Search

Purpose: Urothelial bladder cancer (UCB) care requires frequent follow-up cystoscopy and surgery. Confocal laser endomicroscopy (CLE) is a probe-based optical technique that can provide real-time microscopic evaluation with the potential for outpatient grading of UCB. This study aims to investigate the diagnostic accuracy and interobserver variability for the grading of UCB with CLE during flexible cystoscopy (fCLE)., Methods: Participants scheduled for transurethral resection of papillary bladder tumors were prospectively included for intra-operative fCLE. Exclusion criteria were flat lesions, fluorescein allergy or pregnancy. Two independent observers evaluated fCLE, classifying tumors as low- or high-grade urothelial carcinoma (LGUC/HGUC) or benign. Interobserver agreement was calculated with Cohens kappa (κ) and diagnostic accuracy with 2 × 2 tables. Histopathology was the reference test., Results: Histopathology of 34 lesions revealed 14 HGUC, 14 LGUC and 6 benign tumors. Diagnostic yield for fCLE was 80-85% with a κ of 0.75. Respectively, sensitivity, specificity, NPV and PPV were: for benign tumors 0-20%, 96-100%, unmeasureable-50% and 87%, for LGUC 57-64%, 41-58%, 44-53% and 54-69% and for HGUC 38-57%, 56-68%, 38-57% and 56-68%, with an interobserver agreement of κ 0.61., Conclusion: fCLE is currently insufficient to grade UCB., (© 2024. The Author(s).)

Accurate grading of non-muscle-invasive urothelial cell carcinoma is of major importance; however, high interobserver variability exists. A fully automated detection and grading network based on deep learning is proposed to enhance reproducibility. A total of 328 transurethral resection specimens from 232 patients were included, and a consensus reading by three specialized pathologists was used. The slides were digitized, and the urothelium was annotated by expert observers. The U-Net-based segmentation network was trained to automatically detect urothelium. This detection was used as input for the classification network. The classification network aimed to grade the tumors according to the World Health Organization grading system adopted in 2004. The automated grading was compared with the consensus and individual grading. The segmentation network resulted in an accurate detection of urothelium. The automated grading shows moderate agreement (κ = 0.48 ± 0.14 SEM) with the consensus reading. The agreement among pathologists ranges between fair (κ = 0.35 ± 0.13 SEM and κ = 0.38 ± 0.11 SEM) and moderate (κ = 0.52 ± 0.13 SEM). The automated classification correctly graded 76% of the low-grade cancers and 71% of the high-grade cancers according to the consensus reading. These results indicate that deep learning can be used for the fully automated detection and grading of urothelial cell carcinoma., (Copyright © 2020 American Society for Investigative Pathology. Published by Elsevier Inc. All rights reserved.)

Purpose: Urothelial carcinoma of the bladder (UCB) is the most common urinary cancer. White-light cystoscopy (WLC) forms the corner stone for the diagnosis of UCB. However, histopathological assessment is required for adjuvant treatment selection. Probe-based confocal laser endomicroscopy (pCLE) enables visualization of the microarchitecture of bladder lesions during WLC, which allows for real-time tissue differentiation and grading of UCB. To improve the diagnostic process of UCB, computer-aided classification of pCLE videos of in vivo bladder lesions were evaluated in this study. Materials and Methods: We implemented preprocessing methods to optimize contrast and to reduce striping artifacts in each individual pCLE frame. Subsequently, a semiautomatic frame selection was performed. The selected frames were used to train a feature extractor based on pretrained ImageNet networks. A recurrent neural network, in specific long short-term memory (LSTM), was used to predict the grade of bladder lesions. Differentiation of lesions was performed at two levels, namely (i) healthy and benign vs malignant tissue and (ii) low-grade vs high-grade papillary UCB. A total of 53 patients with 72 lesions were included in this study, resulting in ∼140,000 pCLE frames. Results: The semiautomated frame selection reduced the number of frames to ∼66,500 informative frames. The accuracy for differentiation of (i) healthy and benign vs malignant urothelium was 79% and (ii) high-grade and low-grade papillary UCB was 82%. Conclusions: A feature extractor in combination with LSTM results in proper stratification of pCLE videos of in vivo bladder lesions.

Purpose: Confocal laser endomicroscopy (CLE) is a fluorescence-based fiber-optic imaging technique with the potential for intraoperative grading of upper tract urothelial carcinoma (UTUC). This study aims to (1) investigate the prevalence of the previously proposed CLE criteria for bladder cancer in papillary UTUC, (2) estimate the diagnostic value of CLE for UTUC grading and (3) propose a scoring system for a more quantifiable approach of CLE-based grading of UTUC., Materials and Methods: Ureteroscopic CLE was performed in patients with UTUC. Following CLE imaging, co-localized biopsies were taken for histopathologic comparison. Postoperatively, two blinded raters assessed the CLE images., Results: Fifty-three papillary UTUCs (34 low grade and 19 high grade) were imaged with CLE in 36 patients. All the previously described CLE criteria were identifiable in varying proportions. After excluding 10 non-diagnostic recordings (5 low grade and 5 high grade) due to insufficient image quality, the histopathologic grade was correctly identified with CLE in 26 low-grade UTUCs (90%) and in 12 high-grade UTUCs (86%). The most prevalent CLE criteria with the highest diagnostic potential were cellular organization, morphology and cohesiveness of cells. A scoring system was proposed with these criteria, which yielded similar diagnostic accuracies., Conclusions: Based on the previously proposed criteria, CLE enables accurate grading of papillary UTUC at a non-diagnostic rate of 19%. The most prevalent CLE criteria with the highest diagnostic potential for grading of papillary UTUC are cellular organization, morphology and cohesiveness of cells. The proposed scoring system may simplify the assessment of CLE images for UTUC grading but external validation is required.

