Cytologic evaluation of upper urinary tract specimens: An institutional retrospective study using The Paris System for Reporting Urine Cytology second edition with histopathologic follow-up.

OBJECTIVE: Cytologic evaluation of the upper urinary tract (UUT) can be challenging due to instrumentation artefacts. This study retrospectively reviewed UUT specimens using The Paris System for Reporting Urinary Cytopathology, second edition (TPS 2.0), compared it with the original reporting system (ORS) and correlated it with histopathologic follow-up. METHODS: An institutional database was reviewed for the UUT biopsy/resection histopathologic specimens, and we included 52 UUT cytology specimens pertinent to these cases in the study. These specimens were blindly reviewed and reclassified using TPS 2.0. The correlation between TPS 2.0, ORS and histopathologic follow-up was assessed. RESULTS: The UUT cytology specimens corresponded to 21 (40.4%) high-grade urothelial carcinoma (HGUC), 27 (51.9%) low-grade urothelial carcinoma (LGUC) and 4 (7.7%) benign cases on follow-up. For HGGC cases, the associated TPS categories included unsatisfactory (n = 1, 4.8%), negative for HGUC (NHGUC; n = 3, 14.3%), atypical urothelial cells (AUC; n = 6, 28.6%), suspicious for HGUC (SHGUC; n = 3, 14.3%) and HGUC (n = 8, 38.1%), while ORS categorised the specimens as unsatisfactory (n = 1, 4.8%), negative for malignant cells (NFMC; n = 3, 14.3%), AUC (n = 5, 23.8%), low-grade urothelial carcinoma (LGUC; n = 0, 0%), SHGUC (n = 5, 23.8%) and HGUC (n = 7, 33.3%). The risks of high-grade malignancy among cytologic categories were similar between ORS and TPS (p > 0.05). The majority of LGUC were classified as AUC similarly by ORS and TPS (55.6% vs. 59.3%). CONCLUSIONS: Our study demonstrated comparable performance between TPS 2.0 and ORS for UUT cytology specimens. Cytological diagnosis of UUT specimens remains challenging, especially for LGUC.

Urinary tract cytology showing variant morphology and divergent differentiation.

Urothelial carcinoma represents a diverse group of tumours with distinct histologic subtypes, each exhibiting unique cytomorphologic features, architectural growth patterns, and/or well-developed aberrant differentiation. In fact, there are more than 13 subtypes of urothelial carcinoma recognized in the 2022 WHO classification of tumours in the urinary tract. The identification of these subtypes is crucial for an accurate diagnosis of urothelial carcinoma, and many have important clinical implications. Variant/divergent features may coexist with conventional high-grade urothelial carcinoma (HGUC) or present with 100% variant morphology. In urinary tract cytology (UTC), urothelial carcinoma can display divergent differentiation, such as squamous, glandular, or small cell carcinoma differentiation. The use of cell block preparations and immunohistochemistry with available residual urine can enhance diagnostic accuracy. On the other hand, identifying urothelial carcinoma variants, including nested, micropapillary, and plasmacytoid subtypes, poses significant challenges in UTC. Many cases of these variants are only detected retrospectively after variant histology has been established from resection specimens. Moreover, some variants exhibit features inconsistent with the diagnostic criteria for HGUC according to the Paris System for Reporting Urinary Tract Cytology. Nevertheless, the rarity of pure variant morphology and the occurrence of some false negatives for these variant cases are essential to maintain the specificity of UTC overall. This review covers the histology, cytomorphology, and important clinical aspects observed in urothelial carcinoma exhibiting divergent differentiation and various urothelial carcinoma variants detected in UTC.

Impact of implementing the first edition of the Paris system for reporting: A systematic review and meta-analysis.

