Robust Detection of Masses in Digitized Mammograms

Abstract

This project is to develop a robust computer aided diagnosis (CAD) system for mass detection with high sensitivity and specificity in digitized mammograms. The research scope in past year is on the study of preprocessing and adaptive strategy of CAD modules. Several major progresses have been made including (a) an image standardization algorithm was developed by applying a series of preprocessing to remove extrinsic signal, extract breast area, and normalize the image intensity; (b) multi-mode processing methods were developed by decomposing image features using directional wavelet transform and non-linear multi-scale representation using anisotropic diffusion; (3) adaptive processing in image segmentation using localized adaptive thresholding and adaptive clustering. It is expected that these processing will be very helpful in improving the robustness of the detection system.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2001
Accession Number
ADA392562

Entities

People

  • Lihua Li

Organizations

  • University of South Florida

Tags

Communities of Interest

  • C4I

DTIC Thesaurus Topics

  • Algorithms
  • Biomedical Research
  • Breast Cancer
  • Clustering
  • Computer Vision
  • Detection
  • Diffusion
  • Directional
  • Image Processing
  • Image Segmentation
  • Intensity
  • Machine Learning
  • Preprocessing
  • Shape
  • Standardization
  • Three Dimensional
  • Wavelet Transforms

Fields of Study

  • Physics

Readers

  • Computer Vision.
  • Image Processing and Computer Vision.
  • Oncology and Biomarker-Based Cancer Detection.