[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.

Alix-normalized exosomal programmed death-ligand 1 analysis in urine enables precision monitoring of urothelial cancer.

Anti-programmed death-ligand 1 (PD-L1) Ab-based therapies have demonstrated potential for treating metastatic urothelial cancer with high PD-L1 expression. Urinary exosomes are promising biomarkers for liquid biopsy, but urine's high variability requires normalization for accurate analysis. This study proposes using the PD-L1/Alix ratio to normalize exosomal PD-L1 signal intensity with Alix, an internal exosomal protein less susceptible to heterogeneity concerns than surface protein markers. Extracellular vesicles were isolated using ExoDisc and characterized using various methods, including ExoView to analyze tetraspanins, PD-L1, and Alix on individual exosomes. On-disc ELISA was used to evaluate PD-L1 and Alix-normalized PD-L1 in 15 urothelial cancer patients during the initial treatment cycle with Tecentriq. Results showed that Alix signal range was relatively uniform, whereas tetraspanin marker intensity varied for individual exosome particles. On-disc ELISA was more reliable for detecting exosomal PD-L1 expression than standard plate ELISA-based measurement. Using exosomal Alix expression for normalization is a more reliable approach than conventional methods for monitoring patient status. Overall, the study provides a practical and reliable method for detecting exosomal PD-L1 in urine samples from patients with urothelial cancer.

[Application and evaluation of artificial intelligence TPS-assisted cytologic screening system in urine exfoliative cytology].

Objective: To explore the application of manual screening collaborated with the Artificial Intelligence TPS-Assisted Cytologic Screening System in urinary exfoliative cytology and its clinical values. Methods: A total of 3 033 urine exfoliated cytology samples were collected at the Henan People's Hospital, Capital Medical University, Beijing, China. Liquid-based thin-layer cytology was prepared. The slides were manually read under the microscope and digitally presented using a scanner. The intelligent identification and analysis were carried out using an artificial intelligence TPS assisted screening system. The Paris Report Classification System of Urinary Exfoliated Cytology 2022 was used as the evaluation standard. Atypical urothelial cells and even higher grade lesions were considered as positive when evaluating the recognition sensitivity, specificity, and diagnostic accuracy of artificial intelligence-assisted screening systems and human-machine collaborative cytologic screening methods in urine exfoliative cytology. Among the collected cases, there were also 1 100 pathological tissue controls. Results: The accuracy, sensitivity and specificity of the AI-assisted cytologic screening system were 77.18%, 90.79% and 69.49%; those of human-machine coordination method were 92.89%, 99.63% and 89.09%, respectively. Compared with the histopathological results, the accuracy, sensitivity and specificity of manual reading were 79.82%, 74.20% and 95.80%, respectively, while those of AI-assisted cytologic screening system were 93.45%, 93.73% and 92.66%, respectively. The accuracy, sensitivity and specificity of human-machine coordination method were 95.36%, 95.21% and 95.80%, respectively. Both cytological and histological controls showed that human-machine coordination review method had higher diagnostic accuracy and sensitivity, and lower false negative rates. Conclusions: The artificial intelligence TPS assisted cytologic screening system has achieved acceptable accuracy in urine exfoliation cytologic screening. The combination of manual screening and artificial intelligence TPS assisted screening system can effectively improve the sensitivity and accuracy of cytologic screening and reduce the risk of misdiagnosis.

Are we on track for diagnosing high-grade urothelial carcinoma with a minimum quantity of five malignant cells in lower tract specimens? Critical analysis of The Paris System Quantitation Criteria.

