A platform-independent AI tumor lineage and site (ATLAS) classifier.

Histopathologic diagnosis and classification of cancer plays a critical role in guiding treatment. Advances in next-generation sequencing have ushered in new complementary molecular frameworks. However, existing approaches do not independently assess both site-of-origin (e.g. prostate) and lineage (e.g. adenocarcinoma) and have minimal validation in metastatic disease, where classification is more difficult. Utilizing gradient-boosted machine learning, we developed ATLAS, a pair of separate AI Tumor Lineage and Site-of-origin models from RNA expression data on 8249 tumor samples. We assessed performance independently in 10,376 total tumor samples, including 1490 metastatic samples, achieving an accuracy of 91.4% for cancer site-of-origin and 97.1% for cancer lineage. High confidence predictions (encompassing the majority of cases) were accurate 98-99% of the time in both localized and remarkably even in metastatic samples. We also identified emergent properties of our lineage scores for tumor types on which the model was never trained (zero-shot learning). Adenocarcinoma/sarcoma lineage scores differentiated epithelioid from biphasic/sarcomatoid mesothelioma. Also, predicted lineage de-differentiation identified neuroendocrine/small cell tumors and was associated with poor outcomes across tumor types. Our platform-independent single-sample approach can be easily translated to existing RNA-seq platforms. ATLAS can complement and guide traditional histopathologic assessment in challenging situations and tumors of unknown primary.

Navigating Practice Issues Related to the Unsatisfactory Cervicovaginal Papanicolaou Test: Survey Results of Laboratories Participating in the 2020 College of American Pathologists PAP Education Program.

CONTEXT.­: Unsatisfactory Papanicolaou (Pap) tests pose a unique set of challenges to the laboratory with regard to their processing, review, reporting, and performance of human papillomavirus (HPV) testing. There are no standardized guidelines for the review process and handling of unsatisfactory Pap tests. OBJECTIVE.­: To assess the current practice patterns regarding various aspects of the unsatisfactory Pap test, from processing to reporting, across laboratories worldwide. DESIGN.­: A supplemental questionnaire was mailed to laboratories participating in the 2020 College of American Pathologists (CAP) Gynecologic Cytopathology (PAP Education) Program, requesting data regarding the unsatisfactory Pap test. RESULTS.­: Of 1520 participating laboratories, 619 (40.7%) responded, and the responses of 577 laboratories were included for further analysis. Only 64.6% (373 of 577) laboratories used the unsatisfactory Pap test criteria as specified by the 2014 Bethesda System. About three-quarters of the respondents (433 of 576; 75.2%) routinely rescreened unsatisfactory Pap tests. Routine repreparation of such Pap tests was performed by 54.9% (316 of 576) of laboratories, and 52.0% (293 of 563) used glacial acetic acid for repreparing excessively bloody specimens. HPV test results were reported for unsatisfactory Pap tests, always or sometimes, by 62.4% (353 of 566) of respondents. CONCLUSIONS.­: This CAP survey reveals important information regarding the practice patterns pertaining to several aspects of the unsatisfactory Pap test. It also provides valuable insight into the quality assurance measures that can be implemented for such tests. Future studies can further aid in the standardization of all components of the handling of unsatisfactory Pap tests for overall quality improvement.

Digital cytology part 1: digital cytology implementation for practice: a concept paper with review and recommendations from the American Society of Cytopathology Digital Cytology Task Force.

