Difference between revisions of "2014 Summer Project Week:AutomatedSegmentationQA"
From NAMIC Wiki
| (3 intermediate revisions by the same user not shown) | |||
| Line 2: | Line 2: | ||
<gallery> | <gallery> | ||
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]] | Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]] | ||
| + | Image:roboRater.png|[http://brainsia.github.io/roboRater/ Github site] | ||
</gallery> | </gallery> | ||
==Key Investigators== | ==Key Investigators== | ||
| − | * IOWA: Dave Welch, Hans Johnson | + | * IOWA: Dave Welch, Eun Young (Regina) Kim, Hans Johnson |
==Project Description== | ==Project Description== | ||
| Line 17: | Line 18: | ||
<div style="width: 27%; float: left; padding-right: 3%;"> | <div style="width: 27%; float: left; padding-right: 3%;"> | ||
<h3>Approach, Plan</h3> | <h3>Approach, Plan</h3> | ||
| − | * | + | * Identify the DICE threshold for automatic QA entry |
| + | * Interface with our PostgreSQL database for QA access and recording | ||
| + | * Validate automated responses on 20 test cases | ||
</div> | </div> | ||
<div style="width: 27%; float: left; padding-right: 3%;"> | <div style="width: 27%; float: left; padding-right: 3%;"> | ||
<h3>Progress</h3> | <h3>Progress</h3> | ||
| − | * | + | * Complete |
| + | * Source code on [http://brainsia.github.io/roboRater Github] | ||
</div> | </div> | ||
</div> | </div> | ||
Latest revision as of 13:18, 27 June 2014
Home < 2014 Summer Project Week:AutomatedSegmentationQA
Key Investigators
- IOWA: Dave Welch, Eun Young (Regina) Kim, Hans Johnson
Project Description
Objective
- Create a database-driven script to compare results of segmentation workflow experiments validating results on a per-region basis
- Comparisons will use DICE
- Script will register patient scans from a baseline experiment to the 'new' experiment
Approach, Plan
- Identify the DICE threshold for automatic QA entry
- Interface with our PostgreSQL database for QA access and recording
- Validate automated responses on 20 test cases
Progress
- Complete
- Source code on Github
