Affiliations: Lizzi Center for Biomedical Engineering, Riverside Research Institute, New York, NY, USA. E-mail: [email protected] | Lizzi Center for Biomedical Engineering, Riverside Research Institute, New York, NY, USA
Abstract: Improved means of imaging prostate cancer would enable more-effective biopsy and treatment guidance and potentially would provide a reliable means of monitoring non-surgical therapy. Current, commonly used, conventional means of imaging the prostate do not reliably depict cancerous lesions, and as a result, biopsy needles are placed with respect to visible anatomic features of the gland, treatment tends to involve the entire gland, and monitoring of non-surgical therapy is based predominantly on blood PSA levels, and in many cases, periodic biopsies. Conventional transrectal ultrasound often is the imaging modality of choice for prostate biopsy and treatment procedures, but it offers no advantages in terms of reliably depicting cancerous regions of the gland. However, new methods of tissue-type imaging that are based on spectrum analysis of echo signals and that utilize artificial neural networks for classification offer promise of reliably distinguishing cancerous lesions from non-cancerous tissue in the prostate. The classifier produced an ROC-curve area of 0.84 for 617 biopsied locations compared to areas of 0.64 for conventional assessments of the same locations in biopsy-guidance B-mode images. The potential improvement in imaging sensitivity implied by the ROC curves is more than 50%. If current validation studies confirm these initial results, then an effective, inexpensive, noninvasive means of imaging prostate-cancer foci and therefore of guiding biopsies and treatments will be available to urologists and radiation oncologists.
