Acta Cytologica最新文献

Introduction: Urine cytology is a noninvasive and widely used approach for the early detection of urothelial carcinoma (UC), but its diagnostic accuracy is limited, particularly for low-grade lesions. This study aimed to develop a novel artificial intelligence (AI)-based framework for risk stratification of UC from whole-slide images (WSIs), offering a promising solution to enhance the diagnostic accuracy of urine cytology.

Methods: A total of 385 urine cytology slides were included and stratified into three diagnostic groups based on cytological evaluation: negative for high-grade urothelial carcinoma (NHGUC), low risk (including atypical urothelial cells and low-grade urothelial carcinoma [LGUC]), and high risk (including suspicious for high-grade urothelial carcinoma and high-grade urothelial carcinoma). Following digitization into WSIs, expert pathologists conducted detailed cell-level annotation. Cell detection and segmentation were performed using RTMDet and DuckNet, and the extracted features were aggregated into slide-level representations for training and evaluation of classification models.

Results: Support vector machine demonstrated the highest overall performance among the classifiers, with an accuracy of 79%, recall of 79%, and a specificity of 90%. The model demonstrated strong classification performance across three risk stratifications. The high-risk group achieved a sensitivity of 73.1% and specificity of 90.2%, while the low-risk group showed a sensitivity of 81.8% and specificity of 89.1%. Precision-recall curves indicated that the NHGUC group achieved the highest average precision, reaching 0.93, followed by the high-risk group at 0.85 and the low-risk group at 0.82. ROC analysis further demonstrated strong discriminative capability for three risk groups, with the area under the curve measured at 0.95 for NHGUC and 0.91 for both the low-risk and High-risk groups.

Conclusion: The proposed AI-assisted framework shows robust and interpretable performance in stratifying UC cytological categories from WSIs. It holds strong potential as a supportive tool in urine cytology, especially in assisting with the diagnosis of high-risk UC cases.

Background: Ancillary tests are increasingly important for primary cancer diagnosis, as well as predictive and prognostic information, and occasionally cytological samples are the only material readily available. Advanced ancillary testing, including immunohistochemistry (IHC), immunocytochemistry (ICC), in situ hybridization, and next-generation sequencing (NGS) should be carefully standardized and quality controlled in order to provide reliable results. The diversity of preanalytics in the cytological laboratory process poses challenges for quality management.

Summary: Paraffin-embedded cell blocks (CBs) from cytological samples that are collected in and fixed with formalin appear to be the easiest option for ancillary tests, the majority of which are developed for formalin-fixed and paraffin-embedded (FFPE) samples. They can be stained with the same IHC protocols and on-slide controls without additional validation. Fixation time of FFPE CB samples should be controlled since nucleic acid quality and quantity decrease in formalin in a time-dependent manner. Ethanol and methanol, the standard fixatives in cytology, alter the tertiary structure of proteins, thus impairing ICC staining. Depending on the antibody, staining signals can be weaker or even absent in alcohol-fixed cells. Nevertheless, air-dried or methanol-fixed cytospins, liquid-cytology samples, cell-free supernatants, and unstained or stained smears can successfully be used for ancillary testing, but this requires careful protocol optimization and validation. Appropriate on-slide controls are not easily available for ICC, but these can be prepared for example from cell lines or left-over patient samples. If polymerase chain reaction (PCR) or NGS-based testing is performed in-house, different cytological sample types can be validated for routine use.

Key messages: Ancillary tests like ICC need to be validated according to the up-to-date guidelines in order to use the optimal protocol for each sample and fixation type and to discover the possible limitations of the test. Appropriate controls that reflect the preanalytical conditions of the sample material ensure reliable and reproducible results. Cytological material suits well for molecular pathology and could be more widely exploited in diagnostics. European cytopathology laboratories need to recognize the requirements of the in vitro diagnostic (IVD) regulation especially in documenting validation, risk management, and clinical performance data of the laboratory-developed (in house) tests.

Background: Quality assurance (QA) and quality control (QC) are fundamental to maintaining high standards in cytopathologic diagnostics. The recent adoption of digital cytology (DC) has led to transformative changes in cytopathology workflows, including primary diagnosis, telecytopathology-based consultations, and rapid on-site evaluations (ROSEs). These technological developments call for a conceptual shift and redefinition of QA and QC frameworks in the DC era.

Summary: This review explores the evolving landscape of QA and QC in cytopathology, with a focus on the integration of DC into existing quality systems. We examine the role of DC as both a QC tool and a platform for implementing DC-specific QA/QC protocols. Practical applications discussed include leveraging DC for conventional QA/QC tasks, such as education and training of laboratory staff and cytopathologists, and facilitating digital proficiency testing through cloud-based platforms. Additionally, we review current international recommendations for the adoption of DC in cytopathology and propose strategies for the safe and efficient management of digital environments.

Key messages: (i) DC is reshaping the practice of cytopathology and requires updated QA/QC strategies. (ii) DC can enhance QA/QC activities through improved training, proficiency testing, and collaborative diagnostics. (iii) The development and implementation of DC-specific protocols are essential for ensuring accuracy and reliability in digital cytopathologic practice.

Background: Cervical cancer is the fourth most common cancer in women globally with highest incidence and mortality identified in less developed and medically underserved areas in the world. The diminishing cytology workforce, unavailability of expert consultation, and the high volume of Pap tests needing manual screening are the main reasons for exploring innovative solutions to help mitigate the negative effects resulting from the dearth of timely cervical cancer screening in certain population groups.