BACKGROUND: The Paris System for Reporting Urinary Cytology (TPS) has gained universal acceptance as the standard for reporting urine cytology requiring at least 5-10 malignant cells to diagnose high-grade urothelial carcinoma (HGUC) in lower and upper urinary tract specimens, respectively. These quantitation criteria are still subject to discussion, and this study specifically aims to validate the quantitation criterion of HGUC in lower urinary tract. DESIGN: The authors reviewed two cohorts of lower urinary tract cases. The first cohort consisted of 100 liquid-based ThinPrep slides with the diagnosis of HGUC having positive histology on concurrent or follow-up biopsies within 3 months. The second cohort was 36 HGUC cases with negative histology on concurrent biopsies and within 3 months. The number of high-grade cells (HGCs) meeting the TPS qualitative criteria were counted under the light microscope driven in a grid-like manner. RESULTS: The first 100 urine samples showed five cases (5.0%) with three HGCs, three cases (3.0%) had four HGCs, five cases (5.0%) showed five HGCs, and 25 cases (25.0%) had between 6-10 HGCs. The risk of high-grade malignancy (ROHM) in cases with five or more HGCs was 100%, whereas those with three HGCs was 60.0%. The second cohort of HGUC was considered "positive" despite a negative histology. CONCLUSION: This study confirms that quantitation is an essential key to diagnose HGUC. The current TPS criterion of a minimum of five malignant cells in lower tract is robust with a ROHM of 100%. Diagnosing HGUC with less than five HGCs runs the risk of lowering the ROHM.

Atypical urothelial cells classified according to the Paris System for Reporting Urinary Cytology: A 2-year experience with histological correlation from a Finnish tertiary care center-low rate and high risk of malignancy.

BACKGROUND: The Paris System for Reporting Urinary Cytology (TPS) was issued to shift the focus of urine cytology to high-grade lesions to increase the diagnostic accuracy of urine cytology. The aim of this study was to evaluate the power of TPS in the atypical urothelial cells (AUC) category with histological correlation and follow-up. METHODS: The data cohort consisted of 3741 voided urine samples collected during a 2-year period between January 2017 and December 2018. All samples were prospectively classified using TPS. This study focuses on the subset of 205 samples (5.5%) classified as AUC. All cytological and histological follow-up data were analyzed until 2019, and the time between each sampling was documented. RESULTS: Of the 205 AUC cases, cytohistological correlation was possible in 97 (47.3%) cases. Of these, 36 (12.7%) were benign in histology, 27 (13.2%) were low-grade urothelial carcinomas, and 34 (16.6%) were high-grade urothelial carcinomas. Overall, the risk of malignancy was 29.8% for all cases in the AUC category, and 62.9% in the histologically confirmed cases. The risk of high-grade malignancy was 16.6% in all the AUC category samples and 35.1% in the histological follow-up group. CONCLUSIONS: The performance of 5.5% AUC cases is considered good and within the limits proposed by TPS. TPS is widely accepted by cytotechnologists, cytopathologists, and clinicians; it improves communication and patient management.

Evaluation of the Implementation and Diagnostic Accuracy of the Paris Classification for Reporting Urinary Cytology in Voided Urine Specimens: A Cyto-Histological Correlation Study in a Cancer Center.

INTRODUCTION: The Paris classification highlights the need to focus on accurately identifying high-grade urothelial carcinoma (HGUC). Herein, we aimed to assess the overall implementation and diagnostic performance of the Paris classification for reporting urinary cytology in a cancer center. METHODS: All urinary cytology reports from July 2018 to December 2019 were collected (n = 1,240). Only voided urine samples were included (n = 1,180). Risk of high-grade malignancy (ROHM) was calculated for each Paris category. The diagnostic performance of urinary cytology was assessed, including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy. RESULTS: The distribution of categories was: 0.3% unsatisfactory, 90.5% negative for HGUC, 5.6% atypical urothelial cells (AUC), 1.6% suspicious for HGUC, 1.9% HGUC, and 0.1% other malignancies. No diagnosis of low-grade urothelial neoplasia was given. The ROHM was 21.4% for negative for HGUC, 66.7% for AUC, 91.7% for suspicious for HGUC, and 100% for HGUC. When using suspicious for HGUC as a cutoff, the diagnostic performance of urinary cytology in identifying HGUC histology was 46% sensitivity, 98% specificity, 96% PPV, 68% NPV, and 74% accuracy. CONCLUSION: Specificity of urinary cytology was very high (with only 1 false-positive result), which is important since this will trigger a clinical intervention. The ROHM for each category was in accordance with literature, except for AUC where ROHM was slightly higher (66.7%). This may be explained by the study population characteristics (cancer center; many patients treated with intravesical therapies; lack of clinical annotation for patients referred from outside institutions).

