Recent Developments in Tissue-Type Imaging (TTI) for Planning and Monitoring Treatment of Prostate Cancer

• Published in: Ultrasonic imaging 2004-07, Vol.26 (3), p.163-172
• Main Authors: Feleppa, Ernest J., Porter, Christopher R., Ketterling, Jeffrey, Lee, Paul, Dasgupta, Shreedevi, Urban, Stella, Kalisz, Andrew
• Format: Article
• Language: English
• Subjects: Acoustics; Biological and medical sciences; Biopsy; Exact sciences and technology; Fundamental areas of phenomenology (including applications); Humans; Investigative techniques, diagnostic techniques (general aspects); Male; Medical sciences; Miscellaneous. Technology; Neural Networks (Computer); Patient Care Planning; Physics; Prostate-Specific Antigen - blood; Prostatic Neoplasms - pathology; Prostatic Neoplasms - therapy; ROC Curve; Signal Processing, Computer-Assisted; Ultrasonic investigative techniques; Ultrasonics, quantum acoustics, and physical effects of sound; Ultrasonography, Interventional
• ISSN: 0161-7346; 1096-0910
• DOI: 10.1177/016173460402600303

Because current methods of imaging prostate cancer are inadequate, biopsies cannot be effectively guided and treatment cannot be effectively planned and targeted. Therefore, our research is aimed at ultrasonically characterizing cancerous prostate tissue so that we can image it more effectively and thereby provide improved means of detecting, treating and monitoring prostate cancer. We base our characterization methods on spectrum analysis of radiofrequency (rf) echo signals combined with clinical variables such as prostate-specific antigen (PSA). Tissue typing using these parameters is performed by artificial neural networks. We employed and evaluated different approaches to data partitioning into training, validation, and test sets and different neural network configuration options. In this manner, we sought to determine what neural network configuration is optimal for these data and also to assess possible bias that might exist due to correlations among different data entries among the data for a given patient. The classification efficacy of each neural network configuration and data-partitioning method was measured using relative-operating-characteristic (ROC) methods. Neural network classification based on spectral parameters combined with clinical data generally produced ROC-curve areas of 0.80 compared to curve areas of 0.64 for conventional transrectal ultrasound imaging combined with clinical data. We then used the optimal neural network configuration to generate lookup tables that translate local spectral parameter values and global clinical-variable values into pixel values in tissue-type images (TTIs). TTIs continue to show cancerous regions successfully, and may prove to be particularly useful clinically in combination with other ultrasonic and nonultrasonic methods, e.g., magnetic-resonance spectroscopy.