Computer-aided classification of mammographic masses using visually sensitive image features - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017;25(1):171-186.
doi: 10.3233/XST-16212.

Computer-aided classification of mammographic masses using visually sensitive image features

Yunzhi Wang  1 , Faranak Aghaei  1 , Ali Zarafshani  1 , Yuchen Qiu  1 , Wei Qian  2   3 , Bin Zheng  1
Affiliations

Computer-aided classification of mammographic masses using visually sensitive image features

Yunzhi Wang et al. J Xray Sci Technol. 2017.

Abstract

Purpose: To develop a new computer-aided diagnosis (CAD) scheme that computes visually sensitive image features routinely used by radiologists to develop a machine learning classifier and distinguish between the malignant and benign breast masses detected from digital mammograms.

Methods: An image dataset including 301 breast masses was retrospectively selected. From each segmented mass region, we computed image features that mimic five categories of visually sensitive features routinely used by radiologists in reading mammograms. We then selected five optimal features in the five feature categories and applied logistic regression models for classification. A new CAD interface was also designed to show lesion segmentation, computed feature values and classification score.

Results: Areas under ROC curves (AUC) were 0.786±0.026 and 0.758±0.027 when to classify mass regions depicting on two view images, respectively. By fusing classification scores computed from two regions, AUC increased to 0.806±0.025.

Conclusion: This study demonstrated a new approach to develop CAD scheme based on 5 visually sensitive image features. Combining with a "visual aid" interface, CAD results may be much more easily explainable to the observers and increase their confidence to consider CAD generated classification results than using other conventional CAD approaches, which involve many complicated and visually insensitive texture features.

Keywords: Computer-aided diagnosis (CAD); classification of mammographic masses; quantification of visually sensitive image features; quantitative image feature selection in CAD.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Flowchart of the proposed CAD scheme.
Figure 2
Figure 2
An example of a suspicious mass (a) and computed mass outside surrounding area (b), where the gray area is the outside surrounding area and the white area is the segmented mass area.
Figure 3
Figure 3
Example of radial angle histogram of two mammographic masses where (a) shows a less-spiculated mass with its radial angle histogram (b); while (c) shows a spiculated mass with its radial angle histogram (d).
Figure 4
Figure 4. Spearsman's correlation coefficients matrix of all 14 extracted features using the segmented masses from CC view mammograms
Figure 5
Figure 5. Illustration of CAD interface with two mass segmentation examples, the quantitative characteristic feature rating and a classification score for one benign mass (a) and one malignant mass region (b)
Figure 6
Figure 6
Two ROC curves of two classifiers trained and tested using the mass regions segmented from CC and MLO view images. The AUC values are 0.786±0.026 and 0.758±0.027, respectively.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Schell MJ, Yankaskas BC, Ballard-Barbash R, et al. Evidence-based target recall rates for screening mammography. Radiology. 2007;243:681–689. - PubMed
    1. Brodersen J, Siersma VD. Long-term psychosocial consequences of false-positive screening mammography. Ann Fam Med. 2013;11:106–15. - PMC - PubMed
    1. Gur D, Abrams GS, Chough DM, et al. Digital breast tomosynthesis: observer performance study. Am J Roentgenol. 2009;193:586–591. - PubMed
    1. Malliori A, Bliznakova K, Bliznakov Z, et al. Breast tomosynthesis using the multiple projection algorithm adapted for stationary detectors. J Xray Sci Technol. 2016;24:23–41. - PubMed
    1. Kulkarni M, Dendere R, Nicolls F, Douglas TS. Monto-Carlo simulation of slot-scanning digital mammography system for tomosynthesis. J Xray Sci Technol. 2016;24:191–206. - PubMed

Publication types

MeSH terms