Clinical utility of rapid on-site evaluation of brush cytology during bronchoscopy using endobronchial ultrasound with a guide sheath.

Previous studies have shown that rapid on-site evaluation (ROSE) improves the diagnostic yield of bronchoscopy using endobronchial ultrasound with a guide sheath (EBUS-GS) for peripheral pulmonary lesions (PPL). While ROSE of imprint cytology from forceps biopsy has been widely discussed, there are few reports on ROSE of brush cytology. This study investigated the utility of ROSE of brush cytology during bronchoscopy. We retrospectively analyzed data from 214 patients who underwent bronchoscopy with EBUS-GS for PPL. The patients in the ROSE group had significantly higher diagnostic sensitivity through the entire bronchoscopy process than in the non-ROSE group (96.8% vs. 83.3%, P = 0.002). The use of ROSE significantly increased the sensitivity of brush cytology with Papanicolaou staining (92.9% vs. 75.0%, P < 0.001). When ROSE was sequentially repeated on brushing specimens, initially negative ROSE results converted to positive in 79.5% of cases, and the proportion of specimens with high tumor cell counts increased from 42.1 to 69.0%. This study concludes that ROSE of brush cytology improves the diagnostic accuracy of bronchoscopy and enhances specimen quality through repeated brushing.

Enhancing diagnostic precision in thyroid nodule assessment: evaluating the efficacy of a novel cell preservation technique in fine-needle aspiration cytology.

Objectives: This study aimed to evaluate the effectiveness of thyroid fine needle aspiration cytology (FNAC) using a novel-cell preserving matrix called Cytomatrix in improving diagnostic accuracy for thyroid nodules. Materials and methods: Fifty patients undergoing thyroidectomy were enrolled and FNAC was performed on the excised thyroid glands, with the collected sample being placed on the Cytomatrix. The results were compared with histopathological analysis, and diagnostic performance was assessed statistically. Results: Cytomatrix demonstrated an accuracy of 96%, sensitivity of 84.61%, and specificity of 100%. Concordance between cytological and histopathological findings highlighted Cytomatrix's potential to enhance thyroid FNAC accuracy. Conclusion: FNAC using Cytomatrix shows promise in improving diagnostic accuracy for thyroid nodules. Its application, marked by faster processing and efficient resource utilization, coupled with the preservation of cellular architecture, holds considerable potential in enhancing cytological diagnosis, thus optimizing patient management strategies.

Peritoneal washing cytology status as a crucial prognostic determinant in patients with localized pancreatic ductal adenocarcinoma who underwent curative-intent resection following preoperative chemoradiotherapy.

BACKGROUND: Prognostic implications of peritoneal washing cytology (CY) in patients with localized pancreatic ductal adenocarcinoma (PDAC) undergoing surgical resection following preoperative chemoradiotherapy (CRT) remain unclear. This study aimed to elucidate the prognostic significance and predictors of a positive CY status (CY+) after preoperative CRT. METHODS: Clinical data from 141 patients with localized PDAC who underwent curative-intent resection after preoperative CRT were retrospectively analyzed to examine the association between CY+ and clinicopathological factors and survival. RESULTS: CY+ was observed in six patients (4.3%). The CY+ group exhibited significantly higher preoperative serum levels of CA19-9 and a substantially greater incidence of tumor location in the pancreatic body or tail, along with pathological invasion to the anterior pancreatic capsule, than the CY- group. The CY+ group had a significantly higher incidence of peritoneal recurrence compared with the CY- group (83.3% vs. 18.5%, p = 0.002). Overall survival (OS) and recurrence-free survival (RFS) after surgery were significantly shorter in the CY+ group than in the CY- group (CY+ vs. CY-: 18.3 vs. 46.2 months, p = 0.001, and 8.9 vs. 17.7 months, p = 0.009, respectively). Multivariate analyses identified CY+ as an independent prognostic factor for worse OS (hazard ratio 5.00, 95% confidence interval 1.03-12.31) and RFS (hazard ratio 2.58, 95% confidence interval 1.04-6.43). Local invasion grade on imaging before CRT, limited histological response to CRT, and absence of adjuvant chemotherapy were independent predictors of worse OS and RFS. CONCLUSION: Despite the relatively low incidence of CY+ after preoperative CRT, it emerged as an independent prognostic factor in patients with localized PDAC undergoing curative-intent resection following preoperative CRT.

