Developing a visual sensitive image features based CAD scheme to assist classification of mammographic masses

Yunzhi Wang, Faranak Aghaei, Maxine Tan, Yuchen Qiu, Hong Liu, Bin Zheng

Research output: Chapter in Book/Report/Conference proceedingConference PaperOtherpeer-review


Computer-aided diagnosis (CAD) schemes of mammograms have been previously developed and tested. However, due to using "black-box" approaches with a large number of complicated features, radiologists have lower confidence to accept or consider CAD-cued results. In order to help solve this issue, this study aims to develop and evaluate a new CAD scheme that uses visual sensitive image features to classify between malignant and benign mammographic masses. A dataset of 301 masses detected on both craniocaudal (CC) and mediolateraloblique (MLO) view images was retrospectively assembled. Among them, 152 were malignant and 149 were benign. An iterative region-growing algorithm was applied to the special Gaussian-kernel filtered images to segment mass regions. Total 13 Image features were computed to mimic 5 categories of visually sensitive features that are commonly used by radiologists in classifying suspicious mammographic masses namely, mass size, shape factor, contrast, homogeneity and spiculation. We then selected one optimal feature in each of 5 feature categories by using a student t-test, and applied two logistic regression classifiers using either CC or MLO view images to distinguish between malignant and benign masses. Last, a fusion method of combining two classification scores was applied and tested. By applying a 10-fold cross-validation method, the area under receiver operating characteristic curves was 0.806±0.025. 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 are much more easily explainable to the observers and may increase their confidence to consider CAD-cued results.

Original languageEnglish
Title of host publicationPROCEEDINGS OF SPIE
Subtitle of host publicationMedical Imaging 2017, Image Perception, Observer Performance, and Technology Assessment
EditorsMatthew A. Kupinski, Robert M. Nishikawa
Place of PublicationBellingham WA USA
Number of pages4
ISBN (Electronic)9781510607187
ISBN (Print)9781510607170
Publication statusPublished - 2017
Externally publishedYes
EventConference on Medical Imaging - Image Perception, Observer Performance, and Technology Assessment 2017 - Orlando, United States of America
Duration: 12 Feb 201713 Feb 2017 (Proceedings)

Publication series

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


ConferenceConference on Medical Imaging - Image Perception, Observer Performance, and Technology Assessment 2017
Country/TerritoryUnited States of America
Internet address


  • Assessment of cad performance
  • Classification of mammographic masses
  • Computing visual sensitive features
  • Feature selection
  • Logistic regression based classification
  • Visual-aid interface of cad

Cite this