Diagnostic Classification of Cystoscopic Images Using Deep Convolutional Neural Networks.

PURPOSE: The recognition of cystoscopic findings remains challenging for young colleagues and depends on the examiner's skills. Computer-aided diagnosis tools using feature extraction and deep learning show promise as instruments to perform diagnostic classification. MATERIALS AND METHODS: Our study considered 479 patient cases that represented 44 urologic findings. Image color was linearly normalized and was equalized by applying contrast-limited adaptive histogram equalization. Because these findings can be viewed via cystoscopy from every possible angle and side, we ultimately generated images rotated in 10-degree grades and flipped them vertically or horizontally, which resulted in 18,681 images. After image preprocessing, we developed deep convolutional neural network (CNN) models (ResNet50, VGG-19, VGG-16, InceptionV3, and Xception) and evaluated these models using F1 scores. Furthermore, we proposed two CNN concepts: 90%-previous-layer filter size and harmonic-series filter size. A training set (60%), a validation set (10%), and a test set (30%) were randomly generated from the study data set. All models were trained on the training set, validated on the validation set, and evaluated on the test set. RESULTS: The Xception-based model achieved the highest F1 score (99.52%), followed by models that were based on ResNet50 (99.48%) and the harmonic-series concept (99.45%). All images with cancer lesions were correctly determined by these models. When the focus was on the images misclassified by the model with the best performance, 7.86% of images that showed bladder stones with indwelling catheter and 1.43% of images that showed bladder diverticulum were falsely classified. CONCLUSION: The results of this study show the potential of deep learning for the diagnostic classification of cystoscopic images. Future work will focus on integration of artificial intelligence-aided cystoscopy into clinical routines and possibly expansion to other clinical endoscopy applications.

Randomized trial comparing office flexible to rigid cystoscopy in women.

INTRODUCTION AND HYPOTHESIS: The objective of the study was to compare office rigid cystoscopy (RC) versus flexible cystoscopy (FC) in women. METHODS: This was a prospective randomized trial comparing FC to RC. Aims were to assess 1-week post-procedural complications, compare procedure pain scores, and to assess physician perception of patient discomfort. Pain scores were assessed by visual analogue scale (VAS) and 5-point verbal descriptor scale (VDS). Chi-square was used for categorical comparison and t tests or Wilcoxon test for continuous variables. RESULTS: One hundred women were enrolled. The mean age of participants was 59.7 years (± SD 14.6), and 91 % were Caucasian. This was the first cystoscopy for 86 % of participants. On the 1-week post-procedure questionnaire (85 % response rate), participants in the FC group reported urinary frequency more often than in the RC group (p = 0.041). The FC group reported urgency with urination lasting 1-2 days (p = 0.030) and burning with urination lasting >3 days (p = 0.026), more than the RC group. These symptoms did not persist at 7 days. The duration of the procedure was slightly faster for the FC group (4.6 ± 1.8 min vs 5.7 ± 3.4 min, p = 0.046). Median VAS scores were 0.9 (0.1-2.72) for the FC group and 0.5 (0-2.4) for the RC group (p = 0.505). There were no significant differences between patient or physician perception of pain in either group. CONCLUSIONS: Urinary frequency and duration of urinary burning post procedure occurred more frequently in the FC group, although these symptoms were transient. Both office FC and RC are generally well tolerated in women with overall low morbidity.