Cytopathology Comes of Age

Artificial Intelligence-Driven Morphology-Based Enrichment of Malignant Cells from Body Fluid

Cell morphology is a fundamental feature used to evaluate patient specimens in pathologic analysis. However, traditional cytopathology analysis of patient effusion samples is limited by low tumor cell abundance coupled with the high background of nonmalignant cells, restricting the ability of downstream molecular and functional analyses to identify actionable therapeutic targets. We applied the Deepcell platform that combines microfluidic sorting, brightfield imaging, and real-time deep learning interpretations based on multidimensional morphology to enrich carcinoma cells from malignant effusions without cell staining or labels. Carcinoma cell enrichment was validated with whole genome sequencing and targeted mutation analysis, which showed a higher sensitivity for detection of tumor fractions and critical somatic variant mutations that were initially at low levels or undetectable in presort patient samples. Our study demonstrates the feasibility and added value of supplementing traditional morphology-based cytology with deep learning, multidimensional morphology analysis, and microfluidic sorting.

Oral candidiasis in patients hospitalised in the intensive care unit: Diagnosis through clinical and cytopathological examinations

OBJECTIVE

To evaluate the prevalence and clinical aspects of oral candidiasis in patients hospitalised in the intensive care unit.

METHODS

This is a longitudinal and prospective study that included 48 participants hospitalised in the intensive care unit. Sociodemographic data, presence of systemic disorders, use of medications, laboratory tests, cause of hospital admission, type of breathing, and length of hospital stay were obtained from medical records. Oral clinical inspection and cytopathological examinations were performed on all participants. The diagnosis of clinical candidiasis was based on the presence of clinical alterations together with positive cytopathological examination results. The diagnosis of subclinical candidiasis was based on the absence of clinical lesions and a positive cytopathological examination. The absence of oral candidiasis was considered when the participant did not present oral lesions and had a negative cytopathological examination.

RESULTS

Clinical candidiasis was present in 18.8% of the 48 participants, and 45.8% of them had the subclinical form. Levels of urea (P = 0.005), creatinine (P = 0.009), haemoglobin (P = 0.009), haematocrit (P = 0.011), bands (P = 0.024), international normalised ratio (INR; P = 0.034), types of breathing (P = 0.017), length of hospital stay (P = 0.037), and outcome (P = 0.014) demonstrated statistically significant differences between the groups with and without oral candidiasis.

CONCLUSIONS

Clinical and subclinical forms of oral candidiasis are frequent in intensive care unit patients. Levels of urea, creatinine, haemoglobin, haematocrit, bands, INR, type of breathing, length of hospital stay, and outcome can be associated with the presence of candidiasis.

"SMART" cytology: The next generation cytology for precision diagnosis

Cytology plays an important role in diagnosing and managing human diseases, especially cancer, as it is often a simple, low cost yet effective, and non-invasive or minimally invasive diagnostic tool. However, traditional morphology-based cytology practice has limitations, especially in the era of precision diagnosis. Recently there have been tremendous efforts devoted to apply computational tools and to perform molecular analysis on cytological samples for a variety of clinical purposes. Now is probably the appropriate juncture to integrate morphology, machine learning, and molecular analysis together and transform cytology from a morphology-driven practice to the next level - "SMART" Cytology. In this article we will provide a rather brief review of the relevant works for computational analysis on cytology samples, focusing on single-cell-based multiplex quantitative analysis of biomarkers, and introduce the conceptual framework of "SMART (Single cell, Multiplex, AI-driven, and Real Time)" Cytology.

Geographic Distribution, Number, and Types of Papers Published in International Cytopathology Journals in the Last 5.5 Years: A Preliminary Study

OBJECTIVE

The aim of this study was to explore the geographic distribution and number of papers published in international and Science Citation Index (SCI)-indexed cytology journals based on their country of origin.

MATERIALS AND METHODS

A country-based geographic analysis of studies published over a 5.5-year period from January 2016 to June 2021 in 5 cytopathology journals indexed as SCI and SCI-E with an impact factor higher than 1 (Cancer Cytopathology, Cytopathology, Diagnostic Cytopathology, Acta Cytologica, and CytoJournal) and papers categorized as "original" and "other" was performed.

RESULTS

A total of 3,063 papers were found, with 1,466 (47.8%) categorized as "original" papers and 1,597 (52.1%) designated as "other" papers. These papers were submitted from 62 different countries. The five countries with the greatest number of papers were the USA (38.4%), India (16.8%), Japan (7.4%), Italy (5.5%), and Brazil (3.1%). A general subgroup analysis was also performed on the original studies without a country breakdown. Cytomorphological, cytomorphological-immunohistochemical, and molecular assessments compose 38.5%, 45.7%, and 15% of the subgroups, respectively.

CONCLUSION

The number of academic papers originating from developing countries in the field of cytopathology has increased in recent years. Although most scientific papers are produced in developed countries, the rate in these countries is much lower than that in some developing countries as the rate of academic growth in developed countries has stabilized. Despite the widespread and sophisticated implementation of cytology in daily practice in Western European countries outside the UK, such as Germany and the Netherlands, and in Scandinavian countries and other developed countries, such as Australia and Canada, these countries rank in the middle to lower end of countries producing cytology papers. Meanwhile, there has been an increase in the number of cytology papers published by authors from Southern European countries, such as Italy (ranked 4th) and Spain (ranked 6th), and Turkey (ranked 8th). There is a remarkable increase in cytology papers originating from Asia, particularly India, Japan, and China.

SUMMARY

We aimed to present a basic survey of the geographic distribution of manuscript submissions to high-impact cytopathology journals and to point out emerging trends in cytology utilization and basic research. However, our results show that the landscape of cytology is changing and suggest geographic regions that are ripe for the production of novel "points of view" and new research findings.