Large-scale validation study of an improved semiautonomous urine cytology assessment tool: AutoParis-X

BACKGROUND

Adopting a computational approach for the assessment of urine cytology specimens has the potential to improve the efficiency, accuracy, and reliability of bladder cancer screening, which has heretofore relied on semisubjective manual assessment methods. As rigorous, quantitative criteria and guidelines have been introduced for improving screening practices (e.g., The Paris System for Reporting Urinary Cytology), algorithms to emulate semiautonomous diagnostic decision-making have lagged behind, in part because of the complex and nuanced nature of urine cytology reporting.

METHODS

In this study, the authors report on the development and large-scale validation of a deep-learning tool, AutoParis-X, which can facilitate rapid, semiautonomous examination of urine cytology specimens.

RESULTS

The results of this large-scale, retrospective validation study indicate that AutoParis-X can accurately determine urothelial cell atypia and aggregate a wide variety of cell-related and cluster-related information across a slide to yield an atypia burden score, which correlates closely with overall specimen atypia and is predictive of Paris system diagnostic categories. Importantly, this approach accounts for challenges associated with the assessment of overlapping cell cluster borders, which improve the ability to predict specimen atypia and accurately estimate the nuclear-to-cytoplasm ratio for cells in these clusters.

CONCLUSIONS

The authors developed a publicly available, open-source, interactive web application that features a simple, easy-to-use display for examining urine cytology whole-slide images and determining the level of atypia in specific cells, flagging the most abnormal cells for pathologist review. The accuracy of AutoParis-X (and other semiautomated digital pathology systems) indicates that these technologies are approaching clinical readiness and necessitates full evaluation of these algorithms in head-to-head clinical trials.

Perceptions of Paris: an international survey in preparation for The Paris System for Reporting Urinary Cytology 2.0 (TPS 2.0)

INTRODUCTION

An international panel of experts in the field of urinary cytopathology conducted a survey, supported by the American Society of Cytopathology, to seek opinions, gather evidence, and identify practice patterns regarding urinary cytology before and after the introduction of The Paris System for Reporting Urinary Cytopathology (TPS). Results from this survey were utilized in the development of the second edition of TPS (TPS-2.0).

MATERIALS AND METHODS

The study group, originally formed during the 2013 International Congress of Cytology, reconvened at the 2019 annual meeting of the American Society of Cytopathology. To prepare for the second edition of TPS, the group generated a survey that included 43 questions related to the taxonomy and practice of urinary cytology.

RESULTS

A total of 523 participant responses were collected, and 451 from 54 countries passed a qualifying screen. Three hundred ninety-four participants provided information about their work settings. Eighty-two percent (218/266) of responding participants use TPS. One hundred sixty-eight people who responded on their urinary cytology atypia rates reported an average decrease from 21.6% to 16%. Over three fourths of participants felt that the same criteria should be used for upper and lower tract interpretations and for instrumented and voided samples. There were varied opinions on addressing atypical squamous cells and suggestions for an expanded discussion of the issue to be included in TPS 2.0.

CONCLUSIONS

Results of the survey demonstrate strong support for TPS and show a decreased self-reported atypia rate in the laboratories using TPS. The majority of participants related that the criteria put forth for the reporting categories were user-friendly and applied with relative ease. The comment section of the survey included suggestions from the participants for further improvement of TPS. Results of this survey have been useful in fine-tuning and advancing TPS. They were considered along with recent literature to generate the second edition of TPS.

Indeterminate atypia in urinary tract cytology: Does it really matter?

The study of atypia in urinary cytology has been ongoing for decades but most studies have focused primarily on test performance in patients with concurrent biopsies and/or limited follow-up periods. While these data are useful, many studies fail to consider patient factors that may alter the pretest probability, which can subsequently affect test performance. An isolated diagnosis of malignancy in urinary cytology usually has a high positive predictive value and allows a urologist to conduct a rigorous workup of the patient to establish a tissue diagnosis. However, it is less certain how an atypical diagnosis impacts patient care, given that many patients have a history of bladder cancer and are already under surveillance with cystoscopy at regular screening intervals. Furthermore, a discrete negative urine cytology is unlikely to allow a patient to forego a cystoscopy procedure due to limitations in the sensitivity of urine cytology. Over the last several years, the introduction of The Paris System for Reporting Urinary Cytology (TPS) has improved the predictive value of atypical diagnoses, but additional studies are needed to evaluate the performance of these diagnoses in specific clinical situations. Such data could better inform urologists on how to manage patients with atypical diagnoses. This review discussed the diagnosis of atypia in urinary cytology and the impact of such a diagnosis in various clinical contexts.

Comparison of Diagnostic Performances of Urine Cytology Before and After the Use of The Paris System Criteria: An Institutional Experience from Turkey

Background:

Urine cytology remains to be the test of choice in the detection of high-grade urothelial carcinomas (HGUC) due to its favorable sensitivity. However, a significant rate of cases is reported under atypical/indeterminate categories, which result in a decrease in its specificity. Providing standardized cytologic criteria, one of the aims of The Paris System (TPS) is to reduce the use of indeterminate diagnoses and provide a higher predictive value in these categories.

