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.
Multilevel learning-based segmentation of ill-defined and spiculated masses in mammograms
Rent:
Rent this article for
USD
10.1118/1.3490477
/content/aapm/journal/medphys/37/11/10.1118/1.3490477
http://aip.metastore.ingenta.com/content/aapm/journal/medphys/37/11/10.1118/1.3490477

Figures

Image of FIG. 1.
FIG. 1.

Flowchart of the proposed MLS technique. Major processes of the method as shown in rounded rectangles include pixel-level soft segmentation, object-level detection, and spiculation detection.

Image of FIG. 2.
FIG. 2.

The distribution of the mass statistics of shape, margin, density, sizes, and subtlety ranking within the database.

Image of FIG. 3.
FIG. 3.

Flowchart of ISLM. For the training process, regional features of training subpatches are used for the pixel-level mass/nonmass classifier learning. For the testing process, the learned classifier is used to generate a mass possibility map for the whole testing image. A high intensity value in the mass probability map represents a high likelihood to be mass tissue. It is seen that very high intensity covers mass body and most of mass boundary with edge.

Image of FIG. 4.
FIG. 4.

Results from the pixel-level classification. (a) The original ROI, (b) the mass probability map produced by the two-phase pixel-level classifiers, (c) the segmentation ground truth generated from multiple radiologists (with majority of five radiologists’ consensus), and (d) the ground truth contour superimposed on the original ROI.

Image of FIG. 5.
FIG. 5.

Example of spiculation detection on a synthetic image. (a) Synthetic linear structures superimposed on a fatty mammographic background, (b) the ridge detector response, (c) the extracted backbone of the spiculation, and (d) the superimposed backbone on the original image.

Image of FIG. 6.
FIG. 6.

Results of multiscale spiculation detection, (a) The original ROI, (b) the multiscale line-strength image, (c) the detected spicules, (d) the detected spicules superimposed on the ROI, and (e) the final spiculation map.

Image of FIG. 7.
FIG. 7.

Example outputs of the multiphase pixel-level classification. (a) The original ROI, (b) the PM generated by the first phase classifier, (c) the PM generated by the two-phase classifiers, and (d) the ground truth provided by the radiologists. Note that the noisy responses on the upper left corner of (b) and (c) come from the pectoral muscles, which have been clearly suppressed by the two-phase classifier with low classification values produced.

Image of FIG. 8.
FIG. 8.

The box and whisker plots of the distribution of the segmentation measurements. (a) Box plots of AOR, (b) box plots of AMINDIST, and (c) box plots of HSDIST. The vertical lines of the boxes correspond to the lower, median, and upper quartile. Each cross represents an outlier. The vertical dashed line in (a) corresponds to the threshold for a good segmentation with , which is adopted in the literature (Ref. 8).

Image of FIG. 9.
FIG. 9.

Segmentation results. From left to right, they are the original ROI, segmentation result of MLFA, LS, MLS, manual segmentation, and the contours superimposed on the original image of the MLS approach (white contour) and radiologists’ manual segmentation (black contour). The BI-RADS descriptors of a mass in margin and shape are also shown under each original image in the first column.

Image of FIG. 10.
FIG. 10.

The WIs with CI at 0.95 for the three segmentation measurements of the algorithm and the radiologists. (a) WI of AOR, (b) WI of AMINDIST, and (c) WI of HSDIST.

Image of FIG. 11.
FIG. 11.

Margin segmentation performance. (a) The box and whisker plots of the distribution of MAOR, (b) WI of MAOR for the algorithm and the radiologists. The vertical dashed line in (a) corresponds to the threshold for a good margin segmentation with , which is determined in this study by considering the difficulty in segmenting the margin portion.

Image of FIG. 12.
FIG. 12.

Illustration of cases with considerable disagreement between the computer segmentation and the ground truth. (a) A segmentation of is obtained on a low contrast mammogram. (b) A segmentation case with falsely included ducts as spiculations. The contours superimposed on the original image are the MLS approach (white contour) and manual segmentation (black contour).

Tables

Generic image for table
TABLE I.

Measurements of segmentation accuracy with the three proposed methods. Note that AMINDIST and HSDIST are distance based measurements. The high distance value means low similarity between computer segmentation and radiologists’ delineation. The reciprocal of the distance value is used as the segmentation similarity measurement for testing the multiobserver agreement in Sec. III C.

Generic image for table
TABLE II.

MAOR for various methods.

Loading

Article metrics loading...

/content/aapm/journal/medphys/37/11/10.1118/1.3490477
2010-10-28
2014-04-21
Loading

Full text loading...

This is a required field
Please enter a valid email address
752b84549af89a08dbdd7fdb8b9568b5 journal.articlezxybnytfddd
Scitation: Multilevel learning-based segmentation of ill-defined and spiculated masses in mammograms
http://aip.metastore.ingenta.com/content/aapm/journal/medphys/37/11/10.1118/1.3490477
10.1118/1.3490477
SEARCH_EXPAND_ITEM