Urine cytology is a noninvasive, widely used diagnostic tool for screening and surveillance of genitourinary tract neoplasms. However, the absence of unified terminology and clear objective morphological criteria limits the clinical benefit of urine cytology. The Paris System for Reporting Urine Cytology (TPS) was developed with the goal of standardizing reporting and improving urine cytology performance in detecting high-grade malignancy (HGM). We aimed to evaluate potential effects of TPS on improving urine cytology diagnostic performance and clinical utility by conducting a systematic review and meta-analysis. We searched six electronic databases to identify cross-sectional and cohort studies written in English assessing the accuracy of urine cytology in detecting genitourinary tract malignancies of patients under surveillance or with clinical suspicion of malignancy from January 2004 to December 2022. We extracted relevant data from eligible studies to calculate relative distribution of cytology diagnostic categories; ratio of atypical to HGM cytology diagnosis; and risk of HGM (ROHGM) and HGM likelihood ratio (HGM-LR) associated with cytology diagnostic categories. We used a generalized linear mixed model with logit transformation to combine proportions and multilevel mixed-effect logistic regression to pool diagnostic accuracy measurements. We performed meta-regression to evaluate any significant difference between TPS and non-TPS cohorts. We included 64 studies for 99,796 combined total cytology samples, across 31 TPS and 49 non-TPS cohorts. Pooled relative distribution [95% confidence interval (CI)] of negative for high-grade urothelial carcinoma (NHGUC)/negative for malignancy (NM); atypical urothelial cells (AUC); suspicious for high-grade urothelial carcinoma (SHGUC)/suspicious for malignancy (SM); low-grade urothelial neoplasm (LGUN); and HGM categories among satisfactory cytology cases were 83.8% (80.3%-86.9%), 8.0% (6.0%-10.6%), 2.2% (1.4%-3.3%), 0.01% (0.0%-0.1%), and 4.2% (3.2%-5.5%) in TPS versus 80.8% (76.8-2.7%), 11.3% (8.6%-14.7%), 1.8% (1.2%-2.7%), 0.01% (0.0%-0.1%), and 3.3% (2.5%-4.3%) in non-TPS cohorts. Adopting TPS classification resulted in a significant increase in the frequency of NHGUC and a reduction in AUC cytology diagnoses, respectively. The AUC/HGM ratio in TPS cohort was 2.0, which showed a statistically significant difference from the atypical/HGM ratio of 4.1 in non-TPS cohort (p-value: 0.01). Moreover, the summary rate (95% CI) of LGUN called AUC on cytology significantly decreased to 20.8% (14.9%-28.3%) in the TPS compared with 34.1% (26.4%-42.8%) in non-TPS cohorts. The pooled ROHGM (95% CI) was 20.4% (6.2%-50.0%) in nondiagnostic (NDX), 15.5% (9.6%-24.2%) in NHGUC, 40.2% (30.9%-50.2%) in AUC, 80.8% (72.9%-86.8%) in SHGUC, 15.1% (5.7%-34.3%) in LGUN, and 91.4% (87.3%-94.3%) in HGM categories in TPS studies. NHGUC, AUC, SHGUC, and HGM categories were associated with HGM-LR (95% CI) of 0.2 (0.1-0.3), 0.9 (0.6-1.3), 6.9 (2.4-19.9), and 16.8 (8.3-33.8). Our results suggest that TPS 1.0 has reduced the relative frequency of AUC diagnosis, AUC/HGM ratio, and the frequency of LGUNs diagnosed as AUC on cytology. Adopting this classification has improved the clinical utility of SHGUC and HGM cytology diagnoses in ruling in high-grade lesions. However, an NHGUC diagnosis does not reliably rule out the presence of a high-grade lesion.

Nuclear long diameter as a new criterion to distinguish high-grade urothelial carcinoma cells from benign reactive cells.