Purpose: Biopsies and cytology are cornerstones in the diagnosis of upper urinary tract urothelial carcinoma. However, a high rate of nondiagnostic biopsies, tumor upgrading and tumor up staging after nephroureterectomy has been observed. In this prospective in vivo study we evaluated the diagnostic accuracy of optical coherence tomography for the grading and staging of upper tract urothelial carcinoma., Materials and Methods: A total of 26 patients underwent diagnostic ureterorenoscopy including biopsies and optical coherence tomography, followed by nephroureterectomy or segmental ureter resection. The sensitivity, specificity, negative predictive value and positive predictive value of upper tract urothelial carcinoma grading and staging by optical coherence tomography were evaluated according to the STARD (Standards for Reporting of Diagnostic Accuracy) initiative and the second stage (2a and 2b) of the IDEAL model. For tumor staging a 2×2 table for sensitivity and specificity was calculated. For tumor grading the Wilcoxon rank sum test was used to test μ oct in low and high grade lesions followed by ROC analysis for sensitivity and specificity., Results: In 83% the staging of lesions was in accordance with final histopathology. Sensitivity and specificity analysis for tumor invasion was 100% and 92%, respectively. Tumor size greater than 2 mm and inflammation were risks for false-positives. For low and high grade lesions median μ oct was 2.1 and 3.0 mm -1 , respectively (p <0.01). ROC analysis showed a sensitivity of 87% and a specificity of 90% using a μ oct cutoff of 2.4 mm -1 ., Conclusions: This report describes optical coherence tomography as a real-time, intraoperatively diagnostic modality in the diagnostic evaluation of upper tract urothelial carcinoma. We confirmed the ability of optical coherence tomography to visualize, grade and stage urothelial carcinoma in the upper urinary tract., (Copyright © 2016 American Urological Association Education and Research, Inc. Published by Elsevier Inc. All rights reserved.)

Purpose: Developments in optical diagnostics have potential for less invasive diagnosis of upper urinary tract urothelial carcinoma (UUT-UC). This systematic review provides an overview of technology, applications, and limitations of recently developed optical diagnostics in the upper urinary tract and outlines their potential for future clinical applications. In addition, current evidence was evaluated., Literature Search: A PubMed literature search was performed and articles on narrow band imaging (NBI), photodynamic diagnosis (PDD), Storz professional imaging enhancement system (SPIES), optical coherence tomography (OCT), and confocal laser endomicroscopy (CLE) regarding UUT-UC were reviewed for data extraction. Study quality was reviewed according to Quality Assessment of Diagnostic Accuracy Studies and Innovation, Development, Exploration, Assessment, and Long-term follow-up (IDEAL) standards., Results: Four articles available for quality assessment, demonstrated high level of evidence, but low level of IDEAL stage. NBI and SPIES enhance contrast of mucosal surface and vascular structures, improving tumor detection rate. A first in vivo study showed promising results. PDD uses fluorescence to improve tumor detection rate. However, due to the acute angle of the ureterorenoscopes there is an increased risk of false positives. OCT produces cross-sectional high-resolution images, providing information on tumor grade and stage. A pilot study showed promising diagnostic accuracy. CLE allows ultrahigh-resolution microscopy of tissue resulting in images of the cellular structure. CLE cannot be applied in vivo in the upper urinary tract yet, due to technical limitations., Conclusions: NBI, SPIES, and PDD aim at improving visualization of UUT-UC through contrast enhancement. OCT and CLE aim at providing real-time predictions of histopathological diagnosis. For all techniques, more research has to be conducted before these techniques can be implemented in the routine management of UUT-UC. All techniques might be of value in specific clinical scenarios and allow for integration, for example, OCT with NBI, and could therefore improve tumor detection and staging and help in selecting the optimal treatment for the individual patient.

Purpose: Knowledge of tumor stage and grade is paramount for treatment decision making in cases of upper urinary tract urothelial carcinoma but this condition cannot be accurately assessed by current techniques. Optical coherence tomography can hypothetically provide the urologist with real-time intraoperative information on tumor grade and stage. In this pilot study we report what are to our knowledge the first results of optical coherence tomography for grading and staging upper urinary tract urothelial carcinoma., Materials and Methods: Eight consecutive patients underwent ureterorenoscopy for suspicion or followup of upper urinary tract urothelial carcinoma. Optical coherence tomography data sets were intraoperatively obtained from the ureter and renal pelvis. All patients eventually underwent nephroureterectomy. Optical coherence tomography staging was done by visual inspection of lesions found on optical coherence tomography images. Optical coherence tomography grading was done by quantifying optical coherence tomography signal attenuation in mm(-1) on lesions and comparing results with the histopathological diagnosis. The Wilcoxon rank sum test was used for statistical analysis., Results: For 7 in vivo optical coherence tomography diagnoses staging was in accordance with histology. In patient 8 tumor thickness transcended optical coherence tomography imaging depth range and, therefore, invasiveness findings were inconclusive. For grading the median attenuation coefficient for grade 2 and 3 lesions was 1.97 (IQR 1.57-2.30) and 3.53 mm(-1) (IQR 2.74-3.94), respectively (p<0.001). Healthy urothelium was too thin to reliably determine the attenuation coefficient., Conclusions: Optical coherence tomography is a promising, minimally invasive tool for real-time intraoperative optical diagnosis of tumors in the upper urinary tract. Our results warrant future research in a larger sample size to determine the accuracy of grading and staging by optical coherence tomography, and its possible implementation in the diagnostic algorithm for upper urinary tract urothelial carcinoma., (Copyright © 2013 American Urological Association Education and Research, Inc. Published by Elsevier Inc. All rights reserved.)