Segmentation of suspicious densities in digital mammograms
- PMID: 11243351
- DOI: 10.1118/1.1339884
Segmentation of suspicious densities in digital mammograms
Abstract
State-of-the-art algorithms for detection of masses in mammograms are very sensitive but they also detect many normal regions with slightly suspicious features. Based on segmentations of detected regions, shape and intensity features can be computed that discriminate between normal and abnormal regions. These features can be used to discard false positive detections and hence improve the specificity of the detection method. In this work two different methods to segment suspect regions were examined. A number of different implementations of a region growing method were compared to a discrete dynamic contour method. Both methods were applied to a consecutive data set of 132 mammograms containing masses and architectural distortions, taken from the Dutch screening program. Evaluation of the performance of the methods was done in two different ways. In the first experiment, the segmentations of masses were compared to annotations made by the radiologist. In the second experiment, a number of features were computed for all segmented areas, normal and abnormal, based on which regions were classified with a neural network. The most sophisticated region growing method and the method using the dynamic contour model had a similar performance when evaluation was based on the overlap of the annotations. The second experiment showed that the contours generated by the discrete dynamic contour model were more suited for computation of discriminating features. Contrast features were especially useful to improve the performance of the detection method.
Similar articles
-
A method to test the reproducibility and to improve performance of computer-aided detection schemes for digitized mammograms.Med Phys. 2004 Nov;31(11):2964-72. doi: 10.1118/1.1806291. Med Phys. 2004. PMID: 15587648
-
[Reading screening mammograms with the help of neural networks].Ned Tijdschr Geneeskd. 1999 Nov 6;143(45):2232-6. Ned Tijdschr Geneeskd. 1999. PMID: 10578420 Review. Dutch.
-
Combined adaptive enhancement and region-growing segmentation of breast masses on digitized mammograms.Med Phys. 1999 Aug;26(8):1642-54. doi: 10.1118/1.598658. Med Phys. 1999. PMID: 10501064
-
Computer-aided diagnosis: automatic detection of malignant masses in digitized mammograms.Med Phys. 1998 Jun;25(6):957-64. doi: 10.1118/1.598274. Med Phys. 1998. PMID: 9650186
-
False-positive reduction technique for detection of masses on digital mammograms: global and local multiresolution texture analysis.Med Phys. 1997 Jun;24(6):903-14. doi: 10.1118/1.598011. Med Phys. 1997. PMID: 9198026
Cited by
-
Level set segmentation of breast masses in contrast-enhanced dedicated breast CT and evaluation of stopping criteria.J Digit Imaging. 2014 Apr;27(2):237-47. doi: 10.1007/s10278-013-9652-1. J Digit Imaging. 2014. PMID: 24162667 Free PMC article.
-
Automated noninvasive classification of renal cancer on multiphase CT.Med Phys. 2011 Oct;38(10):5738-46. doi: 10.1118/1.3633898. Med Phys. 2011. PMID: 21992388 Free PMC article.
-
Image analysis in medical imaging: recent advances in selected examples.Biomed Imaging Interv J. 2010 Jul-Sep;6(3):e32. doi: 10.2349/biij.6.3.e32. Epub 2010 Jul 1. Biomed Imaging Interv J. 2010. PMID: 21611048 Free PMC article.
-
Multilevel learning-based segmentation of ill-defined and spiculated masses in mammograms.Med Phys. 2010 Nov;37(11):5993-6002. doi: 10.1118/1.3490477. Med Phys. 2010. PMID: 21158311 Free PMC article.
-
Radial-searching contour extraction method based on a modified active contour model for mammographic masses.Radiol Phys Technol. 2008 Jul;1(2):151-61. doi: 10.1007/s12194-008-0022-5. Epub 2008 May 8. Radiol Phys Technol. 2008. PMID: 20821141
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Medical