The Journal of urology
-
The Journal of urology · Feb 2016
Use of Artificial Intelligence and Machine Learning Algorithms with Gene Expression Profiling to Predict Recurrent Nonmuscle Invasive Urothelial Carcinoma of the Bladder.
Due to the high recurrence risk of nonmuscle invasive urothelial carcinoma it is crucial to distinguish patients at high risk from those with indolent disease. In this study we used a machine learning algorithm to identify the genes in patients with nonmuscle invasive urothelial carcinoma at initial presentation that were most predictive of recurrence. We used the genes in a molecular signature to predict recurrence risk within 5 years after transurethral resection of bladder tumor. ⋯ Using primary nonmuscle invasive urothelial carcinoma from initial occurrences genetic programming identified transcripts in reproducible fashion, which were predictive of recurrence. These findings could potentially impact nonmuscle invasive urothelial carcinoma management.
-
The Journal of urology · Feb 2016
Fiber-Optic Confocal Laser Endomicroscopy of Small Renal Masses: Toward Real-Time Optical Diagnostic Biopsy.
The incidental detection of small renal masses is increasing. However, not all require aggressive treatments as up to 20% are benign and the majority of malignant tumors harbor indolent features. Improved preoperative diagnostics are needed to differentiate tumors requiring aggressive treatment from those more suitable for surveillance. We evaluated and compared confocal laser endomicroscopy with standard histopathology in ex vivo human kidney tumors as proof of principle towards diagnostic optical biopsy. ⋯ We report what is to our knowledge the first feasibility study using confocal laser endomicroscopy to evaluate small renal masses ex vivo and provide a preliminary atlas of images from various renal neoplasms with corresponding histology. These findings serve as an initial and promising step toward real-time diagnostic optical biopsy of small renal masses.