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.
Lung metastases detection in CT images using 3D template matching
Rent this article for


Image of FIG. 1.
FIG. 1.

Flowchart of the 3D template-based detection algorithm. Shown in gray blocks are the processes, followed by the resultant outcome at each step.

Image of FIG. 2.
FIG. 2.

Models of the appearance of a uniform-density diameter sphere on consecutive thick image slices. Left side: depiction of 3D sphere model and image cut-planes. Right side: appearance of sphere in consecutive simulated image slices, with in-plane pixel dimensions and including partial volume effects. Middle pair: Instance where the central cut-plane intersects the sphere exactly through the center. Top pair: the cut-planes are offset by ( of the slice thickness) vertically. Bottom pair: the cut-planes are offset by vertically.

Image of FIG. 3.
FIG. 3.

(a) One slice through the simulated tumor image stack. The three arrows point to simulated tumors. (b) The corresponding correlation map computed using a template, at the image slice location in (a). (c) The correlation map at an adjacent slice. The gray-level values at each voxel in the correlation map represent the normalized 3D cross-correlation coefficient between the 3D tumor model of interest and the 3D patient image dataset. The simulated tumor in the upper left of the image (a) is not centered on the current image slice, thus even though the tumor is apparent in the CT image, its correlation match is more apparent on the adjacent slice (c).

Image of FIG. 4.
FIG. 4.

Tumor size capture range for various-sized appearance models, based on simulated tumor datasets. The horizontal axis is the diameter of the simulated spherical tumor. Plotted on the vertical axis is the lowest individual NCCC for any tumor at each diameter. For a given simulated tumor the individual NCCC value is determined by computing the maximum NCCC among the three template varieties. The individual NCCC value varies among the multiple tumors at any given tumor diameter depending on several factors, including the tumor position offset. The highest individual NCCC is found for tumors offset exactly by 0 and slice spacing (identically matching the appearance models, Fig. 2). The lowest individual NCCC occurs for those tumors with the greatest misalignment (offset by slice spacing). The left-most curve represents the lowest individual NCCC for a diameter tumor appearance model against simulated tumors of size in diameter. The remaining curves, going from left to right, are the plots for tumor appearance models of 6, 8, and diameter, respectively. For example, using a correlation threshold of 0.7 would enable the model to detect tumors of size range diameter, but miss other-sized tumors.

Image of FIG. 5.
FIG. 5.

(a) One slice from a patient scan showing two lung tumors identified by a radiologist, indicated by the white arrows. (b) The corresponding correlation map computed using a template, at the image slice location. Though not readily appreciated in this rendering, the centers of the two tumors are the brightest objects in the correlation map.

Image of FIG. 6.
FIG. 6.

Examples of false positive findings. The size of each example is . Shown in the center of each white box is the false positive object. In (a)–(c), false positives occurred at anatomic structures adjacent to pleura and/or cardiac surfaces; in (d), the false positive was a branching region of a blood vessel; and in (e) and (f), false positives occurred in proximity to the diaphragm where respiratory motion artifacts can disrupt the appearance of blood vessels.


Generic image for table

Detection rate and false positive rate for recently published results from the literature ( not available). All results shown are for human data.


Article metrics loading...


Full text loading...

This is a required field
Please enter a valid email address
752b84549af89a08dbdd7fdb8b9568b5 journal.articlezxybnytfddd
Scitation: Lung metastases detection in CT images using 3D template matching