Application and evaluation of artificial intelligence TPS-assisted cytologic screening system in urine exfoliative cytology / 中华病理学杂志

Objective: To explore the application of manual screening collaborated with the Artificial Intelligence TPS-Assisted Cytologic Screening System in urinary exfoliative cytology and its clinical values. Methods: A total of 3 033 urine exfoliated cytology samples were collected at the Henan People's Hospital, Capital Medical University, Beijing, China. Liquid-based thin-layer cytology was prepared. The slides were manually read under the microscope and digitally presented using a scanner. The intelligent identification and analysis were carried out using an artificial intelligence TPS assisted screening system. The Paris Report Classification System of Urinary Exfoliated Cytology 2022 was used as the evaluation standard. Atypical urothelial cells and even higher grade lesions were considered as positive when evaluating the recognition sensitivity, specificity, and diagnostic accuracy of artificial intelligence-assisted screening systems and human-machine collaborative cytologic screening methods in urine exfoliative cytology. Among the collected cases, there were also 1 100 pathological tissue controls. Results: The accuracy, sensitivity and specificity of the AI-assisted cytologic screening system were 77.18%, 90.79% and 69.49%; those of human-machine coordination method were 92.89%, 99.63% and 89.09%, respectively. Compared with the histopathological results, the accuracy, sensitivity and specificity of manual reading were 79.82%, 74.20% and 95.80%, respectively, while those of AI-assisted cytologic screening system were 93.45%, 93.73% and 92.66%, respectively. The accuracy, sensitivity and specificity of human-machine coordination method were 95.36%, 95.21% and 95.80%, respectively. Both cytological and histological controls showed that human-machine coordination review method had higher diagnostic accuracy and sensitivity, and lower false negative rates. Conclusions: The artificial intelligence TPS assisted cytologic screening system has achieved acceptable accuracy in urine exfoliation cytologic screening. The combination of manual screening and artificial intelligence TPS assisted screening system can effectively improve the sensitivity and accuracy of cytologic screening and reduce the risk of misdiagnosis.

Digital image analysis of high-grade urothelial carcinoma in urine cytology confirms chromasia heterogeneity and reveals a subset with hypochromatic nuclei and another with extremely dark or "India ink" nuclei.

BACKGROUND: The Paris System for Reporting Urinary Cytology (TPS) uses hyperchromasia as major diagnostic criterion for high-grade urothelial carcinoma (HGUC). The purpose of the study was to evaluate cases that were diagnosed as HGUC by TPS and determine whether there are different chromatin distribution patterns (ie, subsets). METHODS: Digital image annotations were performed on microscopic images of HGUC urine specimens with surgical biopsy/resection follow-up. Median gray values were generated for each cell. Neutrophils (polymorphonuclear leukocyte [PMN]) were also enumerated in each case to serve as an internal control. A HGUC/PMN ratio was generated for each case, and the cases were distributed. RESULTS: Sixty-nine HGUC cases yielded 2660 cells, including 2078 HGUC (30.1 cells/case) and 582 PMNs (8.4 cells/case). The average median gray value of an HGUC was 50.6 and of a PMN was 36.8 (P < .0001). Eight of 69 cases (11.6%) contained nuclei that, on average, were darker than or as dark as a PMN (extremely dark, ie, "India ink"). Fifty-one of 69 cases (74.0%) contained nuclei that, on average, were slightly brighter than a PMN (hyperchromatic). Ten of 69 cases (14.5%) contained nuclei that, on average, were much brighter than a PMN (hypochromatic). Within a single case, all cases showed heterogeneity with the hypochromatic cases showing the most dramatic effect. CONCLUSIONS: Digital image analysis reveals that there are large variations in chromasia between cases including a subset of cases with hypochromasia and another with extremely dark or "India ink" nuclei. There was much heterogeneity of chromasia seen within a single sample.