OBJECTIVE: Recently, the nuclear area has attracted attention as a morphological parameter to differentiate high-grade urothelial carcinoma (HGUC) cells from benign reactive cells. The nuclear long diameter (NLD) strongly correlates with the nuclear area and is easy to subjectively estimate. Therefore, this study examined the usefulness of the NLD-to-neutrophil diameter ratio for detecting HGUC cells in urine cytology. METHODS: This study included 29, 26 and 18 patients with HGUC, glomerular disease and urolithiasis respectively. An image analysis system was used to measure the NLD of HGUC and benign reactive cells (reactive renal tubular cells and reactive urothelial cells) and the neutrophil diameter that appeared in the voided urine in these cases. The NLD index was calculated using the NLD-to-neutrophil diameter ratio. We subsequently compared HGUC and benign reactive cells with respect to NLD and NLD indices. In addition, the HGUC cell group and benign reactive cell group were compared by selecting the five cells with the largest NLD and NLD index on each slide. RESULTS: The NLD and NLD indices of HGUC cells were significantly higher than those of benign reactive cells in all cells and in the five cells with the largest NLD and NLD indices. The cut-off value of the NLD index for detecting HGUC cells was 1.25 in all cells and 1.80 in the five cells with the largest NLD index. CONCLUSIONS: The NLD index is a useful parameter that can be introduced into routine microscopic examinations to differentiate HGUC cells from benign reactive cells.

[The Paris System, 2022 edition: What is new?] / La version 2022 du Système de Paris : quoi de neuf ?

The second version of the Paris System for reporting urine cytology was published in 2022. It follows the first version of 2016, which was very successful and widely adopted by many cytopathologists from different countries. Thus, numerous publications using the Paris System have made possible to refine the criteria as well as discussing the limits. The diagnostic accuracy of urinary cytology is high for detection of high-grade urothelial carcinoma, but not for low-grade carcinoma where there are few cytological abnormalities. So, the chapter individualizing low-grade urothelial neoplasms was deleted; the latter were included in the category "negative for high-grade urothelial carcinoma". Indeed, the risk of malignancy is replaced by the risk of high-grade urothelial carcinoma. A new chapter has been devoted to urothelial tumors of the upper tract. Finally, the pitfalls linked to cellular degeneration are discussed for each category. The risk of high-grade malignancy associated with each category will help communication with the clinician and help patient care.

[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.

The inclusion of nuclear area improves the Paris system for reporting urinary cytology.

OBJECTIVE: The Paris System for Reporting Urinary Cytology (TPS) is a well-known urinary diagnostic model; however, occasional false-positives are a problem. To address this issue, we developed an improved algorithm (IA), based on additional cytological features, for TPS diagnosis. METHODS: Cytological features were evaluated in 29 hard-to-classify cases, including 22 malignant cases and seven benign cases, using image analysis. The optimal IA was determined using the area under the receiver operating characteristic curve as an index. Re-evaluation was performed by applying measured values to the TPS and IA algorithms. RESULTS: Using TPS, 12 of the 22 malignant cases were reassigned to a more appropriate category, and the remaining 10 malignant cases remained hard-to-classify. Two of the seven benign cases were classified as suspicious for high-grade urothelial carcinoma, and the remaining five benign cases remained in the original category. The IA, which included nuclear area as a parameter, showed the same diagnostic sensitivity as TPS, and three of the seven benign cases were reassessed as negative. Thus, the positive and negative predictive values of the IA were higher than those of TPS (84.6% and 100% vs 75.9% and 0%). CONCLUSIONS: The newly developed IA is a practical algorithm with which to address the limitations of TPS and thus may contribute to improved diagnostic accuracy.

The Paris System for reporting urinary cytology improves the negative predictive value of high-grade urothelial carcinoma.