[Application of cell blocks to assist in precise cytological diagnosis of serous effusion].

Objective: To investigate the importance of cell block and immunohistochemistry in the accurate diagnosis of serous effusion. Methods: A retrospective study was conducted on 3 124 cases of serous effusion from the Department of Pathology, Beijing Hospital from 2018 to 2022, include 2 213 cases of pleural effusion, 768 cases of peritoneal effusion, 143 cases of pericardial effusion. There were 1 699 males (54.4%) and 1 425 females (45.6%), average age 69 years old. Of which 1 292 cases were prepared with cell blocks and examined with immunohistochemical stain. Results: The percentage of malignant diagnosis increased from 64.9% (839/1 292) to 84.0% (1 086/1 292) after cell block preparation, and 1 086 cases were accurately diagnosed with histological type and/or origin of primary tumor. The undetermined diagnosis of suspected malignancy decreased from 13.3% (172/1 292) to 0.1% (1/1 292) and that of atypical hyperplasia from 18.8% (243/1 292) to 0.4% (5/1 292). The negative result for malignancy rate increased from 3.0% (38/1 292) to 15.5% (200/1 292). The differences highlighted above were statistically significant (Pearson's chi-squared test=12.739, P<0.01). Conclusion: Application of immunohistochemistry based on cell block can significantly improve malignant diagnosis in serous effusion, identify tumor origin and histological type as well as decrease the uncertain diagnosis.

CytoGAN: Unpaired staining transfer by structure preservation for cytopathology image analysis.

With the development of digital pathology, deep learning is increasingly being applied to endometrial cell morphology analysis for cancer screening. And cytology images with different staining may degrade the performance of these analysis algorithms. To address the impact of staining patterns, many strategies have been proposed and hematoxylin and eosin (H&E) images have been transferred to other staining styles. However, none of the existing methods are able to generate realistic cytological images with preserved cellular layout, and many important clinical structural information is lost. To address the above issues, we propose a different staining transformation model, CytoGAN, which can quickly and realistically generate images with different staining styles. It includes a novel structure preservation module that preserves the cell structure well, even if the resolution or cell size between the source and target domains do not match. Meanwhile, a stain adaptive module is designed to help the model generate realistic and high-quality endometrial cytology images. We compared our model with ten state-of-the-art stain transformation models and evaluated by two pathologists. Furthermore, in the downstream endometrial cancer classification task, our algorithm improves the robustness of the classification model on multimodal datasets, with more than 20 % improvement in accuracy. We found that generating specified specific stains from existing H&E images improves the diagnosis of endometrial cancer. Our code will be available on github.

Pitfalls of cytological diagnosis of tumours of the pancreaticobiliary tract.

The recent introduction of the WHO cytology classification of pancreatobiliary tumours aimed to improve the diagnosis and management of these tumours. The present paper briefly describes the methods of diagnosis. Emphasis is then put on a detailed comparison of the previous Papanicolaou classification and the new WHO classification and description of the changes brought about by the introduction of the WHO classification. In the last part of the paper, we present interesting cases from our practice illustrating possible diagnostic pitfalls of cytological evaluation.

Minimally Invasive, Maximally Effective: The Power of Precision Cytoanalysis on Effusion Samples-A Comprehensive Exploration from Traditional Methods to Innovative Approaches.

Precision medicine translates through molecular assays and in minimally invasive diagnosis, evident in analyses of effusions that serve therapeutic and diagnostic purposes. This cost-effective and low-risk approach provides advantages, playing a pivotal role in late-stage oncology and frequently standing as the primary resource for cancer diagnosis and treatment pathways. This article outlines the workflow for managing serous fluid and explores how cytology effusion analysis extends beyond immunocytological diagnosis. Combined with current molecular tests it showcases the potential to be a skillful tool in precision cytopathology.

Artificial Intelligence Applications in Cytopathology: Current State of the Art.

The practice of cytopathology has been significantly refined in recent years, largely through the creation of consensus rule sets for the diagnosis of particular specimens (Bethesda, Milan, Paris, and so forth). In general, these diagnostic systems have focused on reducing intraobserver variance, removing nebulous/redundant categories, reducing the use of "atypical" diagnoses, and promoting the use of quantitative scoring systems while providing a uniform language to communicate these results. Computational pathology is a natural offshoot of this process in that it promises 100% reproducible diagnoses rendered by quantitative processes that are free from many of the biases of human practitioners.