Upper urothelial tract high-grade carcinoma: comparison of urine cytology and DNA methylation analysis in urinary samples.

Numerous studies showed that bladder urothelial carcinoma and upper urothelial tract carcinoma (UTUC) display clinical and genomic similarities. In order to analyze that the same panel of biomarkers used in the diagnosis of bladder urothelial carcinoma could be suitable for early detection of UTUC, we performed a retrospective study in which we analyzed Bladder EpiCheck scores in the urinary samples obtained by selective ureteral catheterization in a high-grade UTUC cohort, correlating the results with urinary cytology and diagnostic urethral biopsies. The present study represents a retrospective analysis of 82 patients with clinically localized high-grade UTUC (60 renal pelvis UTUC, 22 ureter UTUC) who had undergone a radical nephroureterectomy (RNU) at our Urology department from June 2018 to November 2020. Before any surgical procedure, one sample of urine, obtained by selective ureteral catheterization, was collected for each patient for cytological examination, and the remaining material was stored for the Bladder EpiCheck test. Our results showed that the sensitivity of the methylation test for high-grade UTUC was about 97.4%, significantly higher than the sensitivity of urinary cytology either considering the HGUC cytological diagnosis or including in the positive cases the SHGUC cytological diagnosis (97.4% versus 59% or 70.5%). The methylation analysis of urinary samples may represent a valid tool in the diagnostic process of patients with suspected UTUC. In cases with a difficult clinical decision after upper urinary tract biopsy and cytology, the methylation test could assist in the clinical management of UTUC patients.

Urinary Metabolic Biomarkers in Cancer Patients: An Overview.

The pathogenesis of cancer involves multiple molecular alterations at the level of genome, epigenome, and stromal environment, resulting in several deregulated signal transduction pathways. Metabolites are not only end products of gene and protein expression but also a consequence of the mutual relationship between the genome and the internal environment. Considering that metabolites serve as a comprehensive chemical fingerprint of cell metabolism, metabolomics is emerging as the method able to discover metabolite biomarkers that can be developed for early cancer detection, prognosis, and response to treatment. Urine represents a noninvasive source, available and rich in metabolites, useful for cancer diagnosis, prognosis, and treatment monitoring. In this chapter, we reported the main published evidences on urinary metabolic biomarkers in the studied cancers related to hepatopancreatic and urinary tract with the aim at discussing their promising role in clinical practice.

A review of urinary cytology in the setting of upper tract urothelial carcinoma.

Urothelial carcinomas of the upper urinary tract (UUT) are uncommon. Cytological examination of voided urine or washings from the UUT has been part of the standard workup for upper tract urothelial carcinoma (UTUC); however, its value remains controversial. The lack of uniform terminology and specific diagnostic criteria could also have contributed to the inferior performance of urinary cytology for detecting UTUC. The Paris System for Reporting Urinary Cytology (TPS) has provided a standardized reporting system for urinary cytology specimens with clearly defined cytomorphologic diagnostic criteria and found acceptance on an international level after its implementation in 2016. Recent studies have shown that TPS has led to improved diagnostic performance of urinary cytology; however, most of these studies had focused on the evaluation of lower urinary tract cytology specimens. Only a limited number of new research studies have analyzed the effect of TPS when applied to UUT cytology specimens. In the present report, we have summarized the current understanding and utility of UTUC, including its molecular biology, and reviewed the current literature.

Targeted education as a method for reinforcing Paris System criteria and reducing urine cytology atypia rates.

