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.
Comparison and assessment of semi-automatic image segmentation in computed tomography scans for image-guided kidney surgery
Rent:
Rent this article for
USD
10.1118/1.3653220
/content/aapm/journal/medphys/38/11/10.1118/1.3653220
http://aip.metastore.ingenta.com/content/aapm/journal/medphys/38/11/10.1118/1.3653220

Figures

Image of FIG. 1.
FIG. 1.

Example images with hand segmentations from two image sets. The left image shows multiple pathologies on an image without contrast agent. Note some pathology may be of roughly equal intensity when compared to kidney parenchyma, while some may be darker. The right image shows an image taken in an early contrast phase (most contrast is still in the kidney cortex). Some parenchyma takes up this contrast more quickly than others, resulting in variable intensity. This tumor does not take up contrast well compared to normal parenchyma.

Image of FIG. 2.
FIG. 2.

Semi-automatic algorithm corrected by parameter change. Left: Threshold level set method overestimates the segmentation due to easily followed vasculature on CT. Right: The same method’s results using lower propagation scaling, automatically implemented upon detection of the preceding failure.

Image of FIG. 3.
FIG. 3.

Atlas slices from both a polar and central region of the kidney. Each atlas slice represents multiple aligned, overlapping hand segmentations. The value of a slice was normalized, yielding a way to estimate how likely a pixel was to represent kidney tissue for a given axial depth.

Image of FIG. 4.
FIG. 4.

Semi-automatic algorithm corrected by method change. Left: Threshold level set method using low propagation scaling cannot contain an oversize segmentation caused by vessel following. Middle: Curvature detection method’s optimal results, showing only slight improvement in avoiding the vessel bleed. Right: Geodesic active contour method results, demonstrating restriction of the vessel overestimation.

Image of FIG. 5.
FIG. 5.

Algorithm Overview. Once a slice is classified as middle or end (axially extreme slices), the order of methods is set. Each method has its own particular parameters to employ based on axial classification, contrast state, whether it has previously failed to segment the current slice, and whether that failure was too large or too small.

Image of FIG. 6.
FIG. 6.

Preoperative CT and intraoperative laser range scans for three cases, (a)–(c). Registered laser range scan shown with autosegmented (left) and hand segmented (right) CT surfaces. Laser surface intensity indicates closest point distances to the CT surface, with the highest distances highlighted in white. Tumor is visible in case (a) at top right, with the white highlight located over the tumor itself. Tumors are visible for case (b) at both top left and bottom right. Case (c) contains a very endophytic tumor.

Image of FIG. 7.
FIG. 7.

Visualization of distance grouping categories used in evaluation of the transformation variability introduced by using semi-automatic segmentation versus hand segmentation. Points were classified into five categories by increasing distance from target tumor centroid.

Tables

Generic image for table
TABLE I.

Training kidney results. Averages are shown for each contrast phase as well as for all kidneys together.

Generic image for table
TABLE II.

Testing kidney results. Averages are shown for each contrast phase as well as for all kidneys together.

Generic image for table
TABLE III.

Closest point differences between registered laser range scan data and segmented CT surfaces (all distances in mm).

Generic image for table
TABLE IV.

Average distances between resultant physical space points when both hand and semi-automatic segmentation inverse transformations are applied to image space coordinates, divided by category. Each category represents a distance grouping from the tumor’s centroid, with category (1) being the closest.

Loading

Article metrics loading...

/content/aapm/journal/medphys/38/11/10.1118/1.3653220
2011-10-28
2014-04-16
Loading

Full text loading...

This is a required field
Please enter a valid email address
752b84549af89a08dbdd7fdb8b9568b5 journal.articlezxybnytfddd
Scitation: Comparison and assessment of semi-automatic image segmentation in computed tomography scans for image-guided kidney surgery
http://aip.metastore.ingenta.com/content/aapm/journal/medphys/38/11/10.1118/1.3653220
10.1118/1.3653220
SEARCH_EXPAND_ITEM