2014 Summer Project Week:Stroke-SuperResolution - Revision history

Adalca at 14:40, 27 June 2014

2014-06-27T14:40:27Z

2014-06-27T14:39:22Z

2014-06-27T14:34:47Z

Project Description

2014-06-26T21:56:26Z

2014-06-23T18:52:52Z

Project Description

2014-06-23T16:04:31Z

Project Description

2014-06-23T16:02:14Z

2014-06-23T14:59:16Z

2014-06-23T14:40:06Z

2014-06-23T05:01:01Z

@@ Line 5: / Line 5: @@
 Image:STROKE_SR1.png|Super-Resolution initial results -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image. The bottom images are state of the art interpolations. The top right is our current result.
 Image:STROKE_SR2.png|Super-Resolution results on Thursday evening -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image (top-center). The bottom row are all our results, with slight variations.
-Image:STROKE_SR3.png|Bottom results: NLM, Us (before), US  (now)
+Image:STROKE_SR3.png| Top: Original, downsampled(input); Bottom results: NLM, us (before), us  (now)
 </gallery>

@@ Line 5: / Line 5: @@
 Image:STROKE_SR1.png|Super-Resolution initial results -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image. The bottom images are state of the art interpolations. The top right is our current result.
 Image:STROKE_SR2.png|Super-Resolution results on Thursday evening -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image (top-center). The bottom row are all our results, with slight variations.
 </gallery>

@@ Line 25: / Line 25: @@
 <div style="width: 27%; float: left; padding-right: 3%;">
 <h3>Progress</h3>
-* Several improvements as well as an implementation of scale-space has been done, which has helped significantly on simulated data. See result image.
+* Several improvements (i.e. bug fixes :) ) as well as an implementation of scale-space has been done
 * Trying to apply algorithm to new datasets: [http://slicer.kitware.com/midas3/folder/2182 Sample prostate MRI dataset to evaluate applicability] (see 3-SAG, 4-COR and 5-AX series of the same subject/prostate in sagittal coronal and axial planes)
 </div>
 </div>

@@ Line 4: / Line 4: @@
 Image:WMH_T1.png|Clinical Stroke Image
 Image:STROKE_SR1.png|Super-Resolution initial results -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image. The bottom images are state of the art interpolations. The top right is our current result.
 </gallery>
@@ Line 24: / Line 25: @@
 <div style="width: 27%; float: left; padding-right: 3%;">
 <h3>Progress</h3>
-* [http://slicer.kitware.com/midas3/folder/2182 Sample prostate MRI dataset to evaluate applicability] (see 3-SAG, 4-COR and 5-AX series of the same subject/prostate in sagittal coronal and axial planes)
+* Several improvements as well as an implementation of scale-space has been done, which has helped significantly on simulated data. See result image.
 </div>
 </div>

@@ Line 24: / Line 24: @@
 <div style="width: 27%; float: left; padding-right: 3%;">
 <h3>Progress</h3>
+* [http://slicer.kitware.com/midas3/folder/2182 Sample prostate MRI dataset to evaluate applicability] (see 3-SAG, 4-COR and 5-AX series of the same subject/prostate in sagittal coronal and axial planes)
 </div>
 </div>

@@ Line 11: / Line 11: @@
 ==Project Description==
 <div style="margin: 20px;">
-To improve results for Large Datasets of clinical-quality data, we are investigating super-resolution methods. Here, we are using a patch-based approach with MRF priors and utilizing only the current dataset, without an external training dataset.
+Due to the low quality of clinical images (often with many artifacts, 7mm thick slices, etc), most standard algorithms, such as those for registration, segmentation, analysis, will fail. To improve results for large datasets of clinical-quality data, we are investigating super-resolution methods. Here, we are using a patch-based approach with MRF priors and utilizing only the current dataset, without an external training dataset.

@@ Line 2: / Line 2: @@
 <gallery>
 Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
 Image:STROKE_SR1.png|Super-Resolution initial results -- top-left is a 'real' image, from which we simulate a 1x1x7mm clinical image. The bottom images are state of the art interpolations. The top right is our current result.
 </gallery>

@@ Line 19: / Line 19: @@
 <div style="width: 27%; float: left; padding-right: 3%;">
 <h3>Approach, Plan</h3>
-* We are developing a [https://github.com/adalca/patchlib| patch library in MATLAB] and applying it to a large stroke dataset
+* We are developing a [https://github.com/adalca/patchlib patch library in MATLAB], and need to apply it in a scale-space framework to the T2-FLAIR dataset.
 </div>
 <div style="width: 27%; float: left; padding-right: 3%;">

@@ Line 7: / Line 7: @@
 ==Key Investigators==
 - Adrian Dalca, Ramesh Sridharan, Polina Golland, MIT
 ==Project Description==