INTRODUCTION: The Paris System for Urine Cytology (TPS) provides well-defined diagnostic criteria for the category of atypical urothelial cells (AUC). The current study compares the rate of AUC diagnoses at a large academic medical center before and after an educational intervention (EI) by a urine cytology expert. MATERIALS AND METHODS: An expert in TPS delivered an educational intervention consisting of an interactive microscope session and a didactic session that focused on the AUC diagnostic category. The number of urine cytology cases, the AUC rate, and the false-negative percentage were calculated before and after the EI, using the electronic medical records and cytologic-histologic correlation records. RESULTS: A total of 4026 urine cytology cases were signed out in the 25 months prior to the educational intervention and 1585 cases were signed out in the 10 months after the intervention. EI had a significant impact on diagnostic categorization, including a reduction in AUC (19.6% versus 12.5%) and suspicious for high-grade urothelial carcinoma (3.9% versus 3.1%) diagnoses. The cytotechnologists also placed fewer cases into the AUC category during primary screening (27.6% versus 23.0%). Although a higher percentage of cases was reported as negative for high-grade urothelial carcinoma, the false-negative rate did not significantly change after the intervention (1.8% versus 2.0% of negative cases, P = 0.65). CONCLUSIONS: Focused educational sessions for pathologists and cytotechnologists on the diagnostic criteria for AUC as defined by TPS can significantly reduce the rate of atypical diagnoses without a significant increase in the rate of false negatives.

Evidence-based diagnostic accuracy measurement in urine cytology using likelihood ratios.

INTRODUCTION: Recent cytology classification systems have become more evidence-based and advocate for the use of risk of malignancy (ROM) as a measure of test performance. From the statistical viewpoint, ROM represents the post-test probability of malignancy, which changes with the test result and also with the prevalence of malignancies (or pre-test probability) in each individual practice setting and individual patient presentation. Evidence-based medicine offers likelihood ratios (LRs) as a measure of diagnostic accuracy for multilevel diagnostic tests, superior to sensitivity and specificity as data binarization and information loss are avoided. LRs are used in clinical medicine and could be successfully applied to the practice of cytopathology. Our aim was to establish LRs to compare diagnostic accuracy of The Paris System for Reporting Urinary Cytology (TPS) and of a historic urine cytology reporting system. MATERIALS AND METHODS: We analyzed sequential voided urine cytology cases with histologic outcomes: 188 pre-TPS and 167 post-TPS. LRs were calculated as LR = True positive % (per category)/False positive % (per category) [95% confidence interval] and interpreted LRs = 1 nondiagnostic, LR >1 favor, LR >10 strongly favor, LRs <1 favor exclusion, and LR <0.1 strongly favor exclusion of a target condition, respectively. CATmaker open source software and Fagan nomograms were used for calculation and visualization of the corresponding post-test probability (ROM) of high-grade urothelial carcinoma (HGUC) in various scenarios. RESULTS: Both reporting systems show near-similar performance in terms of LRs, with moderate discriminatory power of negative, suspicious, and positive for HGUC test results. The atypical urothelial cell (AUC) category establishes as indiscriminate LR = 1 in the TPS, whereas in pre-TPS it favored a benign condition. We further demonstrate the utility of LRs to determine individual post-test probability (ROM) in a variety of clinical scenarios in a personalized fashion. CONCLUSIONS: The LRs allow for a quantitative performance measure in case of urine cytology across different scenarios adding numeric information on diagnostic test accuracy and post-test probability of HGUC. The diagnostic accuracy of pre-TPS and post-TPS remained similar for all but the AUC category. With the TPS, the AUC category has become genuinely diagnostically and statistically indeterminate and requires further patient investigations.

High-grade urothelial carcinoma in urine cytology: different spaces - different faces, highlighting morphologic variance.