Digital cytology and artificial intelligence (AI) are gaining greater adoption in the cytopathology laboratory. However, peer-reviewed real-world data and literature are lacking regarding the current clinical landscape. The American Society of Cytopathology in conjunction with the International Academy of Cytology and the Digital Pathology Association established a special task force comprising 20 members with expertise and/or interest in digital cytology. The aim of the group was to investigate the feasibility of incorporating digital cytology, specifically cytology whole slide scanning and AI applications, into the workflow of the laboratory. In turn, the impact on cytopathologists, cytologists (cytotechnologists), and cytology departments were also assessed. The task force reviewed existing literature on digital cytology, conducted a worldwide survey, and held a virtual roundtable discussion on digital cytology and AI with multiple industry corporate representatives. This white paper, presented in 2 parts, summarizes the current state of digital cytology and AI practice in global cytology practice. Part 1 of the white paper presented herein is a review and offers best practice recommendations for incorporating digital cytology into practice. Part 2 of the white paper provides a comprehensive review of AI in cytology practice along with best practice recommendations and legal considerations. Additionally, the results of a global survey regarding digital cytology are highlighted.

Digital cytology part 2: artificial intelligence in cytology: a concept paper with review and recommendations from the American Society of Cytopathology Digital Cytology Task Force.

Digital cytology and artificial intelligence (AI) are gaining greater adoption in the cytology laboratory. However, peer-reviewed real-world data and literature are lacking in regard to the current clinical landscape. The American Society of Cytopathology in conjunction with the International Academy of Cytology and the Digital Pathology Association established a special task force comprising 20 members with expertise and/or interest in digital cytology. The aim of the group was to investigate the feasibility of incorporating digital cytology, specifically cytology whole slide scanning and AI applications, into the workflow of the laboratory. In turn, the impact on cytopathologists, cytologists (cytotechnologists), and cytology departments were also assessed. The task force reviewed existing literature on digital cytology, conducted a worldwide survey, and held a virtual roundtable discussion on digital cytology and AI with multiple industry corporate representatives. This white paper, presented in 2 parts, summarizes the current state of digital cytology and AI practice in global cytology practice. Part 1 of the white paper is presented as a separate paper which details a review and best practice recommendations for incorporating digital cytology into practice. Part 2 of the white paper presented here provides a comprehensive review of AI in cytology practice along with best practice recommendations and legal considerations. Additionally, the cytology global survey results highlighting current AI practices by various laboratories, as well as current attitudes, are reported.

The Implementation of Nongynecologic Reporting Systems in Cytopathology Laboratories Is Highly Variable: Analysis of Data From a 2020 Supplemental Survey of Participants in the College of American Pathologists Interlaboratory Comparison Program in Nongynecologic Cytology.

CONTEXT­: In recent years, several reporting systems have been developed by national and international cytopathology organizations to standardize the evaluation of specific cytopathology specimen types. OBJECTIVE­: To assess the current implementation rates, implementation methods, and barriers to implementation of commonly used nongynecologic reporting systems in cytopathology laboratories. DESIGN­: Data were analyzed from a survey developed by the committee and distributed to participants in the College of American Pathologists Nongynecologic Cytopathology Education Program mailing. RESULTS­: Nongynecologic reporting systems with the highest rate of adoption were the Bethesda System for Reporting Thyroid Cytopathology, 2nd edition (74.1%; 552 of 745); the Paris System for Reporting Urinary Cytology (53.9%; 397 of 736); and the Milan System for Reporting Salivary Gland Cytopathology (29.1%; 200 of 688). The most common reason given for not adopting a reporting system was satisfaction with a laboratory's current system. Implementation varied among laboratories with regard to which stakeholders were involved in deciding to implement a system and the amount of education provided during the implementation process. CONCLUSIONS­: The implementation of nongynecologic reporting systems in cytopathology laboratories was highly variable.

A clinical-grade liquid biomarker detects neuroendocrine differentiation in prostate cancer.

