Graph Modeling for Identifying Breast Tumor Located in Dense Background of a Mammogram
Identifying breast tumor in a mammogram is a challenging task even for experienced radiologists if the tumor is located in a dense tissue. In this study, a novel superpixel based graph modeling technique is proposed to extract texture features from the computer identified suspicious regions of mammograms. Graph models are constructed from specific structured superpixel patterns and used to generate feature vectors used for classifications of regions of mammograms. Two mammographic datasets were used to evaluate the effectiveness of the proposed approach: the publicly available Digital Database for Screening Mammography (DDSM), and a local database of mammograms (BSSA). Using Linear Discriminant Analysis (LDA) classifier, an AUC score of 0.910 was achieved for DDSM and 0.893 for BSSA. The results indicate that graph models can capture texture features capable of identifying masses located in dense tissues, and help improve computer-aided detection systems.
KeywordsGraph modeling Superpixel tessellation Mass localization Dense background Mammography
The authors would like to thank Dr. Peter Downey, clinical radiologist of BreastScreen SA for validating the core mass contours and valuable comments and discussions.
- 1.Bilgin, C., Demir, C., Nagi, C., et al.: Cell-graph mining for breast tissue modeling and classification. In: 29th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society, EMBS 2007, pp. 5311–5314 (2007)Google Scholar
- 7.Hall, M.A.: Correlation-based feature selection for machine learning (1999)Google Scholar
- 8.Heath, M., Bowyer, K., Kopans, D., et al.: The digital database for screening mammography. In: Proceedings of the Fifth International Workshop on Digital Mammography, pp. 212–218. Medical Physics Publishing (2001)Google Scholar
- 9.Ma, F., Bajger, M., Bottema, M.J.: A graph matching based automatic regional registration method for sequential mammogram analysis. In: Proceedings of SPIE, vol. 6915, p. 6915-11 (2008)Google Scholar
- 13.Oztan, B., Shubert, K.R., Bjornsson, C.S., et al.: Biologically-driven cell-graphs for breast tissue grading. In: 2013 IEEE 10th International Symposium on Biomedical Imaging (ISBI), pp. 137–140. IEEE (2013)Google Scholar
- 14.Sajeev, S., Bajger, M., Lee, G.: Segmentation of breast masses in local dense background using adaptive clip limit-CLAHE. In: 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp. 1–8, November 2015Google Scholar
- 15.Sajeev, S., Bajger, M., Lee, G.: Superpixel pattern graphs for identifying breast mass ROIs in dense background: a preliminary study. In: 14th International Workshop on Breast Imaging (IWBI 2018). Proc. SPIE. vol. 10718 (2018)Google Scholar