Infrared Spectroscopic Imaging for Prostate Pathology Practice

Abstract

The report summarizes progress towards using Fourier transform infrared spectroscopic imaging for prostate pathology in year 2 of a 3 year award from the PCRP. The aim of the work is to enable histopathologic recognition without the use of human input or stains. The major accomplishments in the past year are: 1) A genetic algorithm based method to distinguish benign from malignant epithelium using infrared spectroscopic imaging data was shown to be effective. Large scale validation is underway. 2) A combination of IR and conventional pathology imaging has been developed. This is a critical step to potential clinical translation, and 3) A combination of IR imaging and conventional pathology shows promising results that can be explained in the context of existing practice. Larger validation studies are needed.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2009
Accession Number
ADA503971

Entities

People

  • Rohit Bhargava

Organizations

  • University of Illinois Urbana–Champaign

Tags

Communities of Interest

  • Autonomy
  • Engineered Resilient Systems
  • Ground and Sea Platforms
  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Biomedical Research
  • Computational Science
  • Data Mining
  • Databases
  • Detectors
  • Dimensionality Reduction
  • Genetic Algorithms
  • Information Processing
  • Information Science
  • Machine Learning
  • Measurement
  • Medical Personnel
  • Scattering
  • Spectroscopy
  • Supervised Machine Learning
  • Three Dimensional

Fields of Study

  • Medicine

Readers

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

Technology Areas

  • AI & ML
  • Biotechnology
  • Biotechnology - Cancer Biotech