rtCAB: A tool for reducing unnecessary prostate biopsy cores

With more than 110.000 new cases/year in Europe, prostate cancer (PCa) isone of the most frequent neoplasy. When suspects arise from standard diagnosticmethods (i.e. Digital Rectal Exam, Transrectal Ultrasonography (TRUS), PSAlevel) a prostate biopsy (PBx) is mandatory. As patient discomfort and adverseevent probability both grows with core number, it is desirable to reduce thenumber of PBx cores without negative impinging on diagnose accuracy. The workdescribes an innovative processing technique called real-time Computer AidedBiopsy (rtCAB) which enhances TRUS video stream with a false color overlayimage, and suggests the physician where to sample thus reducing the total numberof cores. Our proposal consists in a real-time non-linear classifier whichprocesses the output of an original Maximum Likelihood estimator of Nakagamiparameters based on Pade Approximant. The resulting algorithm, implementedmaking full use of CUDA parallel processing capabilities, is capable to deliverframe rates as high as 30 fps. Classification model was trained on a prostategland adenocarcinoma database (400 PBx cores, 8000 ROIs). Ground truth for eachcore was established by an expert physician, providing tissue description andillness percentage for each core. The system was tuned for reducing the numberof false positives while preserving an acceptable number of false negatives.Comparing to a classical double sextant PBx, the positive prediction value (PPV)of our method is 65% better, with an overall sensitivity of 100