The CAD Method for Microcalcification Detection: Independent of Sensor and Resolution

Abstract

The aims of this- work are to explore the feasibility of developing a new class of computer assisted diagnostic (CAD) methods for microcalification cluster (MCC) detection for breast cancer screening using digital mammography. The objectives are to achieve: (a) improved CAD performance that is significantly more robust for large image databases, and (b) an adaptive CAD method that is independent of the digital sensor resolution and gray scale characteristics; for the first time. The proposed method is novel in concept and is based on pioneering experience in development of adaptive CAD algorithms including linear wavelet transforms and non linear transforms for improved feature extraction, their implementation of filter banks that uniquely allow adaptive approaches, and experience in specialized multi-stage neural networks for detection of MCC's with different feature input strategies. The intent is to compare existing wavelet methods to the proposed new method and evaluate them for a common case data base using a state of the art direct digital detector and film (three digitizers)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2001
Accession Number
ADA397029

Entities

People

  • Wei Quian

Organizations

  • University of South Florida

Tags

Communities of Interest

  • Materials and Manufacturing Processes
  • Space

DTIC Thesaurus Topics

  • Algorithms
  • Biomedical Research
  • Breast Cancer
  • Correlation Analysis
  • Databases
  • Detection
  • Detectors
  • Electronic Mail
  • Feature Extraction
  • Health Services
  • Image Processing
  • Information Science
  • Neural Networks
  • Pattern Recognition
  • Recognition
  • Signal Processing
  • Statistical Analysis

Readers

  • Computer Vision.
  • Oncology and Biomarker-Based Cancer Detection.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms