Clinical value of digital image analysis in the diagnosis of urinary bladder cancer, particularly in aggressive tumors: a preliminary report.

Abstract

The aim of the project was to evaluate the clinical value of a computer analysis of cytological specimen images obtained from urine and bladder washing samples. Three sample types (voided urine, catheterized urine and bladder washing) from 59 patients with primary or recurrent tumor were analyzed. All patients underwent cystoscopy and biopsy or resection. The histological results were compared with the results of the image analyzing computer system of collected urine samples. The consistency between the computer diagnosis and the clinical or histological diagnosis both in the presence and absence of cancer was as follows: 77% for voided urine samples, 72.5% for catheterized urine samples and 78% for bladder washing samples. The specificity of the method at the standard pathology level was 71%, and the sensitivity was 83%. The positive and negative predictive values (PPV and NPV) were 87.5% and 63% respectively. The sensitivity for G3 or CIS or T2 or T3 tumors reached nearly 100%. Computer analysis of urine provided correct diagnoses in cancer and control patients with the sensitivity of 83% and specificity of 71% and gave excellent results in aggressive tumors such as T2, T3, G3 and in CIS.