BackgroundNeuroendocrine prostate cancer (NEPC) is an aggressive subtype, the presence of which changes the prognosis and management of metastatic prostate cancer.MethodsWe performed analytical validation of a Circulating Tumor Cell (CTC) multiplex RNA qPCR assay to identify the limit of quantification (LOQ) in cell lines, synthetic cDNA, and patient samples. We next profiled 116 longitudinal samples from a prospectively collected institutional cohort of 17 patients with metastatic prostate cancer (7 NEPC, 10 adenocarcinoma) as well as 265 samples from 139 patients enrolled in 3 adenocarcinoma phase II trials of androgen receptor signaling inhibitors (ARSIs). We assessed a NEPC liquid biomarker via the presence of neuroendocrine markers and the absence of androgen receptor (AR) target genes.ResultsUsing the analytical validation LOQ, liquid biomarker NEPC detection in the longitudinal cohort had a per-sample sensitivity of 51.35% and a specificity of 91.14%. However, when we incorporated the serial information from multiple liquid biopsies per patient, a unique aspect of this study, the per-patient predictions were 100% accurate, with a receiver-operating-curve (ROC) AUC of 1. In the adenocarcinoma ARSI trials, the presence of neuroendocrine markers, even while AR target gene expression was retained, was a strong negative prognostic factor.ConclusionOur analytically validated CTC biomarker can detect NEPC with high diagnostic accuracy when leveraging serial samples that are only feasible using liquid biopsies. Patients with expression of NE genes while retaining AR-target gene expression may indicate the transition to neuroendocrine differentiation, with clinical characteristics consistent with this phenotype.FundingNIH (DP2 OD030734, 1UH2CA260389, R01CA247479, and P30 CA014520), Department of Defense (PC190039 and PC200334), and Prostate Cancer Foundation (Movember Foundation - PCF Challenge Award).

Analytical validation and initial clinical testing of quantitative microscopic evaluation for PD-L1 and HLA I expression on circulating tumor cells from patients with non-small cell lung cancer.

INTRODUCTION: PD-L1 expression in non-small cell lung cancer (NSCLC) predicts response to immune checkpoint blockade, however is an imperfect biomarker given tumor heterogeneity, and the antigen presentation pathway requiring other components including HLA I expression. HLA I downregulation may contribute to resistance, warranting its evaluation in attempts to guide patient selection. In addition, earlier detection of acquired resistance could prompt earlier change in treatment and prolong patient survival. Analysis of circulating tumor cells (CTCs) captures heterogeneity across multiple sites of metastases, enables detection of changes in tumor burden that precede radiographic response, and can be obtained in serial fashion. METHODS: To quantify the expression of both PD-L1 and HLA I on CTCs, we developed exclusion-based sample preparation technology, achieving high-yield with gentle magnetic movement of antibody-labeled cells through virtual barriers of surface tension. To achieve clinical-grade quantification of rare cells, we employ high quality fluorescence microscopy image acquisition and automated image analysis together termed quantitative microscopy. RESULTS: In preparation for clinical laboratory implementation, we demonstrate high precision and accuracy of these methodologies using a diverse set of control materials. Preliminary testing of CTCs isolated from patients with NSCLC demonstrate heterogeneity in PD-L1 and HLA I expression and promising clinical value in predicting PFS in response to PD-L1 targeted therapies. CONCLUSIONS: By confirming high performance, we ensure compatibility for clinical laboratory implementation and future application to better predict and detect resistance to PD-L1 targeted therapy in patients with NSCLC.

Developing dashboards for performance improvement in cytopathology.