Aims:

We compared the diagnostic performances of TPS and our original reporting system, and also investigated the interobserver reproducibility of the cytologic criteria used.

Materials and Methods:

A total of 386 urine samples were reviewed retrospectively. Original cytologic diagnoses have been made using similar cytologic features proposed by TPS. All slides were recategorized after the use of the cytologic criteria as described by TPS guideline.

Results:

After TPS, specificity of the test increased from 39.6% to 63.5, sensitivity decreased from 92.5% to 88.8%, and diagnostic accuracy increased from 63.6% to 75%. The use of negative category increased threefold. Frequencies of indeterminate categories of atypical urothelial cells (AUC) and suspicious for HGUC (SHGUC) decreased by 36% and 56.5%, respectively. A subsequent detection of HGUC after AUC and SHGUC categories increased by 38% and 64%, respectively. Interobserver agreement for TPS categorization was 39%.

Conclusions:

TPS improved diagnostic accuracy of urine cytology by reducing the use of indeterminate categories, and resulted in increase in their predictive value for subsequent diagnosis of HGUC. However, reproducibility of diagnostic categories seemed to be imperfect.

Polyomavirus (BK) cytopathic effect in urine cytology is not associated with high risk of developing high-grade urothelial carcinoma

INTRODUCTION

Polyomavirus cytopathic effect (BK-CPE) is classified as "negative for high-grade urothelial carcinoma" (NHGUC) in the Paris System for Reporting Urinary Cytology. However, polyomaviruses have been historically associated with tumor development and have been recently reported as an independent risk factor for renourinary carcinoma in transplant patients. The aim of the present study was to investigate the relationship between polyomavirus infection in the urinary tract and the subsequent risk of developing high-grade urothelial carcinoma (HGUC) in the general population.

MATERIALS AND METHODS

A retrospective case-control study was conducted to assess BK-CPE in all urinary cytology examinations performed from 2009 to 2011 for cases with an interpretation of NHGUC, NHGUC with BK, atypical urothelial cells (AUCs), or AUCs with BK. The endpoint of the present study was a diagnosis of HGUC on either bladder biopsy or urine cytology for those patients with subsequent follow-up data.

RESULTS

A total of 252 cases with a urinary cytology interpretation of NHGUC, 234 with NHGUC + BK, 255 with AUCs, and 64 with AUCs + BK were identified. The surgical and cytological follow-up data showed that the overall risk of the development of HGUC for those with NHGUC, NHGUC + BK, AUCs, and AUCs + BK was 6.0%, 6.8%, 23.5%, and 12.5%, respectively. No statistically significant differences were found between the patients with NHGUC and those with NHGUC + BK. A statistically significant difference was found for patients with AUCs compared with patients with NHGUC + BK and those with AUCs + BK (P < 0.001).

CONCLUSIONS

The presence of BK-CPE in urine cytology samples does not increase the overall risk of the development of HGUC. Our results support the recommendation from the Paris System for Reporting Urinary Cytology to place urine samples with BK-CPE in the NHGUC category.

Identification of infectious organisms in cytopathology: A review of ancillary diagnostic techniques

Cytology samples obtained from exfoliative sources and fine-needle aspiration (FNA) procedures can all be used to detect microorganisms and/or the associated cytopathologic effects (CPE) caused by an infection. There are many advantages to utilizing cytology samples as an adjunct to routine microbiology laboratory methods. For example, cytology samples can be obtained by non-invasive and minimally invasive techniques, and interpretation is affordable, accurate, and fast. Furthermore, routine cytology stains, including the Papanicolaou (Pap) and the Diff-Quik (DQ) stains, can adequately identify a number of microorganisms. Finally, material obtained by these procedures can also be used for cytologic ancillary testing, microbiology culture, and molecular studies. Currently, there are a variety of ancillary diagnostic techniques that are routinely utilized in the cytopathology laboratory. Additionally, the increasing utilization of molecular-based, diagnostic techniques on fluid specimens, as well as FFPE material, is expanding the role of cytopathology for infectious disease diagnostics. In this review, we provide an overview of the most practical ancillary techniques commonly used to identify microorganisms on cytology specimens.

The Paris System for Reporting Urinary Cytology: early review of the literature reveals successes and rare shortcomings

The Paris System for Reporting Urinary Cytology (TPS) provides recommendations for the diagnosis of urinary tract cytology (UTC) specimens and has found acceptance on an international level. Since the official release of TPS in 2016, numerous research studies have been published analyzing its impact. This review summarizes the studies published since the release of TPS, highlighting areas in which TPS has performed well and other areas in which TPS may need improvement.

