Development and deployment of a histopathology-based deep learning algorithm for patient prescreening in a clinical trial.

Accurate identification of genetic alterations in tumors, such as Fibroblast Growth Factor Receptor, is crucial for treating with targeted therapies; however, molecular testing can delay patient care due to the time and tissue required. Successful development, validation, and deployment of an AI-based, biomarker-detection algorithm could reduce screening cost and accelerate patient recruitment. Here, we develop a deep-learning algorithm using >3000 H&E-stained whole slide images from patients with advanced urothelial cancers, optimized for high sensitivity to avoid ruling out trial-eligible patients. The algorithm is validated on a dataset of 350 patients, achieving an area under the curve of 0.75, specificity of 31.8% at 88.7% sensitivity, and projected 28.7% reduction in molecular testing. We successfully deploy the system in a non-interventional study comprising 89 global study clinical sites and demonstrate its potential to prioritize/deprioritize molecular testing resources and provide substantial cost savings in the drug development and clinical settings.

[Urinary cytology for the detection of urothelial lesions]. / Rôle de la cytologie urinaire dans le dépistage des lésions urothéliales.

Urine cytology is a long-used technique for the detection of high grade neoplastic urothelial lesions. Since 2016, «The Paris System¼ classification has revolutionized this field by introducing a standardized terminology widely adopted by cytopathologists and urologists. In this article, we explain this classification and discuss its impact on the clinical management of patients with urothelial lesions, as well as its role in the secondary prevention of these lesions.

La cytologie urinaire est une technique utilisée depuis longtemps dans la détection des lésions urothéliales tumorales de haut grade. Depuis 2016, la classification «The Paris System¼ a révolutionné ce domaine en introduisant une terminologie standardisée largement adoptée par les cytopathologistes et les urologues. Dans cet article, nous expliquons cette classification et discutons de son impact sur la prise en charge clinique des lésions urothéliales, ainsi que son rôle dans la prévention secondaire de ces lésions.

Molecular Pathology of Urothelial Carcinoma.

Urothelial carcinoma is characterized by the presence of a wide spectrum of histopathologic features and molecular alterations that contribute to its morphologic and genomic heterogeneity. It typically harbors high rates of somatic mutations with considerable genomic and transcriptional complexity and heterogeneity that is reflective of its varied histomorphologic and clinical features. This review provides an update on the recent advances in the molecular characterization and novel molecular taxonomy of urothelial carcinoma and variant histologies.

Defining oligometastatic state in uro-oncological cancers.

PURPOSE OF REVIEW: Oligometastatic tumors illustrate a distinct state between localized and systematic disease and might harbor unique biologic features. Moreover, these tumors represent a different clinical entity, with a potential of long-term disease control or even cure, therefore they receive growing attention in the field of urologic oncology. RECENT FINDINGS: Currently, there is no consensus on the definition of oligometastatic prostate cancer, most experts limit it to a maximum of three to five lesions and involvement of no more than two organs, excluding visceral metastases. Quality data on oligometastatic bladder cancer is scarce, however, a consensus of experts defined it as a maximum of three metastatic lesions, either resectable or suitable for stereotactic therapy, without restrictions to the number of organs involved. As for kidney cancer, a maximum number of five metastases, without limitations to the location are defined as oligometastatic, with an important implication of timing of developing metastases since diagnosis of the primary tumor. SUMMARY: Defining oligometastatic state among urological tumors reflecting their distinct biological and clinical behavior is crucial to establish a sound framework for future clinical trials, and to facilitate guideline and policy formulation for improved patient care. Advancements in molecular imaging are expected to transform the field of oligometastatic urologic tumors in the future.

[What contribution can make artificial intelligence to urinary cytology?] / Quel apport de l'intelligence artificielle en cytologie urinaire ?

Urinary cytology using the Paris system is still the method of choice for screening high-grade urothelial carcinomas. However, the use of the objective criteria described in this terminology shows a lack of inter- and intra-observer reproducibility. Moreover, if its sensitivity is excellent on instrumented urine, it remains insufficient on voided urine samples. Urinary cytology appears to be an excellent model for the application of artificial intelligence to improve performance, since the objective criteria of the Paris system are defined at cellular level, and the resulting diagnostic approach is presented in a highly "algorithmic" way. Nevertheless, there is no commercially available morphological diagnostic aid, and very few predictive devices are still undergoing clinical validation. The analysis of different systems using artificial intelligence in urinary cytology rises clear prospects for mutual contributions.

