Correlative Feature Analysis for Multimodality Breast CAD

Abstract

The purpose of this study is to develop correlative feature analysis methods for integrating image information from multi-modality breast images taking advantage of the information from different views and/or different modalities and thus improving the sensitivity and specificity of breast cancer diagnosis. Identifying the corresponding image pair of a lesion is an essential step for this purpose. During the first year we have collected and maintained a multi-modality breast image database which includes full field digital mammography (FFDM) sonography and MRI images. To differentiate corresponding FFDM image pairs from non-corresponding ones in which images were obtained from CC and ML view respectively we have developed computerized methods for lesion segmentation feature extraction and selection feature correlation analysis and image pair classification. The results have shown that our computerized feature correlative analysis has great potential in identifying the corresponding image pair of a lesion obtained from different views of the same modality.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2007
Accession Number
ADA475156

Entities

People

  • Yading Yuan

Organizations

  • University of Chicago

Tags

Communities of Interest

  • C4I

DTIC Thesaurus Topics

  • Algorithms
  • Breast Cancer
  • Computer Vision
  • Correlation Analysis
  • Data Science
  • Databases
  • Diagnostic Imaging
  • Feature Extraction
  • Fuzzy Sets
  • Health Services
  • Image Segmentation
  • Information Science
  • Machine Learning
  • Neoplasms
  • Three Dimensional
  • Two Dimensional
  • Ultrasounds

Fields of Study

  • Medicine
  • Physics

Readers

  • Medical Imaging.
  • Neural Network Machine Learning.
  • Psychometric Testing or Psychological Assessment.

Technology Areas

  • AI & ML