High-grade urothelial carcinoma in urine cytology with jet black and smooth or glassy chromatin

BACKGROUND

Some high-grade urothelial carcinomas (UCs) in urine cytology can have jet black, smooth, or glassy chromatin, but to the authors' knowledge, the incidence and criteria for diagnosis are not well described. The current study was performed to define the incidence and appearance of high-grade UC in urine cytology in cytospin preparations with jet black and smooth or glassy chromatin.

METHODS

Cytospin preparations from 331 cases with biopsy follow-up (230 benign/low-grade UCs and 101 malignant UCs) were reviewed.

RESULTS

Cases with malignant cells with jet black and smooth or glassy chromatin were identified in a total of 60 cases (59.4% of all malignancies). These comprised 18 carcinoma in situ cases, 28 high-grade papillary UCs, 8 invasive UCs, 3 squamous cell carcinomas, 2 adenocarcinomas, and 1 melanoma. Of the 93 high-grade UCs, 51 (54.8%) had cells with either jet black and smooth or glassy chromatin. These cells were the only type of malignant cell in 6 of 101 cases (5.9%). All cases had at least 50 cells with jet black nuclei. Nuclei with jet black and smooth chromatin often were smaller than normal urothelial cells, often but not always elongate, had irregular nuclear outlines including pointed areas, and usually were accompanied by necrosis. Cells with glassy chromatin often were larger than normal urothelial cells, had rounder but still irregular nuclei, and also had frequent necrosis.

CONCLUSIONS

Malignant urothelial cells in urine cytology with jet black chromatin are common and can be diagnosed as "positive for malignancy" based on their irregular nuclear outline, increased cellularity (≥50 abnormal cells), and frequent necrosis. Cancer Cytopathol 2018;126:64-8. © 2017 American Cancer Society.

Implementation of the Paris System for Reporting Urinary Cytology results in lower atypical diagnostic rates

INTRODUCTION

The Paris System for Reporting Urinary Cytology (PSRUC) provides a standardized reporting schema for urine cytology with defined criteria for each diagnostic category. We report the impact at our institution of adopting the PSRUC on the frequency and distribution of urine cytology diagnoses, with particular attention to the "atypical" category as it serves as a potential laboratory quality control measure.

MATERIALS AND METHODS

Urine cytology specimen diagnoses were evaluated during 5-month periods prior to and after the introduction of PSRUC. The number of cases in each diagnostic category by either the laboratory as a whole or by individual cytopathologists were analyzed. Following confidential feedback given to individual cytopathologists, a third 5-month period of cytology diagnosis analysis was performed.

RESULTS

The overall laboratory atypical call rate was significantly lower in the post-PSRUC as compared with the pre-PSRUC period (29.5% versus 21.8%; P < 0.0001), with individual cytopathologist atypical call rate lower post-PSRUC (range: 10.2%-37.9%) compared with pre-PSRUC (range: 12.2%-45.0%). The institution of feedback based on these findings did not result in any further statistical change in the atypical call rate (21.8% versus 22.2%).

CONCLUSIONS

Adoption of PSRUC resulted in a significant decrease in the number of atypical diagnoses with little change in the suspicious or malignant categories. Future studies are needed to determine the effect of decreased atypical call rates on the sensitivity/specificity of urine cytopathology, as well as to see if other measures (such as continued cytopathologist feedback or educational modules) can further reduce atypical rates.

Diagnostic utility of urine cytology in early detection of polyomavirus in transplant patients

INTRODUCTION

Polyomavirus-associated nephropathy (PVAN) is one of the most common disease affecting transplant patients, mainly caused by BK polyomavirus (BKV) and with <5% of the cases caused by JC polyomavirus (JCV). Screening and early intervention, including appropriate reduction in immunosuppressive therapy, are critical to reduce allograft loss. The presence of decoy cells in the urine is a characteristic cytopathic effect of polyomavirus. The goal of this study was to investigate the significance of decoy cells in urine cytology in transplant patients, comparing with the plasma viral replication level detected by the real-time quantitative BK virus polymerase chain reaction test (Qt-BK PCR).

METHODS

A cohort of post-transplantation patients with serum BKV level monitored by Qt-BK PCR from 2008 to 2013 was studied. Among them, 35 patients had both urine cytology (UC) analysis and Qt-BK PCR performed. The clinical presentation along with the available UC slides were retrieved and reviewed.

RESULTS

Compared with Qt-BK PCR, the sensitivity, specificity, positive predictive value, and negative predictive value of urine cytology analyzed within one week apart were 92%, 71%, 85%, and 83%, respectively. The accuracy of the UC was 84%. More interestingly, UC played a key role in identifying a case of JCV associated PVAN whereas Qt-BK PCR from both urine and plasma failed to detect this virus.

CONCLUSION

Our data suggests that urine cytology is a sensitive surveillance test for early detection of polyomavirus in transplant patients, and it is particularly useful to screen for rare JC polyomavirus.