Multimodal Approach in the Diagnosis of Urologic Malignancies: Critical Assessment of ChatGPT-4V's Image-Reading Capabilities.

ChatGPT-4V model with image interpretation tested for distinguishing kidney & prostate tumors from normal tissue.

C-reactive protein (CRP) as a prognostic biomarker in patients with urothelial carcinoma: A systematic review and meta-analysis.

C-reactive protein (CRP) may reflect a pro-inflammatory tumor microenvironment and could represent a biomarker to select patients with urothelial carcinoma more likely to benefit from therapies directed at modulating tumor-promoting inflammation. We performed a systematic review to evaluate survival outcomes based on pre-treatment CRP values in urothelial carcinoma. The hazard ratios (HRs) of survival such as overall survival (OS) and progression-free survival (PFS) between groups with high versus low CRP values were pooled by the random-effect model meta-analyses. Overall, 28 studies comprising 6789 patients were identified for meta-analyses. High CRP levels were associated with shorter OS (HR=1.96 [95% CI: 1.64-2.33], p < 0.01), particularly in advanced disease treated with immune checkpoint blockade (ICB, HR=1.78 [1.47-2.15], p < 0.01). Similar findings were observed in ICB-treated patients with PFS. These findings suggest that CRP could be an attractive biomarker to select patients with urothelial carcinoma for strategies seeking to modulate tumor-promoting inflammation.

Enhancing upper tract urothelial carcinoma diagnosis: Utility of cytokeratin 17 and CK20/CD44/p53 immunohistochemical panel.

Upper tract urothelial carcinoma (UTUC) presents diagnostic challenges due to small biopsy specimen size, poor orientation, and technical obstacles that can yield equivocal diagnoses. This uncertainty often mandates repeated biopsies to evaluate the necessity of nephroureterectomy. Prior studies have suggested cytokeratin 17 (CK17) immunostain as an adjunctive tool for diagnosing bladder urothelial neoplasia in both urine cytology and tissue biopsy specimens. We evaluated the utility of CK17 in differentiating UTUC from benign urothelium and its ability to stratify low-grade from high-grade neoplasia. Our study involved a cohort of previously diagnosed cytology (n = 29) and tissue specimens from biopsies and resections (n = 85). We evaluated CK17 staining percentage in cytology and tissue samples and localization patterns in biopsy/resection samples. Our findings showed a statistically significant distinction (p < 0.05) between UTUC and benign tissue specimens based on full thickness localization pattern (odds ratio 8.8 [95% CI 1.53-67.4]). The percentage of CK17 staining failed to significantly differentiate neoplastic from non-neoplastic cases in cytology or tissue samples. Additionally, based on prior research showing the efficacy of CK20/CD44/p53 triple panel in bladder urothelial neoplasia, we utilized tissue microarrays to evaluate if these markers could distinguish UTUC from benign urothelium. We found that CK20/CD44/p53, individually or in combination, could not distinguish urothelial neoplasia from non-neoplasia. Full thickness CK17 urothelial localization by immunohistochemistry was highly reproducible with excellent interobserver agreement and may play a supplementary role in distinguishing upper tract urothelial neoplasia from benign urothelium.

A deep-learning workflow to predict upper tract urothelial carcinoma protein-based subtypes from H&E slides supporting the prioritization of patients for molecular testing.

