Combining Clinical, Sonographic and Elastigraphic Features to Improve the Detection of Prostate Cancer
Abstract
The ultimate goal of this project is to combine features derived from ultrasound (US) images, US radio-frequency (RF) data, tissue elasticity imaging, and clinical data such as PSA into a computerized system for displaying prostate images that indicate probable location(s) of cancer. This project proposed to begin by gathering RF data from in-vitro prostatectomy specimens in cross sectional planes 2mm apart. These data are used to calculate RF features such as scatterer size, and backscatter coefficient at each location in the gland. The data are also used to generate images and elastograms from which image texture features and tissue hardness features are computed. The features are then correlated with histology taken at the same tissue planes to determine which features and feature combinations most accurately predict the presence of cancer. Despite continuing delays in hiring personnel to do work on the project, considerable progress in development of the ultrasound signal processing algorithms has been made. We have developed a user interface for the software, and have developed algorithms to calculate RF and statistical texture features for the data. In addition, collection of clinical data has continued with 79 prostate glands having been examined producing perhaps the largest database ever of complete prostate histology with ultrasound correlation. Slow progress on the assembly of quarter sections into whole mount sections for comparison with the ultrasound images has been achieved because no person to do the work was found. The work of assembling the images will now be performed by the research assistant supervised by the PI with the Department of Pathology in a consultative role.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 2000
- Accession Number
- ADA389753
Entities
People
- Brian S. Garra
Organizations
- University of Vermont