BACKGROUND: The Paris System (TPS) for reporting urinary cytology differs from conventional systems (CS) in that it focuses on the diagnosis of high-grade urothelial carcinoma (HGUC). This study investigated the impact of TPS implementation on the diagnostic accuracy of HGUC by comparing it with our institutional CS. METHODS: A total of 649 patients who underwent transurethral resection of bladder tumor (TURBT) between January 2009 and December 2020 were included in this study. Our institution adopted TPS to report urinary cytology in February 2020. The diagnostic accuracy of HGUC in preoperative urinary cytology was compared with the presence or absence of HGUC in resected specimens of TURBT before and after TPS implementation. RESULTS: After implementing TPS in urinary cytology, 89 patients were reviewed and compared with 560 patients whose urinary cytology was diagnosed by CS. TPS and CS for detecting HGUC had 56.0% and 58.2% sensitivity, 97.8% and 91.2% specificity, and 93.3% and 87.9% positive predictive values, respectively. There were no significant differences between TPS and CS in terms of sensitivity, specificity, and positive predictive value for HGUC (P = 0.83, 0.21, 1.00). On the other hand, the negative predictive value for HGUC using TPS was 80.0%, which was significantly higher than that of CS (66.4%, P = 0.04) The multivariate logistic regression analysis indicated that not using TPS was one of the independent predictive factors associated with false-negative results for HGUC (odds ratio, 2.26; 95% confidence interval, 1.08-4.77; P = 0.03). CONCLUSION: In instances where urinary cytology is reported as negative for HGUC by TPS, there is a low probability of HGUC, indicating that TPS has a potential diagnostic benefit.

Deep learning based digital cell profiles for risk stratification of urine cytology images.

Urine cytology is a test for the detection of high-grade bladder cancer. In clinical practice, the pathologist would manually scan the sample under the microscope to locate atypical and malignant cells. They would assess the morphology of these cells to make a diagnosis. Accurate identification of atypical and malignant cells in urine cytology is a challenging task and is an essential part of identifying different diagnosis with low-risk and high-risk malignancy. Computer-assisted identification of malignancy in urine cytology can be complementary to the clinicians for treatment management and in providing advice for carrying out further tests. In this study, we presented a method for identifying atypical and malignant cells followed by their profiling to predict the risk of diagnosis automatically. For cell detection and classification, we employed two different deep learning-based approaches. Based on the best performing network predictions at the cell level, we identified low-risk and high-risk cases using the count of atypical cells and the total count of atypical and malignant cells. The area under the receiver operating characteristic (ROC) curve shows that a total count of atypical and malignant cells is comparably better at diagnosis as compared to the count of malignant cells only. We obtained area under the ROC curve with the count of malignant cells and the total count of atypical and malignant cells as 0.81 and 0.83, respectively. Our experiments also demonstrate that the digital risk could be a better predictor of the final histopathology-based diagnosis. We also analyzed the variability in annotations at both cell and whole slide image level and also explored the possible inherent rationales behind this variability.

Comparison of conventional and liquid-based cytology using The Paris System for Reporting Urinary Cytology.

BACKGROUND: This retrospective study was conducted to compare the conventional cytospin method and ThinPrep liquid-based urinary cytology in diagnosing bladder cancer using The Paris System (TPS) of classification. METHODS: We retrieved files for 2020, at the Cytopathology Department of Laiko Hospital, of urinary cases diagnosed according to TPS. Cytospin and ThinPrep slides were separately reviewed and new diagnoses were rendered, then compared with the original diagnosis and histology when available. Risk of high-grade malignancy (ROHM) for each TPS category was assessed, along with accuracy parameters of each method and their combination. RESULTS: The study material comprised 100 cases of void urinary cytology classified as 20 high-grade urothelial carcinoma (HGUC = TPS5) cases, 20 of suspicion for HGUC (SHGUC = TPS4), 25 of atypical urothelial cells (AUC = TPS3), and 35 of negative for HGUC (NHGUC = TPS2). A single inadequate (TPS1) case and 4 of low-grade urothelial neoplasm (TPS6) were excluded as small in number. The ROHM was 95% for HGUC, 55% for SHGUC, 28% for AUC and 5.7% for NHGUC. Agreement with the original diagnosis was 86% for cytospin and 82% for ThinPrep. No significant differences were observed among the two techniques or their combination regarding sensitivity and specificity, with a mild advantage for cytospin. Interobserver reproducibility and repeatability were high. CONCLUSION: No significant differences were found concerning sensitivity and specificity between cytospin and ThinPrep when applying TPS criteria. TPS is a reliable classification scheme for either conventional/cytospin or liquid-based cytology, or their combination.