Upper tract urothelial carcinoma (UTUC) is a rare and aggressive, yet understudied, urothelial carcinoma (UC). The more frequent UC of the bladder comprises several molecular subtypes, associated with different targeted therapies and overlapping with protein-based subtypes. However, if and how these findings extend to UTUC remains unclear. Artificial intelligence-based approaches could help elucidate UTUC's biology and extend access to targeted treatments to a wider patient audience. Here, UTUC protein-based subtypes were identified, and a deep-learning (DL) workflow was developed to predict them directly from routine histopathological H&E slides. Protein-based subtypes in a retrospective cohort of 163 invasive tumors were assigned by hierarchical clustering of the immunohistochemical expression of three luminal (FOXA1, GATA3, and CK20) and three basal (CD44, CK5, and CK14) markers. Cluster analysis identified distinctive luminal (N = 80) and basal (N = 42) subtypes. The luminal subtype mostly included pushing, papillary tumors, whereas the basal subtype diffusely infiltrating, non-papillary tumors. DL model building relied on a transfer-learning approach by fine-tuning a pre-trained ResNet50. Classification performance was measured via three-fold repeated cross-validation. A mean area under the receiver operating characteristic curve of 0.83 (95% CI: 0.67-0.99), 0.8 (95% CI: 0.62-0.99), and 0.81 (95% CI: 0.65-0.96) was reached in the three repetitions. High-confidence DL-based predicted subtypes showed significant associations (p < 0.001) with morphological features, i.e. tumor type, histological subtypes, and infiltration type. Furthermore, a significant association was found with programmed cell death ligand 1 (PD-L1) combined positive score (p < 0.001) and FGFR3 mutational status (p = 0.002), with high-confidence basal predictions containing a higher proportion of PD-L1 positive samples and high-confidence luminal predictions a higher proportion of FGFR3-mutated samples. Testing of the DL model on an independent cohort highlighted the importance to accommodate histological subtypes. Taken together, our DL workflow can predict protein-based UTUC subtypes, associated with the presence of targetable alterations, directly from H&E slides.

An artificial intelligence-powered PD-L1 combined positive score (CPS) analyser in urothelial carcinoma alleviating interobserver and intersite variability.

AIMS: Immune checkpoint inhibitors targeting programmed death-ligand 1 (PD-L1) have shown promising clinical outcomes in urothelial carcinoma (UC). The combined positive score (CPS) quantifies PD-L1 22C3 expression in UC, but it can vary between pathologists due to the consideration of both immune and tumour cell positivity. METHODS AND RESULTS: An artificial intelligence (AI)-powered PD-L1 CPS analyser was developed using 1,275,907 cells and 6175.42 mm2 of tissue annotated by pathologists, extracted from 400 PD-L1 22C3-stained whole slide images of UC. We validated the AI model on 543 UC PD-L1 22C3 cases collected from three institutions. There were 446 cases (82.1%) where the CPS results (CPS ≥10 or <10) were in complete agreement between three pathologists, and 486 cases (89.5%) where the AI-powered CPS results matched the consensus of two or more pathologists. In the pathologist's assessment of the CPS, statistically significant differences were noted depending on the source hospital (P = 0.003). Three pathologists reevaluated discrepancy cases with AI-powered CPS results. After using the AI as a guide and revising, the complete agreement increased to 93.9%. The AI model contributed to improving the concordance between pathologists across various factors including hospital, specimen type, pathologic T stage, histologic subtypes, and dominant PD-L1-positive cell type. In the revised results, the evaluation discordance among slides from different hospitals was mitigated. CONCLUSION: This study suggests that AI models can help pathologists to reduce discrepancies between pathologists in quantifying immunohistochemistry including PD-L1 22C3 CPS, especially when evaluating data from different institutions, such as in a telepathology setting.

Utility of The Paris System (TPS) for upper urinary tract cytopathology: correlation with histology follow-up and UroVysion fluorescence in situ hybridization (FISH) analysis.

INTRODUCTION: The Paris System (TPS) provides a uniform reporting system of urine cytology based on well-defined cytologic criteria. Due to their rarity, there are limited data on the utility of TPS in upper urinary tract (UUT) lesions and follow-up histology of cases with abnormal cytology. We aimed to evaluate the utility of TPS for UUT lesions by correlating the cytologic diagnoses using TPS criteria with subsequent histology. Additionally, the diagnostic utility of UroVysion (Abbott) fluorescence in situ hybridization (FISH) was assessed. MATERIALS AND METHODS: A total of 148 UUT cytology specimens were retrospectively identified (2018-2022). Cytologic interpretation was performed using TPS, and then correlated with the findings of concurrent or subsequent histologic specimens. The performance of UroVysion FISH was analyzed. Sensitivity and specificity, positive predictive value (PPV) and negative predictive value (NPV) for detecting high-grade urothelial carcinoma (HGUC) were determined. RESULTS: Among 83 patients who had concurrent or subsequent histologic specimens, cyto-histologic discrepancy was seen in 7 cases (8.4%). The sensitivity, specificity, PPV, and NPV using TPS criteria for detecting HGUC were 87%, and 92%, 96.4%, and 73%, respectively. UroVysion FISH was performed in 21 patients with atypical cytologic findings. The sensitivity and specificity of UroVysion for detecting HGUC was 75% and 86%, respectively, while PPV and NPV were 86% and 75%, respectively. CONCLUSIONS: In our experience, the application of TPS criteria for reporting upper urinary cytology was reliable at detecting UUT lesions, especially HGUC. UroVysion FISH was a valuable ancillary test for detecting HGUC of UUT.

