Superpixel pattern graphs for identifying breast mass ROIs in dense background: A preliminary study

Shelda Sajeev, Mariusz Bajger, Gobert Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Finding mamographic masses located in a dense breast tissue is a challenge even for an experienced radiologist. The difficulty comes from the similarity of intensity between the masses and the overlapped normal dense tissues. In this study, a novel method for classification of masses localized in dense background of breast is proposed. The method can identify meaningful superpixel patterns present in mammograms within mass-like regions. The topology of superpixel patterns, captured by using spatial connectivity graphs, revealed significant differences between cancerous and healthy areas of breasts. Four clinically recognizable features were extracted from the superpixel graphs and used for classification. The proposed approach was evaluated using ninety three dense ROIs selected from the publicly available Digital Database for Screening Mammography (DDSM). All 93 ROIs were localized in dense backgrounds of breasts. Among them, 41 contained malignant masses in dense backgrounds and 52 contained healthy dense breast tissues. The results indicate that the graph features generated from superpixel pattern graphs can produce very effective and efficient feature descriptors of breast masses localized in dense background. Using Fisher Linear Discriminant Analysis (LDA) classifier AUC score of 0.90 was achieved for the four dimensional feature vector.

Original languageEnglish
Title of host publication14th International Workshop on Breast Imaging (IWBI 2018)
EditorsElizabeth A. Krupinski
PublisherSPIE
ISBN (Electronic)9781510620070
DOIs
Publication statusPublished - 1 Jan 2018
Externally publishedYes
Event14th International Workshop on Breast Imaging (IWBI 2018) - Atlanta, United States
Duration: 8 Jul 201811 Jul 2018

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume10718
ISSN (Print)1605-7422

Conference

Conference14th International Workshop on Breast Imaging (IWBI 2018)
CountryUnited States
CityAtlanta
Period8/07/1811/07/18

    Fingerprint

Keywords

  • dense ROIs
  • graph features
  • Mammograms
  • superpixels

Cite this

Sajeev, S., Bajger, M., & Lee, G. (2018). Superpixel pattern graphs for identifying breast mass ROIs in dense background: A preliminary study. In E. A. Krupinski (Ed.), 14th International Workshop on Breast Imaging (IWBI 2018) [107180V] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10718). SPIE. https://doi.org/10.1117/12.2317589