Difference between revisions of "DBP3:MGH"
From NAMIC Wiki
Line 15: | Line 15: | ||
=== Image Segmentation === | === Image Segmentation === | ||
− | *Recommend: Automatic segmentation (atlas-based) | + | *Require: Contour propagation for intra-subject segmentation |
− | *Recommend: Automatic segmentation (model-based) | + | *Recommend: Automatic segmentation (atlas-based) for inter-subject segmentation |
+ | *Recommend: Automatic segmentation (model-based) for inter-subject segmentation | ||
=== Radiotherapy Workflow === | === Radiotherapy Workflow === |
Revision as of 03:23, 16 November 2010
Home < DBP3:MGHProject plan for NA-MIC DBP on adaptive radiotherapy (MGH)
http://www.na-mic.org/pages/DBP:Head_and_Neck_Cancer
Contents
DBP Science
- Require: Update literature review
- Recommend: Study to quantify geometry of anatomic differences
- Require: Comparison study of delivered vs. planned dose
- Require: Comparison study of delivered vs. adaptive dose
- Wishlist: Comparison study of IMRT vs. protons
Image Registration
- Recommend: Experimental evaluation of existing registration methods
- Require: Interactive registration (landmark splines)
Image Segmentation
- Require: Contour propagation for intra-subject segmentation
- Recommend: Automatic segmentation (atlas-based) for inter-subject segmentation
- Recommend: Automatic segmentation (model-based) for inter-subject segmentation
Radiotherapy Workflow
- Goal: Reasonably complete workflow, including dose review and comparison tools
- Require: Labelmap that can handle overlapping structures
- Require: Visualization of RT dose (2D, as isodose lines, with legend)
- Wishlist: Visualization of RT dose (3D, w/ Shadie)
- Require: DICOM improvements (CT export, DICOM-RT import/export)
- Require: Compute dose volume histograms
- Recommend: Margin tools
- Wishlist: Visualize dose volume histograms
- Require: Better support for extensions
- Recommend: MRML node for registration
- Recommend: MRML node for patient demographics
- Wishlist: Editor enhancements
- Wishlist: Unevely spaced CT
- Wishlist: Vector field visualization
- Wishlist: DICOM Network I/O
Data
- Goal: 50 cases for inter-subject segmentation
- Goal: 30 cases for intra-subject registration
- Require: New retrospective IRB
- Require: Careful QA of segmentation data
- Require: Validation data for registration studies