Exosomal circRNAs: Novel biomarkers and therapeutic targets for urinary tumors.

Exosomal circRNAs have emerged as promising biomarkers and therapeutic targets for urinary tumors. In this review, we explored the intricate role of exosomal circRNAs in urological cancers, focusing on their biological functions, dysregulation in tumors, and potential clinical applications. The review delves into the mechanisms by which exosomal circRNAs contribute to tumor progression and highlights their diagnostic and therapeutic implications. By synthesizing current research findings, we present a compelling case for the significance of exosomal circRNAs in the context of urinary tumors. Furthermore, the review discusses the challenges and opportunities associated with utilizing exosomal circRNAs as diagnostic tools and targeted therapeutic agents. There is a need for further research to elucidate the specific mechanisms of exosomal circRNA secretion and delivery, as well as to enhance the detection methods for clinical translational applications. Overall, this comprehensive review underscores the pivotal role of exosomal circRNAs in urinary tumors and underscores their potential as valuable biomarkers and therapeutic tools in the management of urological cancers.

The significance of G8 and other geriatric assessments in urologic cancer management: A comprehensive review.

In urologic oncology, which often involves older patients, it is important to consider how to manage their care appropriately. Geriatric assessment (GA) is a method that can address the specific needs of older cancer patients. The GA encompasses various assessment domains, but these domains exhibit variations across the literature. Some of the common items include functional ability, nutrition, comorbidities, cognitive ability, psychosocial disorders, polypharmacy, social and financial support, falls/imbalance, and vision/hearing. Despite the diversity of domains, there is limited consensus on reliable measurement methods. This review discusses the role of GA in managing urologic cancer in unique scenarios, such as those necessitating temporary or permanent urinary catheters or stomas due to urinary diversion. A comprehensive GA is time and human-resource-intensive in real-world clinical practice. Hence, simpler tools such as the Geriatric-8 (G8), capable of identifying high-risk patients requiring a detailed GA, are also under investigation in various contexts. Therefore, we conducted a systematic literature review on the G8. Our findings indicate that patients with low G8 scores encounter difficulties with stoma self-care after urinary diversion and have higher risks of urinary tract infections and ileus after radical cystectomy. The utilization of G8 as a screening tool for urologic cancer patients may facilitate the delivery of appropriate and personalized treatment and care.

Multiple Fluorescences in Situ Hybridization Status in Excreted Urine Improve Diagnostic Efficacy for Upper Urinary Tract Urothelial Carcinomas.

PURPOSE: To evaluate the diagnostic accuracy of single and multiple fluorescence in situ hybridization (FISH) tests for upper urinary tract cancer (UTUC), we analyzed the diagnostic efficacy of FISH in patients with UTUC and the difference between it and the Tumor Node Metastasis (TNM) stage and grade of the tumor. MATERIALS AND METHODS: Patients treated for UTUC at our institution between 2011 and 2021 who had not been previously diagnosed with UTUC were included. Patients were divided into single, two, and multiple (three times or four times) FISH groups based on the number of FISH tests performed on different samples from the same patient, and the diagnostic efficiency of single, two, and multiple FISH tests for muscle-invasive tumors and highgrade tumors were assessed. RESULTS: We included a total of 207 patients with UTUC, and when compared to single FISH, the sensitivity of multiple and double FISH for the diagnosis of UTUC increased from 62% to 76% and 78%, respectively. It went from 67% to 78% and 80% for muscle-invasive UTUC (> = pT2) and from 71% to 79% and 81% for the highest- grade UTUC. CONCLUSION: Multiple FISH improves the diagnostic efficacy of UTUC and helps to differentiate aggressive tumors.

Implementation of The Paris System for Reporting Urine Cytology improves diagnostic accuracy of selective upper urinary tract cytology.

