1887
banner image
No data available.
Please log in to see this content.
You have no subscription access to this content.
No metrics data to plot.
The attempt to load metrics for this article has failed.
The attempt to plot a graph for these metrics has failed.
Automated 3-dimensional segmentation of pelvic lymph nodes in magnetic resonance images
Rent:
Rent this article for
USD
10.1118/1.3654162
/content/aapm/journal/medphys/38/11/10.1118/1.3654162
http://aip.metastore.ingenta.com/content/aapm/journal/medphys/38/11/10.1118/1.3654162

Figures

Image of FIG. 1.
FIG. 1.

Example of a CCRG segmentation leaking out of the lymph node at a certain (unpredictable) value of b.

Image of FIG. 2.
FIG. 2.

Segmentation results of three example lymph nodes. For each node, a coronal, sagittal, and axial slice through the seed point are shown. Lymph node A is segmented well by all four automated segmentation methods. Leakage out of lymph nodes B and C is seen in the segmentations by the CCRG and GCS methods, respectively. Note that, while in these 2-D slices, some leaked-into regions seem disjoint, they are connected in the 3-D image.

Image of FIG. 3.
FIG. 3.

ROC curves of all segmentation methods.

Image of FIG. 4.
FIG. 4.

The effect on the diagnostic accuracy of the normal vs metastasis classification using six types of segmentation. Error bars represent 95% confidence intervals.

Tables

Generic image for table
TABLE I.

Summary statistics (minimum, first quartile, median, mean, third quartile, and maximum) for the segmentation performance in terms of DSC and JI.

Loading

Article metrics loading...

/content/aapm/journal/medphys/38/11/10.1118/1.3654162
2011-10-26
2014-04-19
Loading

Full text loading...

This is a required field
Please enter a valid email address
752b84549af89a08dbdd7fdb8b9568b5 journal.articlezxybnytfddd
Scitation: Automated 3-dimensional segmentation of pelvic lymph nodes in magnetic resonance images
http://aip.metastore.ingenta.com/content/aapm/journal/medphys/38/11/10.1118/1.3654162
10.1118/1.3654162
SEARCH_EXPAND_ITEM