Improving Detection of Axillary Lymph Nodes by Computer-Aided Kinetic Feature Identification in Positron Emission Tomography

Abstract

The goal of this project is to improve detection of metastatic axillary breast cancer through sophisticated physiological modeling and statistical signal processing techniques. The major focus of this project was to explore temporal physiological differences in malignant and normal tissues based on the advanced FDG-PET kinetic modeling assessment; assess and improve the accuracy of ROI-based molecular feature extraction techniques from the known primary breast tumor; design the space-temporal filtering and detection criteria to identify the early metastases from severe background interference and count noise; integrate the developed feature extraction and filtering/detection criteria into a software prototype of Intelligent Detection of Early Metastasized Molecular Feature (IDEMMF) system; and test and evaluate the prototype with phantom, animal study and clinical patient study. Our theoretical findings include mathematically map of the physiological differences in temporal domain onto the kinetic (macro) parameter domain; revealing and characterization of the temporal or parametric domain differences in frequency domain and time-frequency. The evaluations on a small scale of animal and patient data show that the IDEMMF system can significantly enhance the metastatic lesion detection by exploring the temporal differences in dynamic FDG-PET images.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2004
Accession Number
ADA434712

Entities

People

  • Xiaoli Yu

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Breast Cancer
  • Cancer
  • Computational Science
  • Detection
  • Detectors
  • Diagnostic Imaging
  • Electrical Engineering
  • Factor Analysis
  • Feature Extraction
  • Frequency Domain
  • Image Processing
  • Medical Personnel
  • Neoplasms
  • Positron Emission Tomography
  • Positron Emissions
  • Signal Processing
  • Tomography

Fields of Study

  • Physics

Readers

  • Neural Network Machine Learning.
  • Oncology and Biomarker-Based Cancer Detection.

Technology Areas

  • AI & ML
  • Space
  • Space - Space Objects