INTRODUCTION: The Paris System for Reporting Urinary Cytology (TPS) was first published in 2016 to standardize reporting and placed a specific emphasis on high-grade urothelial carcinoma (HGUC). The urinary tract is anatomically divided into the upper tract (UT) and the lower tract (LT). A major morphologic criterion in TPS for HGUC defines the nuclear-to-cytoplasmic (N/C) ratio as ≥ 0.7. In this study, we evaluated N/C ratios of HGUC arising from UT and LT urine specimens, to ascertain differences due to location. MATERIALS AND METHODS: Digital annotations of whole slide scanned images were performed and enumerated. RESULTS: The cohort consisted of 59 ThinPrep specimens from 52 patients. The majority of the tumors were located in LT (39 of 59, 66.1%). A total of 590 cells were analyzed (10 cells per case). In UT, the average N/C was 0.58 and LT the average was 0.54 (P < 0.001). The average nuclear area for UT was 126.3 and for LT was 158.2 µm2 (P = 0.01). The average cytoplasmic area for UT was 219.1 µm2 and for LT was 296.2 µm2 (P < 0.001). The average cellular circumference for UT was 59.4 µm and for LT was 66.1 µm (P < 0.001). CONCLUSIONS: We found that UT HGUCs have higher N/C ratios, smaller cell circumference, smaller nuclei, and less cytoplasm compared with LT. When UT was divided into renal pelvis and ureter, no statistical difference was identified.

An institutional experience evaluating hTERT immunostaining in 100 consecutive ThinPrep urine specimens.

INTRODUCTION: Studies have shown that expression of human telomerase reverse transcriptase (hTERT) in mature urothelial cells indicates an increased risk of urothelial carcinoma. We evaluated the utility of immunocytochemistry with a commercially available anti-hTERT antibody (SCD-A7) in 100 consecutive urine cytology specimens using ThinPrep processing. MATERIALS AND METHODS: ThinPrep slides prepared from 100 consecutive urine specimens were stained using anti-hTERT antibody (SCD-A7) after staining optimization had been successfully completed. Patient demographics, cytology diagnoses, histologic follow-up data, and anti-hTERT staining results were recorded. RESULTS: The cytology diagnoses included 7 cases of high-grade urothelial carcinoma (HGUC), 2 cases suspicious for HGUC (SHGUC), 24 cases of atypical urothelial cells (AUCs), and 67 cases negative for HGUC (NHGUC). Of 92 samples, 68 (74%) were positive and 24 (26%) were negative for anti-hTERT staining. Although 31 of 32 specimens (97%) with a diagnosis of AUCs and greater showed positive staining, 37 of 60 NHGUC cases (62%) were also positive for anti-hTERT. Although the HGUC and suspicious for HGUC cases were more likely to show strong staining (6 of 9; 67%), 7 AUC (32%) and 8 NHGUC (22%) cases also demonstrated strong staining. Eight samples (8%) were unsatisfactory for interpretation. Anti-hTERT staining of nonurothelial cells was seen in 77 of 92 samples (84%). CONCLUSIONS: Interpretation of anti-hTERT immunocytochemical staining of ThinPrep material is challenging owing to obscuring of nonurothelial cell staining and difficulty discerning individual urothelial cell cytomorphology when the cells are stained. The significance of the large number of anti-hTERT-positive but cytology-negative cases in our study is uncertain.

Cyto-histo correlations of plasmacytoid and micropapillary variants of high-grade urothelial carcinoma: do they fit well in The Paris System for reporting urinary cytology?

INTRODUCTION: Plasmacytoid and micropapillary variants of high-grade urothelial carcinoma (HGUC) exhibit unique histologic morphology and very aggressive clinical behavior. However, the morphology of these 2 variants in urinary cytology is not well studied and evaluated using The Paris System for reporting urinary cytology. MATERIALS AND METHODS: A database search was performed in all patients with the diagnosis of plasmacytoid or micropapillary HGUC. A total of 5 patients with positive urinary cytology cases were identified. The cytomorphology of every urinary cytology case was correlated with the histologic features in the surgical specimens from the same patient. RESULTS: One urine and 4 bladder washings were evaluated. Cytologically, plasmacytoid HGUCs are characterized by single, large tumor cells with hyperchromasia, irregular nuclear membranes, and vacuolated cytoplasm. The nuclear-to-cytoplasmic (N:C) ratio was less than 0.5 in many of the malignant cells due to the abundant cytoplasm. The cytology features of micropapillary HGUC include the presence of micropapillae of tumor cells with no fibrovascular core. Individual high-grade urothelial cells were also identified in all 4 cases, but 1 (25%) of these had only rare cells meeting The Paris System criteria for HGUC due to abundant cytoplasm and lack of hyperchromasia in most malignant cells. CONCLUSIONS: Plasmacytoid and micropapillary variants of HGUC have unique cytomorphologic features in urinary cytology specimens, which are reflective of the corresponding histological findings. These 2 clinically aggressive variants of HGUC may not be as readily interpreted as malignant using The Paris System for reporting urinary cytology, creating potential diagnostic pitfalls.

