Improving Clinical Diagnosis Through Change Detection in Mammography

Abstract

Temporal change of mass lesions overtime is a key piece of information in computer-aided diagnosis of breast cancer and treatment monitoring. For a specific patient, change detection depends on the ability to align the images of the mammogram sequence to a common axis, and the ability to build up memory about the image scene overtime. The process of aligning images to a common axis is termed image registration. The image scene representation is called site model. In the second year of this project, we developed a novel registration technique to align temporal sequences of the same patient, to construct a scene memory or site model, with the ultimate goal of performing change detection. We developed (1) a new hybrid registration algorithm aimed at the registration of non-rigid objects with minimal a prior knowledge; (2) a new change quantification metric based on the joint relative entropy between two images; (3) a patient specific site model concept to image-guided lesion monitoring; (4) a methodology to combine multiple transforms together to determine a composite image transform; and (5) an improved statistical segmentation algorithm for sequences of images.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2000
Accession Number
ADA386825

Entities

People

  • Yue-joseph Wang

Organizations

  • The Catholic University of America

Tags

Communities of Interest

  • Ground and Sea Platforms
  • Space

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Body Weight
  • Change Detection
  • Computational Science
  • Computer Science
  • Computer Vision
  • Coordinate Systems
  • Detection
  • Electrical Engineering
  • Image Processing
  • Image Registration
  • Image Segmentation
  • Information Processing
  • Information Science
  • Medical Personnel
  • Signal Processing

Readers

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