Quantitative cytomorphological comparison of SurePath and ThinPrep liquid-based cytology using high-grade urothelial carcinoma cells.

OBJECTIVE: In The Paris System for Reporting Urinary Cytology (TPS), the important cytomorphological features for diagnosing high-grade urothelial carcinoma (HGUC) are a nuclear-to-cytoplasmic (N:C) ratio exceeding 0.7, hyperchromasia, coarse chromatin, and irregular nuclear borders. However, quantitative cytomorphological assessments of HGUC cells using SurePath slides are rare. Therefore, we evaluated HGUC cells on SurePath slides quantitatively using a digital image analysis system and compared these data with ThinPrep data. METHODS: The same urine samples were divided into two aliquots and used to prepare SurePath and ThinPrep slides. We used ImageJ to measure the N:C ratio, hyperchromasia, and irregular nuclear borders for HGUC cells on SurePath and ThinPrep slides. RESULTS: The total number of analysed HGUC cells on SurePath slides was 981, versus 889 on ThinPrep slides. Hyperchromasia and irregular nuclear borders were significantly more severe on SurePath than on ThinPrep slides. Conversely, the N:C ratio did not differ between the methods. Additionally, HGUC cells with N:C ratios exceeding 0.7 were present on almost all slides for both methods. CONCLUSIONS: Our data indicated the reasonableness of using the N:C ratio as the major criterion for TPS on both SurePath and ThinPrep slides, and an N:C ratio cut-off of 0.7 as suitable for identifying HGUC cells. However, the severity of hyperchromasia and irregular nuclear borders differed between the processing methods.

Urinary cytology and the Paris system for reporting urinary cytology: Implications for urological management.

By reducing the rate of indeterminate (atypical) diagnoses and standardising reporting terminology, The Paris System for Reporting Urine Cytology helps focus the application of cytology towards the detection primarily of high-grade urothelial carcinoma. We present a urology-based perspective of how the new system has influenced clinical decision-making.

Cytohistological correlation of urine cytology in a tertiary centre with application of the Paris system.

OBJECTIVES: Urine cytology has a high sensitivity in morphological recognition of high-grade urothelial carcinoma (HGUC) as compared to low-grade urothelial neoplasms. The Paris system (TPS) was designed to standardise the reporting of HGUC on urine cytology. We evaluated the diagnostic efficacy of urine cytology in routine practice with the cytohistological correlation and application of TPS. METHODS: A retrospective review of urine cytology reported from 2014 to 2015 was carried out with cytohistological correlation, wherever available. The cases were also recategorised according to TPS with the calculation of malignancy risk of all categories. RESULTS: More than 4000 specimens from 1396 patients were evaluated. Histopathology was available in 244 cases. Urine cytology had a sensitivity of 70.5%, specificity of 78.4%, with an overall diagnostic accuracy of 71.7%. The urine cytology when categorised by TPS had 0.9% unsatisfactory cases, 75.9% negative for HGUC, 8.5% atypical urothelial cells, 0.2% suspicious for HGUC, 14.1% HGUC and 0.4% cases of other malignancies. The risk of HGUC with each category of negative for HGUC, atypical, suspicious for HGUC, HGUC and other malignancy was 11.6%, 12.3%, 33.3%, 58.8% and 80%, respectively. CONCLUSION: Urine cytology continues to show high diagnostic accuracy for the detection of urothelial carcinoma with a relatively high sensitivity for HGUC. TPS for reporting urine cytology defines specific criteria for diagnosing atypical and HGUC but increases the cases in the atypical category.

The Paris System for urine cytology in upper tract urothelial specimens: A comparative analysis with biopsy and surgical resection.

