2011 Summer Project Week NerveSeg - Revision history

Adalca at 14:01, 24 June 2011

2011-06-24T14:01:02Z

Adalca at 14:00, 24 June 2011

2011-06-24T14:00:28Z

Adalca at 03:28, 24 June 2011

2011-06-24T03:28:15Z

Adalca at 03:28, 24 June 2011

2011-06-24T03:28:00Z

Adalca: /* Key Investigators */

2011-06-24T03:27:07Z

Key Investigators

Adalca: /* Key Investigators */

2011-06-24T03:26:39Z

Key Investigators

Adalca: /* Key Investigators */

2011-06-24T03:26:01Z

Key Investigators

Adalca at 03:24, 24 June 2011

2011-06-24T03:24:09Z

Adalca: /* Key Investigators */

2011-06-24T03:23:52Z

Key Investigators

Adalca: /* Key Investigators */

2011-06-23T21:32:55Z

Key Investigators

@@ Line 57: / Line 57: @@
 <div style="width: 97%; float: left;">
 A.V. Dalca; Giovanna Danagoulian; Ron kikinis; Ehud Schmidt; Polina Golland. (2011) Segmentation of Nerve Bundles and Ganglia in Spine MRI using Particle Filters. To Appear in MICCAI 2011
 </div>

@@ Line 57: / Line 57: @@
 <div style="width: 97%; float: left;">
+A.V. Dalca; Giovanna Danagoulian; Ron kikinis; Ehud Schmidt; Polina Golland. (2011) Segmentation of Nerve Bundles and Ganglia in Spine MRI using Particle Filters. To Appear in MICCAI 2011
 </div>

← Older revision		Revision as of 03:28, 24 June 2011
Line 1:		Line 1:
−	<h1>Segmentation of Nerve Bundles and Ganglia in Spine MRI ~~using Particle Filters.~~ </h1>	+	<h1>Segmentation of Nerve Bundles and Ganglia in Spine MRI</h1>

	__NOTOC__		__NOTOC__

← Older revision		Revision as of 03:28, 24 June 2011
Line 1:		Line 1:
−	Nerve ~~Segmentation~~	+	<h1>Segmentation of Nerve Bundles and Ganglia in Spine MRI using Particle Filters. </h1>
−

	__NOTOC__		__NOTOC__

@@ Line 48: / Line 48: @@
 <gallery>
-Image:NerveSeg-peripheral.png|Figure 7 - Example_3: Another example, following several nerve bundles.
+Image:NerveSeg-peripheral.png|Figure 7 - Example_4: Another example, following several nerve bundles.
 Image:NerveSeg-mapp.png|Figure 8 - Example_4: A map of several automatically segmented nerves with herniated disc manually segmented.
 </gallery>

← Older revision		Revision as of 03:26, 24 June 2011
Line 32:		Line 32:

	<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>

@@ Line 42: / Line 42: @@
 <h3>Progress</h3>
-* Sudden changes in the segmentation can be ameliorated. In general, can now constrain the radius function to be smoother, to avoiding sudden changes in the segmentation.
+* Sudden changes in the segmentation can be ameliorated. In general, can now constrain the radius function to be smoother in the general (visual) sense not just in the technical mathematical sense, to avoiding sudden changes in the segmentation (which are simply areas with fast but smooth radius function change).
-* With careful characterization of the newer radius function, we can segment some of the thinner peripheral nerves.
+* With careful characterization of the newer radius function, we can segment some of the thinner peripheral nerves. This is still specific to the images explored, but it can be done.
 * Full width estimation is hard as part of the current system, may have to be a separate extension.
-Results are attached.
+Results are attached:
 <gallery>
 Image:NerveSeg-peripheral.png|Figure 7 - Example_3: Another example, following several nerve bundles.
 Image:NerveSeg-mapp.png|Figure 8 - Example_4: A map of several automatically segmented nerves with herniated disc manually segmented.

@@ Line 16: / Line 16: @@
 Image:NerveSeg-res-scr3.png|Figure 5 - Example_2: Another View.
 Image:NerveSeg-mapo.png|Figure 6 - Example_3: Map of automatically segmented nerves. Circled in red are areas of sudden changes.
 </gallery>
@@ Line 55: / Line 48: @@
 Results are attached.

@@ Line 43: / Line 43: @@
 <h3>Approach, Plan</h3>
-Currently we use a particle-filter tracking approach for segmenting the nerves. The algorithm is given a seed point, preferably somewhere in the spine. The particles are tubes following Bézier curves (and hence forming a B-spline track). The dynamics model encourages continuity and smoothness. The image likelihood model compares gradient fields and intensities of predicted patches with image observations to evaluate a posterior distribution of the particles' importance. While we can currently usually track the nerve cores, usually fully throughout the vertebral canal, the algorithm does not delineate the full extent of the nerves, and behaves poorly on peripheral nerves outside of the vertebral canal. We will modify the likelihood function and parameters and concentrate on achieving this during the project week.
+Currently we use a particle-filter tracking approach for segmenting the nerves. The algorithm is given a seed point, preferably somewhere in the spine. The particles are tubes following Bézier curves (and hence forming a B-spline track). The dynamics model encourages continuity and smoothness. The image likelihood model compares gradient fields and intensities of predicted patches with image observations to evaluate a posterior distribution of the particles' importance. While we can currently usually track the nerve cores, usually fully throughout the vertebral canal, the algorithm does not delineate the full extent of the nerves and has sudden changes, and behaves poorly on peripheral nerves outside of the vertebral canal. We will modify the likelihood function and parameters and concentrate on achieving this during the project week.
 </div>
@@ Line 49: / Line 49: @@
 <h3>Progress</h3>