Event:2011-Registration-Retreat-Tuesday - Revision history

Westin: /* = Unsorted Notes */

2011-02-22T18:30:36Z

= Unsorted Notes

2011-02-22T18:30:16Z

Notes

2011-02-22T18:29:09Z

1 Grand challenge in registration

2011-02-22T18:10:32Z

2 What works using current technology

2011-02-22T18:09:32Z

2 What works using current technology

2011-02-22T18:08:57Z

2 What works using current technology

2011-02-22T17:52:33Z

2011-02-22T17:50:53Z

2 What works using current technology

2011-02-22T17:21:29Z

1 Grand challenge in registration

2011-02-22T17:20:08Z

1 Grand challenge in registration

@@ Line 86: / Line 86: @@
 * At invisible landmarks, alignment measures performance of the registration priors (prediction, extrapolation).
-=== Unsorted Notes==
+===Unsorted Notes===
 * Example of such a data is full body registration, with for example data from mice CT.
 * One issue that comes up in a grand challenge is how to define goodness/success. How do we define what is a good registration?

@@ Line 86: / Line 86: @@
 * At invisible landmarks, alignment measures performance of the registration priors (prediction, extrapolation).
-==Notes==
+=== Unsorted Notes==
 * Example of such a data is full body registration, with for example data from mice CT.
 * One issue that comes up in a grand challenge is how to define goodness/success. How do we define what is a good registration?

@@ Line 7: / Line 7: @@
 The motivation for having a grand challenge in registration is to define a problem where current technology fails, and that is interesting for the community to work on. This will likely lead to novel and relevant solutions. A grand challenge will likely have larger impact than more traditional short term contests that aims at finding the best method available with current technology and careful settings of algorithmic parameters.  The task will be to register data sets that are complex enough to force new technology to be developed. Example of grand challenges from other communities, such as for example the vision community is the [http://www.darpa.mil/grandchallenge/overview.asp DARPA Grand Challenges] and the  [http://www.computer.org/portal/web/csdl/doi/10.1109/CVPR.2005.268 Face Recognition Grand Challenge]
-* Example of such a data is full body registration, with for example data from mice CT.
 === Possible Challenges ===
@@ Line 107: / Line 86: @@
 * At invisible landmarks, alignment measures performance of the registration priors (prediction, extrapolation).
 ==2 What works using current technology==

@@ Line 110: / Line 110: @@
 ==2 What works using current technology==
-Draft Word document: [[Media:What works.docx]]
+Draft Word document: [[Media:What works.docx|What works]]
 ==3 White paper outline==

@@ Line 110: / Line 110: @@
 ==2 What works using current technology==
-Draft Word document: [[File:What works.docx]]
+Draft Word document: [[Media:What works.docx]]
 ==3 White paper outline==

← Older revision		Revision as of 18:08, 22 February 2011
Line 109:		Line 109:

	==2 What works using current technology==		==2 What works using current technology==
		+
		+	Draft Word document: [[File:What works.docx]]

	==3 White paper outline==		==3 White paper outline==

@@ Line 42: / Line 42: @@
 # Phase II: run on commodity hardware, run time and memory constraints.
-==== Longitudinal Change Detection ====
+=== Longitudinal Change Detection ===
 Provide baseline and follow-up images (e.g., non-contrast abdominal CT) for a set of cases.
@@ Line 67: / Line 67: @@
 # Solution may not actually involve registration
-==== Multimodal Diagnosis ====
+=== Multi-modality Diagnosis ===
 For a number of cases, provide a collection of images of various modalities, e.g., CT with and without CE, PET, MRI, US.
@@ Line 81: / Line 81: @@
 # Solution may not actually involve registration.
-==== Intra-subject Registration ====
+=== Intra-subject Registration ===
 Provide baseline and follow-up date in a given modality (e.g., CT). Hard-to-register data, e.g., whole-body or abdominal.

@@ Line 29: / Line 29: @@
 * Come up with a medically relevant topic.
 * Asking clinicians if this is good enough, get to the relevance. Then ask the practical questions, is this fast enough, robust enough, ...
 ==2 What works using current technology==
 ==3 White paper outline==

@@ Line 8: / Line 8: @@
 The motivation for having a grand challenge in registration is to define a problem where current technology fails, and that is interesting for the community to work on. This will likely lead to novel and relevant solutions. A grand challenge will likely have larger impact than more traditional short term contests that aims at finding the best method available with current technology and careful settings of algorithmic parameters.  The task will be to register data sets that are complex enough to force new technology to be developed. Example of grand challenges from other communities, such as for example the vision community is the [http://www.darpa.mil/grandchallenge/overview.asp DARPA Grand Challenges] and the  [http://www.computer.org/portal/web/csdl/doi/10.1109/CVPR.2005.268 Face Recognition Grand Challenge]
 * Example of such a data is full body registration, with for example data from mice CT.
-* How do we define good registration,
+* One issue that comes up in a grand challenge is how to define goodness/success. How do we define what is a good registration?
 * Vanderbilt data set. Blind evaluation and “you cheat you lose” approach.
 * Look at taxonomy, see what checks off: if speed is important, if ...