INTRODUCTION: The Paris System (TPS) has recently been used in classification of urinary tract cytological specimens. Upper urinary tract (UUT) specimens are cytologically challenging. The utility of TPS was investigated in evaluating UUT specimens and its correlation with subsequent histological follow-up. METHOD: From 2014 to 2017, 324 cytology cases of UUT from 179 patients were retrieved. Concurrent or subsequent biopsy or resection within a 2-month period was available in 125 cases from 74 patients. RESULT: None of the cases with a cytology of low-grade urothelial neoplasm was found to have a high-grade urothelial carcinoma (HGUC) on biopsy. Among the 19 atypical urothelial cells (AUC) cytology cases, the histology is heterogeneous (seven benign, one atypia, five low-grade lesion, and six HGUC). The risk of HGUC for each cytological diagnostic category are 0% for non-diagnostic/unsatisfactory, 6% for negative for HGUC, 27.3% for AUC, 0% for low-grade urothelial neoplasm, 48% for suspicious for HGUC and 95% for positive HGUC. When we considered cytology cases with suspicious or positive for HGUC interpretations as positive, the performance of TPS in predicting high grade urothelial carcinoma on histology had values of: 78.6% sensitivity, 86% specificity, 80.5% positive predictive value and 84.5% negative predictive value. CONCLUSION: More than one-third of the UUT cytological cases were classified as AUC and approximately 1/15 as suspicious or positive for HGUC. Based on UUT cytology specimens, the risk of malignancy of each cytological diagnostic category of TPS was comparable to those reported in the literature. The use of TPS in evaluating UUT cytology specimens was specific and sensitive in identifying patients with HGUC by histology.

Application of The Paris System to atypical urine cytology samples: correlation with histology and UroVysion® FISH.

OBJECTIVES: To evaluate whether atypical urine cytology cases may be stratified more objectively using The Paris System (TPS) and whether reclassified cases correlate with histology and UroVysion® results. METHODS: Atypical urine cytology cases subjected to UroVysion® testing over a period of 6 years were reviewed. Each case was reclassified according to TPS and correlated with histology and UroVysion® results. RESULTS: A total of 91 cases were identified; 70.3% were reclassified as 'negative for high-grade urothelial carcinoma (HGUC)' and 14.3% as 'atypical urothelial cells (AUC)'. The histological correlation was available in 45 cases. In the 'negative for HGUC' category, 67.9% had no histological evidence of malignancy, but 17.9% were diagnosed as HGUC. In the 'AUC' category, histology revealed urothelial carcinoma in 70% of the cases (of these, 71.4% were high grade). There was no histological evidence of malignancy in 30% of cases; notably, all of which were from patients under surveillance. The sensitivity and specificity of UroVysion® were 85.7% and 33.3% in the 'AUC' group and 62.5% and 100% in the 'negative for HGUC' group. CONCLUSIONS: The Paris System is an objective template for reporting urine cytology specimens, and is particularly useful in identifying HGUC cases and refining the category of 'AUC'.

An institutional experience with The Paris System: A paradigm shift from ambiguous terminology to more objective criteria for reporting urine cytology.

BACKGROUND: Urine cytology is a highly specific modality for diagnosing high-grade urothelial carcinoma (HGUC), but plagued by low sensitivity and wide inter-observer variability mainly ascribed to the lack of an established template of reporting. The Paris System (TPS) working group proposed such a template at the 2013 International Congress of Cytology, replete with objective criteria for categorising specimens into one of the seven categories: non-diagnostic, negative for HGUC, atypical urothelial cells, suspicious for HGUC, HGUC, low-grade urothelial neoplasm and others (including non-malignant entities). This study was undertaken to determine the impact of TPS criteria in the morphological interpretation of urine samples. METHODS: A total of 255 voided urine specimens from 97 patients who had follow-up biopsies were re-assessed according to TPS criteria and correlated with the final histological diagnosis. RESULTS: Sixty-three patients were diagnosed with HGUC, and 34 had low-grade papillary UC on biopsy. Earlier samples from 40 (41.2%) patients were categorised as merely "atypical" wheereas the "positive for malignancy" category was assigned to 33 (34%) patients. After re-evaluation of the same cases using TPS criteria, cytological features in 44 (69.8%) out of 63 HGUC patients were correctly recognised as HGUC and samples from additional seven patients were re-categorised as suspicious for HGUC (total 81%). The sensitivity of the HGUC category in predicting HGUC was 69.8% which rose to 81% when HGUC was grouped with suspicious for HGUC category. CONCLUSION: The criteria outlined by TPS facilitated the standardisation of urine cytology reporting and significantly increased the sensitivity of diagnosing HGUC.