Summary: Developments in whole slide imaging and artificial intelligence (AI) have enabled the emergence of new computer-assisted systems that have the potential for transforming traditional cytopathology practice. However, AI-based systems are relatively new with limited published data on their validation and clinical utility in clinical practice. Our article aims to increase awareness of the availability of such systems, explores the history and development of AI-assisted screening platforms for Pap tests, compares the performance characteristics of various systems, elaborates on technical challenges associated with conducting clinical trials employing this technology, and discusses considerations around deploying such systems in routine cytopathology practice.

Key message: Revolutionary AI-based systems are being developed and utilized in cytopathology practice to screen Pap tests. Some of these systems have good performance characteristics and provide opportunities to combat various issues such as workload and standardization faced by cytology laboratories globally. However, judicious review of these systems using evidence-based studies is imperative to promote widespread adoption and maintain high-quality standards for patient safety.

Background: Pap classes have been replaced by organ-specific reporting systems in recent decades; however, part of the cytological specimens is insufficient. The present review summarizes how different organ-specific systems define the insufficient category: both quantitative and qualitative criteria are used. In addition, the sample volume may be evaluated in certain specimens.

Summary: The reasons for an insufficient sample may vary and depend either on the lesion itself or the sampling procedure.

Key messages: The management recommendations for insufficient specimens improve communication between cytopathologists and treating physicians.

Background: Cytotechnologists are integral members of the cytopathology team with their role extending beyond that of analyzing slides. They have a unique understanding of cytopreparation, laboratory systems, and workflows given their involvement in varied laboratory processes which makes them key players in quality control, quality assurance, and quality improvement measures. Many cytotechnologists endorse performing quality assurance and/or quality control activities as part of their duties.

Summary: In this article, we review some of the key quality control and assurance measures cytotechnologists are involved in with an emphasis on how they can take a leading role in systems operations and improvements.

Key messages: Cytotechnologists are essential to quality assurance and improvement in the cytopathology laboratory given their intimate knowledge and experience with cytopathology techniques and laboratory operations making them key contributors to maintaining and enhancing laboratory standards.

Background: External quality assessment (EQA), including proficiency testing (PT), is a fundamental aspect of laboratory quality management and a key requirement for diagnostic laboratory accreditation.

Summary: This review highlights significant gaps in comprehensive EQA/PT programs for diagnostic non-gynecological cytopathology that fully address all aspects of the diagnostic process, particularly in Europe.

Key messages: Current EQA/PT programs for diagnostic cytopathology are mostly regional, national, and only partially cover the examination process. The unique challenges of diagnostic cytopathology, including small and limited patient samples, non-standardized laboratory procedures, biomarker testing tailored to specific cytology samples, and the qualitative subjective nature of cytopathologic reporting, necessitate adapted approaches for effective and meaningful EQA.

Background: The advent of programmed cell death-1/programmed death-ligand 1 (PD-1/PD-L1) inhibitors has revolutionized lung cancer treatment, necessitating accurate PD-L1 immunohistochemical (IHC) assessment. While standardized for formalin-fixed paraffin-embedded histological samples, PD-L1 testing on cytology remains challenging. This review aims to address the complexities of PD-L1 IHC in cytology, focusing on validation guidelines, quality assessment, cytohistological correlation, and interobserver variability.

Summary: This review synthesizes current guidelines and research on PD-L1 IHC in cytology; in particular, recent College of American Pathologists (CAP) guidelines emphasize the necessity for rigorous validation, particularly for non-formalin-fixed specimens. As far as cytohistological concordance studies are concerned, the review of 48 original articles revealed significant variability in PD-L1 expression, with concordance rates ranging from 54 to 100% at the 1% cutoff and 82-100% at the 50% cutoff. Finally, interobserver variability, particularly in the 1-49% PD-L1 expression range, further complicates accurate assessment. The review also discusses the challenges associated with quality assessment in cytology, including the lack of standardized control materials and external quality assessment (EQA) programs specifically tailored for cytological samples.

Key messages: PD-L1 testing in cytology is feasible but faces substantial challenges compared to histological specimens. Validation of PD-L1 IHC protocols for cytological preparations, especially non-formalin-fixed samples, is essential. Concordance between cytological and histological PD-L1 expression is variable, highlighting the need for caution in interpretation. Interobserver variability, particularly in cases with intermediate PD-L1 expression (1-49%), affects diagnostic reproducibility. The development of standardized quality control materials and EQA programs for cytology is urgently needed to support consistent and reliable PD-L1 testing.

Background: Quality assurance (QA) is essential in cytopathology to ensure diagnostic accuracy. Common QA methods include peer reviews, 10% random reviews, and benchmarking against published standards. Benchmarking, which compares institutional data on specimen category assignment and risk of malignancy (ROM) with published body site reviews, helps evaluate performance and identify areas of improvement. Cytopathology reporting systems for various body sites categorize specimens based on ROM estimates. The diagnostic categories and ROM estimates in non-gynecologic cytopathology systems can serve as quality metrics to improve practices and maintain high standards of patient care.

Summary: A well-developed QA system in cytology is crucial for ensuring diagnostic accuracy and minimizing errors. By using tools like secondary reviews, retrospective analyses, and structured reporting systems, laboratories can improve practices, detect errors, and maintain high standards of patient care.

Key messages: The cytopathology reporting systems help provide categorical information that can guide clinicians, ensuring quality assurance (QA) and accuracy in diagnosis across various organ sites. Institutional data on category assignments and ROM can be compared with broader literature to assess accuracy and QA. Significant outliers in ROM for specific categories should trigger peer review and potential retraining to improve diagnostic accuracy.