INTRODUCTION: Cytopathology has well-defined and objective quality metrics for monitoring the performance of cytopathologists (CPs) and cytotechnologists (CTs). We transformed these metrics into dashboards for real-time visualization and on-demand feedback. METHODS: Dashboards were constructed with data from the previous 10 calendar years using the software Tableau. The dashboards for CPs were designed to display 2 gynecologic metrics and 1 nongynecologic metric: the ASCUS:SIL ratio, the percentage of high-risk human papillomavirus (HPV)-positive ASCUS interpretations (HPV+ ASCUS rate), and the proportion of AUS/FLUS thyroid interpretations. CT dashboards were designed to include these plus 2 others: the percentage of Papanicolaou tests referred for CP review and the percentage of Papanicolaou tests interpreted as unsatisfactory. Established professional benchmarks or standard deviations were used to set color-coded "goal," "borderline," and "attention" zones. RESULTS: Personal dashboards were successfully developed and implemented for CPs and CTs in the laboratory, with results that are automatically updated every week, requiring minimal curation. Each CP and CT has a unique link that allows them access to their results at any time. Color-coded displays show the individual their quality metrics over the past 10 years, with a snapshot of data from the past 3 months. The laboratory director has a unique link that allows the director access to results for each individual and the laboratory in aggregate. CONCLUSIONS: Personalized dashboards enable individuals to access their performance metrics on demand and examine recent performance as well as patterns over time. This facilitates self-motivation to improve performance and adhere to professional benchmarks.

The Paris system of Reporting Urinary Cytology: Strengths and opportunities.

The Paris system for reporting urinary cytopathology (TPS) was created to address inherent weaknesses inherent in the practice of urinary cytopathology. While urothelial cytology has always performed well at finding high grade, genetically unstable urothelial carcinoma, it performs poorly when it comes to detecting low-grade urothelial neoplasia. TPS intends to improve the utility of urothelial cytology by focusing on what is important, high-grade urothelial carcinoma. This article is a snapshot of the current state of TPS as it heads into its second edition. Successes are described and further developments are considered.

Environmental chemical exposures in the urine of dogs and people sharing the same households.

INTRODUCTION: Urothelial carcinoma (UCC) develops in both humans and dogs and tracks to regions of high industrial activity. We hypothesize that dogs with UCC may act as sentinels for human urothelial carcinogen exposures. The aim of this pilot study was to determine whether healthy people and dogs in the same households share urinary exposures to potentially mutagenic chemical carcinogens. METHODS: We measured urinary concentrations of acrolein (as its metabolite 3-HPMA), arsenic species, 4-aminobiphenyl, and 4-chlorophenol (a metabolite of the phenoxyherbicide 2,4-D) in healthy dogs and their owners. We assessed possible chemical sources through questionnaires and screened for urothelial DNA damage using the micronucleus assay. RESULTS: Biomarkers of urinary exposure to acrolein, arsenic, and 4-chlorophenol were found in the urine of 42 pet dogs and 42 owners, with 4-aminobiphenyl detected sporadically. Creatinine-adjusted urinary chemical concentrations were significantly higher, by 2.8- to 6.2-fold, in dogs compared to humans. Correlations were found for 3-HPMA (r = 0.32, P = 0.04) and monomethylarsonic acid (r = 0.37, P = 0.02) between people and their dogs. Voided urothelial cell yields were inadequate to quantify DNA damage, and questionnaires did not reveal significant associations with urinary chemical concentrations. CONCLUSIONS: Healthy humans and pet dogs have shared urinary exposures to known mutagenic chemicals, with significantly higher levels in dogs. Higher urinary exposures to acrolein and arsenic in dogs correlate to higher exposures in their owners. Follow-up studies will assess the mutagenic potential of these levels in vitro and measure these biomarkers in owners of dogs with UCC.

Standardized terminology systems in cytopathology.

There has been increasing pressure for systemization in cytopathology. Lack of uniformity in categorization, variation in opinion based regional practice, and technologic advancement have created an environment disposed toward creation of more consistent evidence-based approaches to diagnostic problems. This review provides an overview of the major standardized terminology systems in cytology, with historical perspectives and commentary on current uses of these systems. These systems now include gynecologic, thyroid, pancreaticobiliary, urinary, salivary gland, and breast cytology. We summarize major classification systems supported by national and international professional organizations, outlining the structure and goals of each system. Specific benefits and potential pitfalls in the implementation of each system are given. Finally, we address potential criticisms of standardized terminology systems and proposed future directions to continue the evolution of standardized terminology to improve clinical practice.

Circulating Tumor Cells: Overview and Opportunities in Cytology.