Reproducibility of the Paris System in Urine Cytology by Third-Year Pathology Residents.

INTRODUCTION: Standardized basic morphology and the algorithmic approach make the Paris System (TPS) for Reporting Urinary Cytology understandable and applicable. This study examined how well the TPS categories are understood by pathology residents and how well these criteria are enabling them reaching accurate diagnosis. MATERIALS/METHODS: A hundred consecutive cases representing all categories were selected. Authors reevaluated slides using TPS regardless of their original diagnosis. In the next step, the TPS was explained to four residents and trained them by five optimal urine cytology samples from each category. Then they were asked to diagnose the selected slides according to the TPS. The diagnoses were compared to authors. The agreement was assessed using kappa. Discordant diagnoses were classified as high and low impact based on potential on clinical practice. RESULTS: The sensitivity of authors was 62.8%, and residents' were 24-31.8%. The specificity of authors was 98.8%, and residents' were 82.3-92.8%. Reproducibility of TPS was 40-46%. Kappa values were below 0.40 except for one resident. The highest rate of concordance was for negative for high-grade urothelial carcinoma (NHGUC): authors assigned 38 NHGUC (35 biopsy-proven benign cases). Twenty to twenty-six of them were assigned as NHGUC by residents. While authors assigned 42 cases as suspicious for high-grade urothelial carcinoma (SHGUC) or high-grade urothelial carcinoma (HGUC) (35 biopsy-proven malignant cases), residents assigned 22-29 of them. Discordant diagnosis with high clinical implication was 56-63%. CONCLUSION: Diagnostic accuracy rates of junior pathology residents using the TPS were unsatisfactory. The best agreement was observed in NHGUC and HGUC categories. Combining HGUC and SHGUC doubled the sensitivity of residents.

A Fully Automated Artificial Intelligence System to Assist Pathologists' Diagnosis to Predict Histologically High-grade Urothelial Carcinoma from Digitized Urine Cytology Slides Using Deep Learning.

BACKGROUND: Urine cytology, although a useful screening method for urothelial carcinoma, lacks sensitivity. As an emerging technology, artificial intelligence (AI) improved image analysis accuracy significantly. OBJECTIVE: To develop a fully automated AI system to assist pathologists in the histological prediction of high-grade urothelial carcinoma (HGUC) from digitized urine cytology slides. DESIGN, SETTING, AND PARTICIPANTS: We digitized 535 consecutive urine cytology slides for AI use. Among these slides, 181 were used for AI development, 39 were used as AI test data to identify HGUC by cell-level classification, and 315 were used as AI test data for slide-level classification. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Out of the 315 slides, 171 were collected immediately prior to bladder biopsy or transurethral resection of bladder tumor, and then outcomes were compared with the histological presence of HGUC in the surgical specimen. The primary aim was to compare AI prediction of the histological presence of HGUC with the pathologist's histological diagnosis of HGUC. Secondary aims were to compare the time required for AI evaluation and concordance between the AI's classification and pathologist's cytology diagnosis. RESULTS AND LIMITATIONS: The AI capability for predicting the histological presence of HGUC was 0.78 for the area under the curve. Comparing the AI predictive performance with pathologists' diagnosis, the AI sensitivity of 63% for histological HGUC prediction was superior to a pathologists' cytology sensitivity of 46% (p = 0.0037). On the contrary, there was no significant difference between the AI specificity of 83% and pathologists' specificity of 89% (p = 0.13), and AI accuracy of 74% and pathologists' accuracy of 68% (p = 0.08). The time required for AI evaluation was 139 s. With respect to the concordance between the AI prediction and pathologist's cytology diagnosis, the accuracy was 86%. Agreements with positive and negative findings were 92% and 84%, respectively. CONCLUSIONS: We developed a fully automated AI system to assist pathologists' histological diagnosis of HGUC using digitized slides. This AI system showed significantly higher sensitivity than a board-certified cytopathologist and may assist pathologists in making urine cytology diagnoses, reducing their workload. PATIENT SUMMARY: In this study, we present a deep learning-based artificial intelligence (AI) system that classifies urine cytology slides according to the Paris system. An automated AI system was developed and validated with 535 consecutive urine cytology slides. The AI predicted histological high-grade urothelial carcinoma from digitized urine cytology slides with superior sensitivity than pathologists, while maintaining comparable specificity and accuracy.