The Paris System "atypical urothelial cells" category: can the current criteria be improved?

INTRODUCTION: The Paris System (TPS) for reporting urine cytology was developed for standardization of diagnosis focusing on the detection of high-grade urothelial carcinoma (HGUC). Probably the most challenging task for TPS is to provide criteria for the atypical urothelial cell (AUC) category. The TPS criteria for AUC include increased nuclear/cytoplasmic (N/C) ratio (>0.5) and 1 of the 3 minor criteria including nuclear hyperchromasia (NH), coarse chromatin (CC) and irregular nuclear membrane (INM). We evaluated TPS-AUC diagnostic value and investigated whether other morphologic parameters can improve its criteria. MATERIALS AND METHODS: Urine samples with diagnoses of AUC collected during a 6-month period were re-reviewed. Data captured included N/C ratio >0.5, NH, CC, INM, and 2 additional criteria including enlarged nuclear size (ENS) and the presence of nucleolus (N). ENS was considered when the nucleus was 2 times larger than the urothelial cell or 3 times larger than lymphocyte. RESULTS: By applying the TPS-AUC criteria, the rate of atypia diagnosis reduced in comparison to Pre-TPS (9% versus 13%, P = 0.02). Among the AUC minor criteria, NH was the best criterion with the highest interobserver agreement (IOA) and correlation with HGUC (k = 0.342, r = 0.61, P < 0.001) and strong PPV (93.6%). ENS had the highest PPV (95.8%) and, after NH, had the highest IOA and correlation with HGUC (k = 0.29, r = 0.52, P < 0.001). CONCLUSION: TPS improves the diagnostic value of urine cytology, particularly in cases with atypia. ENS is a strong criterion for increasing the diagnostic value of AUC and potentially can improve TPS performance as a minor criterion.

A new 7-point method facilitates accurate diagnosis of high-grade urothelial carcinoma in routine urinary cytology practice.

INTRODUCTION: This study was designed to identify the minimal and necessary cell morphologies to be considered for high-precision diagnosis of high-grade urothelial carcinoma (HGUC) in a routine urinary cytology practice. MATERIALS AND METHODS: We included 338 urine cytology specimens from 11 medical facilities in Japan. Six experts evaluated these Papanicolaou-stained specimens using their own diagnostic criteria to categorize them within an initial 4-tiered classification system. Of the 338 cases, 70 HGUC and 32 benign cases (with a complete consensus diagnosis of 6 experts) were included for the analysis. Two of the cytologists evaluated the specimens for 20 specific cellular features. The results were analyzed using a contingency table and by discriminant analysis. RESULTS: Of the original 338 cases, 165 were originally diagnosed as HGUC, but only 70 (42.4%) were scored as malignant by all participating cytologists; of the 101 benign cases, only 32 (31.7%) were classified as such in all examinations. These specimens were re-evaluated by 6 experts using a panel of 20 specific cellular features used to distinguish between HGUC and benign diseases; tests of significance and discriminant analyses identified 7 critical features that were most useful for cytological diagnosis. Statistical analysis revealed that a focus on these 7 features led to a diagnosis of HGUC with a probability of over 95%. CONCLUSIONS: The accuracy of our presently used method to evaluate urinary cytology is not consistently high. This novel classification system, which focuses on 7 critical features, facilitates the high accurate diagnosis of HGUC in routine cytology practice.

