Difference between revisions of "Event:2011-Registration-Retreat-Tuesday"

From NAMIC Wiki
Jump to: navigation, search
Line 9: Line 9:
  
  
** Grand challenge, pick problem that current technology fails on. Will have a greater impact that a normal miccai contest, tweaking current methods.
+
* Grand challenge, pick problem that current technology fails on. Will have a greater impact that a normal miccai contest, tweaking current methods.
** Define a general data set, that is complex enough to force new technology.
+
* Define a general data set, that is complex enough to force new technology.
** Example data set full body registration, for example mice
+
* Example data set full body registration, for example mice
** How do we define good registration,  
+
* How do we define good registration,  
** Vanderbilt data set. Blind evaluation and “you cheat you lose” approach.
+
* Vanderbilt data set. Blind evaluation and “you cheat you lose” approach.
** Look at taxonomy, see what checks off: if speed is important, if ...
+
* Look at taxonomy, see what checks off: if speed is important, if ...
** Use a clinical outcome for the quality of the result? Use a secondary system, that relies on the registration to make its decision.
+
* Use a clinical outcome for the quality of the result? Use a secondary system, that relies on the registration to make its decision.
** Subjective clinical decisions often not reliable (example size of ventricles, normal, enlarged, hugely enlarged)
+
* Subjective clinical decisions often not reliable (example size of ventricles, normal, enlarged, hugely enlarged)
** Several grand challenges, for example estimate the uncertainty of the registration.
+
* Several grand challenges, for example estimate the uncertainty of the registration.
** What can today’s method to well? Good start to find a grand challenge.  
+
* What can today’s method to well? Good start to find a grand challenge.  
** Pig, 1000 lead balls. CT the Pig, move, CT again. Do radiation therapy. Shrink tumors. etc.
+
* Pig, 1000 lead balls. CT the Pig, move, CT again. Do radiation therapy. Shrink tumors. etc.
** Need a grant to get such a project going.
+
* Need a grant to get such a project going.
** The balls migrate over time, can we use anatomical landmarks. Can we use features in the data for landmarks that also will be used for driving the algorithm?
+
* The balls migrate over time, can we use anatomical landmarks. Can we use features in the data for landmarks that also will be used for driving the algorithm?
** Error bars on positions of landmarks.
+
* Error bars on positions of landmarks.
** Find landmarks, easier in bone, vascularture, gyration patterns, more difficult with breast, and in white matter.
+
* Find landmarks, easier in bone, vascularture, gyration patterns, more difficult with breast, and in white matter.
** Using anatomical feature for registration often robust (vasculature, ..).  
+
* Using anatomical feature for registration often robust (vasculature, ..).  
** Define validation strategies that most people agree on, but is strongly related to the applications.
+
* Define validation strategies that most people agree on, but is strongly related to the applications.
** What is the aspect, robustness, accuracy, speed? Need to be specific in a challenge.
+
* What is the aspect, robustness, accuracy, speed? Need to be specific in a challenge.
** Two types of registration, having visual landmarks, or not. If no visible features, still models of stiffness and physical properties can meaningfully predict movement.
+
* Two types of registration, having visual landmarks, or not. If no visible features, still models of stiffness and physical properties can meaningfully predict movement.
** Point landmarks, Synthetic data, what are the taxonomy for metrics?  
+
* Point landmarks, Synthetic data, what are the taxonomy for metrics?  
** Other user (metrics?) critera are: is it to slow, is it useful? Amount of user interaction, etc.
+
* Other user (metrics?) critera are: is it to slow, is it useful? Amount of user interaction, etc.
** Marketing, grant challenge should capture imagination, should not be technology oriented.  A vision that can capture attention, and funding.
+
* Marketing, grant challenge should capture imagination, should not be technology oriented.  A vision that can capture attention, and funding.
** Come up with a medically relevant topic.  
+
* 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, ...
+
* Asking clinicians if this is good enough, get to the relevance. Then ask the practical questions, is this fast enough, robust enough, ...
  
* What works using current technology
+
==What works using current technology==
  
* White paper outline
+
==White paper outline==

Revision as of 17:02, 22 February 2011

Home < Event:2011-Registration-Retreat-Tuesday
 Back to Registration Brainstorming 2011


Tuesday registration topics

Grand challenge in registration

Example from the vision community is the face recognition grand challenge


  • Grand challenge, pick problem that current technology fails on. Will have a greater impact that a normal miccai contest, tweaking current methods.
  • Define a general data set, that is complex enough to force new technology.
  • Example data set full body registration, for example mice
  • How do we define 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 ...
  • Use a clinical outcome for the quality of the result? Use a secondary system, that relies on the registration to make its decision.
  • Subjective clinical decisions often not reliable (example size of ventricles, normal, enlarged, hugely enlarged)
  • Several grand challenges, for example estimate the uncertainty of the registration.
  • What can today’s method to well? Good start to find a grand challenge.
  • Pig, 1000 lead balls. CT the Pig, move, CT again. Do radiation therapy. Shrink tumors. etc.
  • Need a grant to get such a project going.
  • The balls migrate over time, can we use anatomical landmarks. Can we use features in the data for landmarks that also will be used for driving the algorithm?
  • Error bars on positions of landmarks.
  • Find landmarks, easier in bone, vascularture, gyration patterns, more difficult with breast, and in white matter.
  • Using anatomical feature for registration often robust (vasculature, ..).
  • Define validation strategies that most people agree on, but is strongly related to the applications.
  • What is the aspect, robustness, accuracy, speed? Need to be specific in a challenge.
  • Two types of registration, having visual landmarks, or not. If no visible features, still models of stiffness and physical properties can meaningfully predict movement.
  • Point landmarks, Synthetic data, what are the taxonomy for metrics?
  • Other user (metrics?) critera are: is it to slow, is it useful? Amount of user interaction, etc.
  • Marketing, grant challenge should capture imagination, should not be technology oriented. A vision that can capture attention, and funding.
  • 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, ...

What works using current technology

White paper outline