Urinary Tract Cytopathology: Current and Future Impact on Patient Care.

Urine cytology is a non-invasive, cost-efficient, and sensitive test to detect high-grade urothelial carcinoma. The Paris System (TPS) for Reporting Urinary Cytology is an evidence-based system that uses the risk of malignancy to guide patient management. Since its inception, TPS has standardized urine cytology reports, facilitating communication among pathologists and between pathologists and clinicians. It is imperative to correlate the urine cytology findings with the concurrent tissue sample to avoid false-negative and false-positive results when possible. Several ancillary tests and artificial intelligence algorithms are being developed to increase the accuracy of urine cytology interpretation.

Utility of the Paris System in Urine Cytology for Improved Screening of High-Grade Urothelial Carcinoma in Bahrain.

BACKGROUND: Urothelial carcinoma, a prevalent and aggressive urological malignancy, necessitates early detection for improved prognosis. Urine cytology serves as a cost-effective screening tool, but inconsistencies in reporting due to the lack of standardized criteria limit its efficacy. The Paris System for reporting urinary cytology (TPS) was introduced to address this issue, aiming to improve diagnostic accuracy. This retrospective study investigates the effectiveness of urine cytology in detecting high-grade urothelial carcinoma (HGUC) using TPS classification, specifically focusing on atypical urothelial cells (AUC) categorized as TPS-III and suspicious for high-grade urothelial carcinoma (SHGUC) categorized as TPS-IV. METHODS: We reviewed 470 urine cytology samples collected over two years at a tertiary healthcare center in Bahrain. All samples were re-evaluated using TPS classification by two independent consultant cytopathologists blinded to the original cytology report. The analysis included only samples categorized as TPS-III or TPS-IV with corresponding histopathology reports from confirmatory biopsies performed within four months of urine collection. Biopsy results were categorized as either benign/low-grade urothelial carcinoma (non-HGUC) or malignant (HGUC). The positive predictive value (PPV) of urine cytology for HGUC detection was calculated for both TPS-III and TPS-IV categories. Statistical significance was assessed using Fisher's exact test. RESULTS: Among the 470 urine cytology samples, 40 (8.5%) were classified as TPS-III or TPS-IV. Within this subset, 16 patients underwent confirmatory biopsies. Histopathological analysis revealed HGUC in 12 (75%) patients and non-HGUC (benign or low-grade) in 4 (25%) patients. The PPV of TPS-III for HGUC was 50%, while TPS-IV demonstrated a higher PPV of 90%. However, the difference between these values was not statistically significant (p = 0.25). This study explored the utility of TPS classification in urine cytology for HGUC detection. While SHGUC (TPS-IV) exhibited a numerically higher PPV compared to AUC (TPS-III), the lack of statistical significance necessitates further investigation. Our findings highlight the potential of TPS to improve the accuracy of urine cytology. TPS implementation has been shown to reduce the number of inconclusive "atypical" diagnoses, leading to more targeted investigations. CONCLUSION: Our study suggests that SHGUC (TPS-IV) within TPS classification framework might hold promise as a more specific indicator for HGUC compared to AUC (TPS-III). However, further research with larger cohorts is necessary to definitively establish the clinical significance of this observation. This investigation paves the way for future studies exploring the potential of TPS, particularly the SHGUC category, as a reliable screening tool for HGUC, potentially leading to earlier diagnoses and improved patient outcomes.