 69: / Line 69: @@
 = Publications =
-* [http://www.na-mic.org/publications/pages/display?search=Projects:RegistrationRegularization&submit=Search&words=all&title=checked&keywords=checked&authors=checked&abstract=checked&sponsors=checked&searchbytag=checked| NA-MIC Publications Database]
 [[Category: Registration]] [[Category:Segmentation]]

@@ Line 65: / Line 65: @@
 = Key Investigators =
-* MIT : [[http://people.csail.mit.edu/ythomas/ | B.T. Thomas Yeo]], Mert Sabuncu, Rahul Desikan, Bruce Fischl, Polina Golland
+* MIT : [[http://people.csail.mit.edu/ythomas/ | B.T. Thomas Yeo]], Mert Sabuncu, Polina Golland
 = Publications =

← Older revision		Revision as of 13:41, 28 August 2009
Line 1:		Line 1:
−	Back to ~~[[NA-MIC_Internal_Collaborations:StructuralImageAnalysis\|NA-MIC Collaborations]],~~ [[Algorithm:MIT\|MIT Algorithms]]	+	Back to [[Algorithm:MIT\|MIT Algorithms]]

	We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. In non-rigid registration, the tradeoff between warp regularization and image fidelity is typically set empirically. In segmentation, this leads to a probabilistic atlas of arbitrary “sharpness”: weak regularization results in well-aligned training images, producing a “sharp” atlas; strong regularization yields a “blurry” atlas. We study the effects of this tradeoff in the context of cortical surface parcellation, but the framework applies to volume registration as well. This is an important question because of the increasingly availability of atlases in public databases and the development of registration algorithms separate from the atlas construction process.		We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. In non-rigid registration, the tradeoff between warp regularization and image fidelity is typically set empirically. In segmentation, this leads to a probabilistic atlas of arbitrary “sharpness”: weak regularization results in well-aligned training images, producing a “sharp” atlas; strong regularization yields a “blurry” atlas. We study the effects of this tradeoff in the context of cortical surface parcellation, but the framework applies to volume registration as well. This is an important question because of the increasingly availability of atlases in public databases and the development of registration algorithms separate from the atlas construction process.

@@ Line 31: / Line 31: @@
 (3) Registration to a single atlas with fixed constrained warps. We call this single atlas, single warp scale (SASS).
-= Experimental Results =
+== Experimental Results ==
 We use dice as the measure of segmentation quality. From the graph below, we note that the optimal algorithms correspond to a unique balance between atlas “sharpness” and warp regularization. Our experiments show that the optimal parameter values that correspond to this balance can be determined using cross-validation. The optimal parameter values are robust across subjects, and the same for both co-registration of the training data and registration of a new subject. This suggests that a single atlas at an optimal sharpness is sufficient to achieve the best segmentation results. Furthermore, our experiments also suggest that segmentation accuracy is tolerant up to a small mismatch between atlas sharpness and warp smoothness.

← Older revision		Revision as of 18:08, 26 August 2009
Line 1:		Line 1:
−	Back to [[NA-MIC_Internal_Collaborations:StructuralImageAnalysis\|NA-MIC Collaborations]], [[Algorithm:MIT\|MIT Algorithms]]	+	Back to [[NA-MIC_Internal_Collaborations:StructuralImageAnalysis\|NA-MIC Collaborations]], [[Algorithm:MIT\|MIT Algorithms]]

	We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. In non-rigid registration, the tradeoff between warp regularization and image fidelity is typically set empirically. In segmentation, this leads to a probabilistic atlas of arbitrary “sharpness”: weak regularization results in well-aligned training images, producing a “sharp” atlas; strong regularization yields a “blurry” atlas. We study the effects of this tradeoff in the context of cortical surface parcellation, but the framework applies to volume registration as well. This is an important question because of the increasingly availability of atlases in public databases and the development of registration algorithms separate from the atlas construction process.		We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. In non-rigid registration, the tradeoff between warp regularization and image fidelity is typically set empirically. In segmentation, this leads to a probabilistic atlas of arbitrary “sharpness”: weak regularization results in well-aligned training images, producing a “sharp” atlas; strong regularization yields a “blurry” atlas. We study the effects of this tradeoff in the context of cortical surface parcellation, but the framework applies to volume registration as well. This is an important question because of the increasingly availability of atlases in public databases and the development of registration algorithms separate from the atlas construction process.

@@ Line 70: / Line 70: @@
 ''In Print''
-* [http://www.na-mic.org/publications/pages/display?search=Projects:RegistrationRegularization%20Yeo&submit=Search&words=all&title=checked&keywords=checked&authors=checked&abstract=checked&sponsors=checked&searchbytag=checked| NA-MIC Publications Database]
+* [http://www.na-mic.org/publications/pages/display?search=Projects:RegistrationRegularization&submit=Search&words=all&title=checked&keywords=checked&authors=checked&abstract=checked&sponsors=checked&searchbytag=checked| NA-MIC Publications Database]
 [[Category: Registration]] [[Category:Segmentation]]