Correlative Feature Analysis for Multimodality Breast CAD

Abstract

The purpose of this research 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. During the second year of the project, we have expanded the multimodality database, which includes full-field digital mammograms, breast ultrasound images and breast MR images. We have further evaluated the performance of the proposed dual-stage segmentation method for the task of assessing the likelihood of malignancy of a mass lesion. We have developed a computerized correlative feature analysis framework to identify the correspondence between lesions imaged in different images, and evaluated its performance on two different mammographic view pairs, i.e. Cranio-Caudal versus Medio-Lateral and Cranio-Caudal versus Medio-Lateral-Oblique. Furthermore, we conducted a pilot study on computerized diagnosis of breast lesions with mammography and DCE-MRI.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2008
Accession Number
ADA508617

Entities

People

  • Yading Yuan

Organizations

  • University of Chicago

Tags

Communities of Interest

  • C4I
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Cancer
  • Computer Vision
  • Databases
  • Health Services
  • Image Registration
  • Image Segmentation
  • Information Science
  • Machine Learning
  • Maximum Likelihood Estimation
  • Medical Personnel
  • Pattern Recognition
  • Pilot Studies
  • Three Dimensional
  • Two Dimensional
  • Ultrasounds
  • United States

Fields of Study

  • Medicine
  • Physics

Readers

  • Computer Vision.
  • Medical Imaging.
  • Oncology and Biomarker-Based Cancer Detection.