2033 EXTERNAL VALIDATION OF THE ANNA/C-TRUS SYSTEM REGARDING THE CORRECT IDENTIFICATION OF PROSTATE CANCER LESIONS IN THE DIAGNOSIS OF PROSTATE CANCER
Jochen Christoph Walz, Jeanne Thomassin Piana, Flora Poizat, Serge Brunelle, Naji Salem, Gwénaëlle Gravis · The Journal of Urology · 2012
You have accessJournal of UrologyImaging/Radiology: Uroradiology I1 Apr 20122033 EXTERNAL VALIDATION OF THE ANNA/C-TRUS SYSTEM REGARDING THE CORRECT IDENTIFICATION OF PROSTATE CANCER LESIONS IN THE DIAGNOSIS OF PROSTATE CANCER Jochen Walz, Jeanne Thomassin-Piana, Flora Poizat, Serge Brunelle, Naji Salem, and Gwenaelle Gravis Jochen WalzJochen Walz Marseille, France More articles by this author , Jeanne Thomassin-PianaJeanne Thomassin-Piana Marseille, France More articles by this author , Flora PoizatFlora Poizat Marseille, France More articles by this author , Serge BrunelleSerge Brunelle Marseille, France More articles by this author , Naji SalemNaji Salem Marseille, France More articles by this author , and Gwenaelle GravisGwenaelle Gravis Marseille, France More articles by this author View All Author Informationhttps://doi.org/10.1016/j.juro.2012.02.2197AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookTwitterLinked InEmail INTRODUCTION AND OBJECTIVES Conventional grey scale ultrasound has only limited value in the diagnosis of prostate cancer. The ANNA/C-TRUS system was developed to overcome this problem. It is based on an artificial neuronal network analysis (ANNA) of trans rectal grey scale ultrasound pictures. The system was trained to identify the lesion most suspicious for prostate cancer by coding it in different shades of yellow to red. Based on the analysis targeted biopsies of suspicious lesions can be performed. First clinical results are promising. However, so far no external validation of the system using pathological whole mount sections as the reference was done. Such validation is considered the Goldstandard for the validation of prostate cancer imaging tools. The aim of the study was to perform such a validation. METHODS Between June and Sept 2011, 28 patients diagnosed with prostate cancer and scheduled for radical prostatectomy underwent ultrasound the day before radical prostatectomy. The preoperative pictures were filed and send via the internet platform to the ANNA/C-TRUS server for analysis. For validation purposes each prostate was partitioned into 6 sectors (left, right and base, middle gland, apex) for a total of 168 sectors evaluated. Suspicious zones were filed depending on their localization. The prostatectomy specimens were processed according to the Stanford protocol and prostate cancer lesion were filed according to the 6 sector scheme. The preoperative and postoperative results regarding tumor localization were then compared and diagnostic values were calculated. RESULTS In the study group median age was 62 years, median PSA was 6.4ng/ml, pathological stage was pT2a in 3.6%,pT2b in 3.6%, pT2c in 67.9% and pT3 in 25.0%, and pathological Gleason score was =8 in 7.1%. In total, 86 cancer lesions could be identified with a median of 3 lesions per prostate. Regarding the correct identification of prostate cancer lesions in the prostate the ANNA/C-TRUS system achieved a sensitivity of 83.1%, a specificity of 63.9%, a NPV of 68.4% a PPV of 80.1% and an overall accuracy of 76.2%. CONCLUSIONS In this study, the ANNA/C-TRUS system showed a high reliability to identify prostate cancer lesions in the prostate as evidenced by the high sensitivity and PPV. ANNA/C-TRUS has great potential to improve prostate cancer diagnosis by targeting biopsies to suspicious lesions. Multicentre biopsy studies need to confirm these results. © 2012 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 187Issue 4SApril 2012Page: e820 Advertisement Copyright & Permissions© 2012 by American Urological Association Education and Research, Inc.MetricsAuthor Information Jochen Walz Marseille, France More articles by this author Jeanne Thomassin-Piana Marseille, France More articles by this author Flora Poizat Marseille, France More articles by this author Serge Brunelle Marseille, France More articles by this author Naji Salem Marseille, France More articles by this author Gwenaelle Gravis Marseille, France More articles by this author Expand All Advertisement Advertisement PDF downloadLoading ...