Difference between revisions of "2016 Winter Project Week/Projects/BatchImageAnalysis"

From NAMIC Wiki
Jump to: navigation, search
Line 20: Line 20:
 
! style="text-align: left; width:27%" |      Objective
 
! style="text-align: left; width:27%" |      Objective
 
<!-- Add a bulleted list of key points -->
 
<!-- Add a bulleted list of key points -->
*  
+
* Run feature detection code over a collection of medical images pulled from PACS
 +
* Investigate a collection of ADC maps of neonates (diffusion MR)
 +
* Patients labeled with age and health status (normal, mildly abnormal, severely abnormal)
 +
* Use 3D SIFT code to see if health status can be detected in images
 +
* (if time) try text analysis of radiology reports
  
 
! style="text-align: left; width:27%" |      Approach, Plan
 
! style="text-align: left; width:27%" |      Approach, Plan
 
<!-- Add a bulleted list of key points -->
 
<!-- Add a bulleted list of key points -->
*  
+
* Use deidentified cohort of neonate images collected from MGH
 +
* Install data and software on AWS, try StarCluster
 +
* Explore visualization options
 +
* (if time) integrate image features with analysis of radiology report text
  
 
! style="text-align: left; width:27%" |      Progress
 
! style="text-align: left; width:27%" |      Progress

Revision as of 00:41, 16 December 2015

Home < 2016 Winter Project Week < Projects < BatchImageAnalysis

Key Investigators

  • Kalli Retzepi (MGH)
  • Yangming Ou (MGH)
  • Matt Toews (?)
  • Steve Pieper (BWH)
  • Sandy Wells (BWH)
  • Randy Gollub (MGH)

Project Description

Objective
  • Run feature detection code over a collection of medical images pulled from PACS
  • Investigate a collection of ADC maps of neonates (diffusion MR)
  • Patients labeled with age and health status (normal, mildly abnormal, severely abnormal)
  • Use 3D SIFT code to see if health status can be detected in images
  • (if time) try text analysis of radiology reports
Approach, Plan
  • Use deidentified cohort of neonate images collected from MGH
  • Install data and software on AWS, try StarCluster
  • Explore visualization options
  • (if time) integrate image features with analysis of radiology report text
Progress

Background and References