Circulating tumor cells (CTCs) have long been assumed to be the substrate of cancer metastasis. However, only in recent years have we begun to leverage the potential of CTCs found in minimally invasive peripheral blood specimens to improve care for cancer patients. Currently, CTC enumeration is an accepted prognostic indicator for breast, prostate, and colorectal cancer; however, CTC enumeration remains largely a research tool. More recently, the focus has shifted to CTC characterization and isolation which holds great promise for predictive testing. This review summarizes the relevant clinical, biological, and technical background necessary for pathologists and cytopathologists to appreciate the potential of CTC techniques. A summary of relevant systematic reviews of CTCs for specific cancers is then presented, as well as potential applications to precision medicine. Finally, we suggest future applications of CTC technologies that can be easily incorporated in the pathology laboratory, with the recommendation that pathologists and particularly cytopathologists apply these technologies to small specimens in the era of "doing more with less."

Ancillary studies in pleural, pericardial, and peritoneal effusion cytology.

Pleural, pericardial, and peritoneal effusion specimens present diagnostic challenges and clinical opportunities for cytology. For the patient, these specimens may be the first diagnosis of malignancy or the first sign of disease recurrence. This review aims to provide useful approaches with which to resolve key difficulties in cytologic diagnosis through the use of ancillary studies, focusing on immunohistochemistry. These approaches are suggested in concert with clinical, radiographic, and morphologic findings. The differentiation of reactive mesothelial cells from malignant mesothelioma and adenocarcinoma is a recurring theme, and Wilms tumor 1 (WT1)/AE1/AE3, claudin 4, and BRCA1-associated protein 1 (BAP1) immunostains are useful new tools in the armamentarium. A targeted workup is suggested for patients with no known primary site or with multiple prior malignancies. Molecular and other biomarker testing can be performed on even modestly cellular fluid specimens and may allow patients to benefit from targeted therapy without the need for additional tissue biopsies. Cancer Cytopathol 2018;000:000-000. © 2018 American Cancer Society.

Pathologic Features of Primary Colon, Rectal, and Anal Malignancies.

In the United States, colorectal cancer is the third most commonly diagnosed cancer in both men and women, as well as the third leading cause of cancer deaths (Colorectal cancer facts & figures 2014­2016, 2014 [2]). Worldwide, colorectal cancer is the fourth leading cause of death and causes almost 700,000 deaths each year (Cancer: fact sheet No. 297, 2015 [55]). This chapter discusses the clinical and pathologic features of the spectrum of epithelial, hematolymphoid, and mesenchymal malignant tumors of the colon, rectum, appendix, and anus.

Saccharomyces cerevisiae Sen1 as a model for the study of mutations in human Senataxin that elicit cerebellar ataxia.

The nuclear RNA and DNA helicase Sen1 is essential in the yeast Saccharomyces cerevisiae and is required for efficient termination of RNA polymerase II transcription of many short noncoding RNA genes. However, the mechanism of Sen1 function is not understood. We created a plasmid-based genetic system to study yeast Sen1 in vivo. Using this system, we show that (1) the minimal essential region of Sen1 corresponds to the helicase domain and one of two flanking nuclear localization sequences; (2) a previously isolated terminator readthrough mutation in the Sen1 helicase domain, E1597K, is rescued by a second mutation designed to restore a salt bridge within the first RecA domain; and (3) the human ortholog of yeast Sen1, Senataxin, cannot functionally replace Sen1 in yeast. Guided by sequence homology between the conserved helicase domains of Sen1 and Senataxin, we tested the effects of 13 missense mutations that cosegregate with the inherited disorder ataxia with oculomotor apraxia type 2 on Sen1 function. Ten of the disease mutations resulted in transcription readthrough of at least one of three Sen1-dependent termination elements tested. Our genetic system will facilitate the further investigation of structure-function relationships in yeast Sen1 and its orthologs.