Use of border information in the classification of mammographic masses
- PMID: 16394348
- DOI: 10.1088/0031-9155/51/2/016
Use of border information in the classification of mammographic masses
Abstract
We are developing a new method to characterize the margin of a mammographic mass lesion to improve the classification of benign and malignant masses. Towards this goal, we designed features that measure the degree of sharpness and microlobulation of mass margins. We calculated these features in a border region of the mass defined as a thin band along the mass contour. The importance of these features in the classification of benign and malignant masses was studied in relation to existing features used for mammographic mass detection. Features were divided into three groups, each representing a different mass segment: the interior region of a mass, the border and the outer area. The interior and the outer area of a mass were characterized using contrast and spiculation measures. Classification was done in two steps. First, features representing each of the three mass segments were merged into a neural network classifier resulting in a single regional classification score for each segment. Secondly, a classifier combined the three single scores into a final output to discriminate between benign and malignant lesions. We compared the classification performance of each regional classifier and the combined classifier on a data set of 1076 biopsy proved masses (590 malignant and 486 benign) from 481 women included in the Digital Database for Screening Mammography. Receiver operating characteristic (ROC) analysis was used to evaluate the accuracy of the classifiers. The area under the ROC curve (A(z)) was 0.69 for the interior mass segment, 0.76 for the border segment and 0.75 for the outer mass segment. The performance of the combined classifier was 0.81 for image-based and 0.83 for case-based evaluation. These results show that the combination of information from different mass segments is an effective approach for computer-aided characterization of mammographic masses. An advantage of this approach is that it allows the assessment of the contribution of regions rather than individual features. Results suggest that the border and the outer areas contained the most valuable information for discrimination between benign and malignant masses.
Similar articles
-
Can computer-aided detection be detrimental to mammographic interpretation?Radiology. 2009 Oct;253(1):17-22. doi: 10.1148/radiol.2531090689. Radiology. 2009. PMID: 19789251 Review. No abstract available.
-
Improvement of mammographic mass characterization using spiculation meausures and morphological features.Med Phys. 2001 Jul;28(7):1455-65. doi: 10.1118/1.1381548. Med Phys. 2001. PMID: 11488579
-
Classification of malignant and benign masses based on hybrid ART2LDA approach.IEEE Trans Med Imaging. 1999 Dec;18(12):1178-87. doi: 10.1109/42.819327. IEEE Trans Med Imaging. 1999. PMID: 10695530
-
Computerized characterization of masses on mammograms: the rubber band straightening transform and texture analysis.Med Phys. 1998 Apr;25(4):516-26. doi: 10.1118/1.598228. Med Phys. 1998. PMID: 9571620
-
[Computer-assisted diagnosis in screening mammography].Radiologe. 1996 Jan;36(1):72-80. doi: 10.1007/s001170050042. Radiologe. 1996. PMID: 8820375 Review. German.
Cited by
-
Applying artificial intelligence technology to assist with breast cancer diagnosis and prognosis prediction.Front Oncol. 2022 Aug 31;12:980793. doi: 10.3389/fonc.2022.980793. eCollection 2022. Front Oncol. 2022. PMID: 36119479 Free PMC article. Review.
-
Mass Detection and Segmentation in Digital Breast Tomosynthesis Using 3D-Mask Region-Based Convolutional Neural Network: A Comparative Analysis.Front Mol Biosci. 2020 Nov 11;7:599333. doi: 10.3389/fmolb.2020.599333. eCollection 2020. Front Mol Biosci. 2020. PMID: 33263004 Free PMC article.
-
Digital Mammography in Breast Cancer: Additive Value of Radiomics of Breast Parenchyma.Radiology. 2019 Apr;291(1):15-20. doi: 10.1148/radiol.2019181113. Epub 2019 Feb 12. Radiology. 2019. PMID: 30747591 Free PMC article.
-
Computer-aided classification of mammographic masses using visually sensitive image features.J Xray Sci Technol. 2017;25(1):171-186. doi: 10.3233/XST-16212. J Xray Sci Technol. 2017. PMID: 27911353 Free PMC article.
-
Is the false-positive rate in mammography in North America too high?Br J Radiol. 2016 Sep;89(1065):20160045. doi: 10.1259/bjr.20160045. Epub 2016 Jun 8. Br J Radiol. 2016. PMID: 27187600 Free PMC article. Review.
MeSH terms
LinkOut - more resources
Full Text Sources
Medical