BACKGROUND: The Paris System for Reporting Urine Cytology (TPS) recommends diagnostic criteria for urinary tract cytology, focusing primarily on the detection of high-grade urothelial carcinoma (HGUC) in the lower urinary tract. The second edition of TPS (TPS 2.0), published in 2022, extends these recommendations to the upper urinary tract (UUT); however, there is a lack of comprehensive data on this subject. METHODS: In total, 223 consecutive UUT cytology specimens from 137 patients were retrieved and reclassified according to TPS 2.0 criteria and were compared with the original diagnosis based on the conventional system (CS). Histologic follow-up within a 3-month period was conducted for 43 patients. RESULTS: Histologic follow-up revealed 30 HGUCs, five low-grade urothelial carcinomas (LGUCs), and eight nonneoplastic fibrotic tissues. The risk of high-grade malignancy for each TPS diagnostic category was 16.7% for nondiagnostic/unsatisfactory, 2.3% for negative for HGUC (NHGUC), 42.1% for atypical urothelial cells, 50.0% for suspicious for HGUC (SHGUC), and 81.8% for HGUC. In all five cases of histologically diagnosed LGUC, the cytologic diagnosis was NHGUC. When SHGUC/HGUC was considered positive, the diagnostic accuracy of TPS had 63% sensitivity, 95% specificity, a 90% negative predictive value, and a 79% positive predictive value, which were better than those of CS. In addition, the TPS indices did not differ significantly between the specimens obtained before and after the application of contrast reagents. CONCLUSIONS: TPS implementation improved the accuracy of UUT cytology in predicting histologic HGUC, which was unaffected by the application of contrast reagents. These data indicate the usefulness of TPS for UUT cytology in routine clinical settings.

Predictive and prognostic biomarkers in urological tumours.

Advancements in cutting-edge molecular profiling techniques, such as next-generation sequencing and bioinformatic analytic tools, have allowed researchers to examine tumour biology in detail and stratify patients based on factors linked with clinical outcome and response to therapy. This manuscript highlights the most relevant prognostic and predictive biomarkers in kidney, bladder, prostate and testicular cancers with recognised impact in clinical practice. In bladder and prostate cancer, new genetic acquisitions concerning the biology of tumours have modified the therapeutic scenario and led to the approval of target directed therapies, increasing the quality of patient care. Thus, it has become of paramount importance to choose adequate molecular tests, i.e., FGFR screening for urothelial cancer and BRCA1-2 alterations for prostate cancer, to guide the treatment plan for patients. While no tissue or blood-based biomarkers are currently used in routine clinical practice for renal cell carcinoma and testicular cancers, the field is quickly expanding. In kidney tumours, gene expression signatures might be the key to identify patients who will respond better to immunotherapy or anti-angiogenic drugs. In testicular germ cell tumours, the use of microRNA has outperformed conventional serum biomarkers in the diagnosis of primary tumours, prediction of chemoresistance, follow-up monitoring, and relapse prediction.

The National Health Service urgent cancer referral pathway for suspected urological cancers: early economic evaluation of a risk prediction test.

OBJECTIVES: In the UK, the number of patients urgently referred for suspected cancer is increasing, and providers are struggling to cope with demand. We explore the potential cost-effectiveness of a new risk prediction test - the PinPoint test - to triage and prioritize patients urgently referred with suspected urological cancers. METHODS: Two simulation models were developed to reflect the diagnostic pathways for patients with (i) suspected prostate cancer, and (ii) bladder or kidney cancer, comparing the PinPoint test to current practice. An early economic analysis was conducted from a UK National Health Service (NHS) perspective. The primary outcomes were the percentage of individuals seen within 2 weeks and health care costs. An exploratory analysis was conducted to understand the potential impact of the Pinpoint test on quality-adjusted life years gained. RESULTS: Across both models and applications, the PinPoint test led to more individuals with urological cancer being seen within 2 weeks. Using PinPoint only to prioritize patients led to increased costs overall, whereas using PinPoint to both triage and prioritize patients led to cost savings. The estimated impact on life years gained/lost was very small and highly uncertain. CONCLUSIONS: Using the PinPoint test to prioritize urgent referrals meant that more individuals with urological cancer were seen within 2 weeks, but at additional cost to the NHS. If used as a triage and prioritization tool, the PinPoint test shortens wait times for referred individuals and is cost saving. More data on the impact of short-term delays to diagnosis on health-related quality of life is needed.