Developing a Machine Learning Algorithm for Identifying Abnormal Urothelial Cells: A Feasibility Study.

INTRODUCTION: Urine cytology plays an important role in diagnosing urothelial carcinoma (UC). However, urine cytology interpretation is subjective and difficult. Morphogo (ALAB, Boston, MA, USA), equipped with automatic acquisition and scanning, optical focusing, and automatic classification with convolutional neural network has been developed for bone marrow aspirate smear analysis of hematopoietic diseases. The goal of this preliminary study was to determine the feasibility of developing a machine learning algorithm on Morphogo for identifying abnormal urothelial cells in urine cytology slides. METHODS: Thirty-seven achieved abnormal urine cytology slides from cases with the diagnosis of atypical urothelial cells and above (suspicions or positive for UC) were obtained from 1 hospital. A pathologist (J.R.) reviewed the slides and manually selected and annotated representative cells to feed into Morphogo with following categories: benign (urothelial cells, squamous cells, degenerated cells, and inflammatory cells), atypical cells, and suspicious cells. Initial validation of the algorithm was performed on a subset of the original 37 cases. Urine samples from additional 12 unknown cases with various histological diagnoses (6 cases of high-grade urothelial carcinoma (HGUC), 1 case of low-grade urothelial carcinoma (LGUC), 1 case of prostate adenocarcinoma, 1 case of renal cell carcinoma, and 4 cases of non-neoplastic conditions) were collected from another hospital for initial blind testing. RESULTS: A total of 1,910 benign and 1,978 abnormal (atypical and suspicious) cells from 37 slides were annotated for developing and training of the algorithm. This algorithm was validated on 27 slides that resulted in identification of at least 1 abnormal cell per slide, with a total of 200 abnormal cells, and an average of 7.4 cells per slide. Of the 12 unknown cases tested, the original cytology was positive for tumor cells in 2 HGUC samples. Morphogo was abnormal (atypical or suspicious) for 6 samples from patients with UC, including one with LGUC and one with prostate adenocarcinoma. CONCLUSION: Morphogo machine learning algorithm is capable of identifying abnormal urothelial cells. Further validation studies with a larger number of urine samples will be needed to determine if it can be used to assist the cytological diagnosis of UC.

Urinary tract cytology: a cytologic-histopathologic correlation with The Paris System, an institutional study.

INTRODUCTION: Urothelial carcinoma (UC) requires lifelong monitoring, commonly through urinary cytology and cystoscopy. Urine cytology has a relatively high sensitivity for detecting high-grade urothelial carcinoma (HGUC); however, its sensitivity for low-grade urothelial neoplasm (LGUN) is significantly lower with wide interobserver variability. The Paris System (TPS) was proposed to create standardized diagnostic categories with defined cytomorphologic criteria. We attempt to evaluate diagnostic efficacy of identifying UC using TPS through cytologic-histologic correlation. MATERIALS AND METHODS: A retrospective search identified 170 cases of urine cytology cases with concurrent biopsies collected during a 2-year time period at University of Rochester Medical Center. Patient age, sex, smoking history, prior malignancy diagnoses, cystoscopy findings, specimen collection method, UroVysion results, and 1-year follow-up of surgical pathology cases were included. RESULTS: Cytologic-histologic correlation was identified in 59% of cases, with 18% true positives and 41% true negatives. Discordant results were identified in 41% of cases; of these, 4% were false positives, 11% false negatives, 12% potential sampling bias, and 14% were low-grade urothelial carcinoma (LGUC). The analysis of this 2-year study finds a positive predictive value of urine cytology for HGUC to be 81%, a negative predictive value of 79%, a sensitivity of 61%, a specificity of 91%, and an accuracy of 79%. CONCLUSIONS: Our results support TPS's ability to improve the reliability and accuracy of interpretations in urine cytology for HGUC. Nevertheless, additional studies are essential to improve the diagnostic accuracy of LGUN, and urine adequacy, in order to improve patient care and early detection, while identifying potential sampling bias.