Three-dimensional ultrasound analyses of the prostate.

Although conventional ultrasonography has proven to be clinically useful for depicting many types of cancerous lesions, it cannot distinguish reliably between cancerous and noncancerous tissue of the prostate. Therefore, conventional transrectal ultrasonography (TRUS) is used primarily for general evaluations of the gland and for guiding biopsies based on clearly imaged anatomic features such as the capsule, seminal vesicles, and urethra. Spectrum analysis extracts ultrasound signal parameters associated with biopsy-proven tissue types, and these parameters are then classified using neural network tools such as learning vector quantization, radial basis, and multilayer perceptron algorithms. Classification of cancerous and noncancerous prostate tissue using neural networks produces receiver operating characteristic (ROC) curves of 0.87 +/- 0.04 compared with 0.64 +/- 0.04 for conventional ultrasonography. To image the prostate using these methods, parameter values are computed at each pixel location, then translated into a score for the likelihood of cancer using a look-up table generated using the best classification algorithm. The score for cancer likelihood is expressed as a gray-scale or color value, and the resulting image may be useful to guide biopsies or therapy. Changes in parameter or score values over time potentially can be used to assess progression of disease or efficacy of therapy.

Progress in Two-Dimensional and Three-Dimensional Ultrasonic Tissue-Type Imaging of the Prostate Based on Spectrum Analysis and Nonlinear Classifiers.

Spectrum analysis of radiofrequency (RF) ultrasonic echo signals often can sense tissue differences that are not visible on conventional ultrasonic images. Spectrum-analysis parameter values combined with other variables, such as serum prostate specific antigen (PSA) concentration, can be classified by neural networks to distinguish effectively between cancerous and noncancerous prostate tissues. Images based on neural network classification of spectral parameters and clinical variables can be advantageous for biopsy guidance, staging, and treatment planning and monitoring. A study based on 644 biopsies from 137 patients showed that these methods are significantly superior to B-mode image interpretation for differentiating cancerous from noncancerous prostate tissues. Using the histologic determination of tissue types as the gold standard, the area under the receiver-operator characteristic (ROC) curve for neural network classification based on spectrum analysis and PSA value for the 644 biopsies was 0.87 +/- 0.04, and the ROC curve are for a level-of-suspicion (LOS) assignment based on B-mode imaging was 0.64 +/- 0.04. Color-encoded and gray-scale images derived from neural network assignment of suspicion for cancer at each pixel location showed remarkable detail and suggested potential clinical value for biopsy guidance using real-time two-dimensional (2D) images and staging, treatment planning, and monitoring using three-dimensional (3D) images.