Efficacy of Follicular Cell Pattern Analysis in Thyroid Fine-needle Aspiration Cytology Evaluation.

CONTEXT: Fine-needle aspiration cytology (FNAC) is widely utilized for thyroid lesion diagnosis but faces challenges such as sample inadequacy and overlapping cytological features. This study examines how accurately these patterns correlate with histopathological diagnoses, shedding light on FNAC's limitations and diagnostic potential. AIMS: To study the application of the architectural pattern of follicular cells in the interpretation of thyroid lesions and to demonstrate the diagnostic accuracy (DA) of FNAC. SETTINGS AND DESIGN: Cross-sectional study carried over 1 year. SUBJECTS AND METHODS: A total of 110 cases were reviewed by the cytopathologists. The prominent follicular cell architecture, namely macrofollicular, microfollicular, papillary, trabecular, three-dimensional clusters, and dispersed cells, was described in each case. In addition to these patterns, cellular morphology and background features were also noted, and a final cytological diagnosis was established. The cytology diagnosis was correlated with the histopathological diagnosis. STATISTICAL ANALYSIS USED: Sensitivity, specificity, positive predictive value, negative predictive value, DA of FNAC in diagnosing nonneoplastic and neoplastic lesions. RESULTS: Macrofollicular pattern was seen in 80.26% of colloid goiter cases. Microfollicular pattern was observed in 72.2% of follicular neoplasm. About 62.5% of papillary thyroid carcinomas showed a papillary pattern. The trabecular pattern was seen in 42.86% of chronic lymphocytic thyroiditis and 16.67% of follicular neoplasms. The sensitivity and specificity of FNAC in diagnosing neoplastic lesions was 92.59% and 97.59%, respectively. CONCLUSIONS: FNAC is a simple, rapid, definite, and cost-effective primary diagnostic tool for thyroid evaluation. Cell architecture pattern is a simple and appropriate approach that complements cell morphology and background details in arriving at the final cytological diagnosis of thyroid lesions.

Résumé Contexte:La cytologie par aspiration à l'aiguille fine (FNAC) est largement utilisée pour le diagnostic des lésions thyroïdiennes, mais elle est confrontée à des défis tels que l'insuffisance des échantillons et des caractéristiques cytologiques qui se chevauchent. Cette étude examine avec quelle précision ces modèles sont en corrélation avec les diagnostics histopathologiques, l'excrétion lumière sur les limites et le potentiel diagnostique de la FNAC.Objectifs:Étudier l'application du modèle architectural des cellules folliculaires dans le interprétation des lésions thyroïdiennes et démontrer la précision diagnostique (DA) de la FNAC.Paramètres et conception:étude transversale réalisée sur 1 an.Sujets et méthodes:Au total, 110 cas ont été examinés par les cytopathologistes. L'architecture cellulaire folliculaire proéminente, à savoir des amas macrofolliculaires, microfolliculaires, papillaires, trabéculaires, tridimensionnels et des cellules dispersées, ont été décrits dans chaque cas. Dans En plus de ces modèles, la morphologie cellulaire et les caractéristiques de fond ont également été notées, et un diagnostic cytologique final a été établi. Le Le diagnostic cytologique était corrélé au diagnostic histopathologique.Analyse statistique utilisée:sensibilité, spécificité, prédictif positif valeur, valeur prédictive négative, DA de la FNAC dans le diagnostic des lésions non néoplasiques et néoplasiques.Résultats:un schéma macrofolliculaire a été observé dans 80,26 % des cas de goitre colloïde. Un profil microfolliculaire a été observé dans 72,2 % des néoplasmes folliculaires. Environ 62,5 % de la thyroïde papillaire les carcinomes présentaient un aspect papillaire. L'aspect trabéculaire a été observé dans 42,86 % des thyroïdites lymphoïdes chroniques et 16,67 % des cas folliculaires néoplasmes. La sensibilité et la spécificité du FNAC dans le diagnostic des lésions néoplasiques étaient respectivement de 92,59 % et 97,59 %.Conclusions:FNAC est un outil de diagnostic primaire simple, rapide, précis et rentable pour l'évaluation de la thyroïde. Le modèle d'architecture cellulaire est simple et approprié approche qui complète la morphologie cellulaire et les détails de base pour parvenir au diagnostic cytologique final des lésions thyroïdiennes.

Deep learning predicts the 1-year prognosis of pancreatic cancer patients using positive peritoneal washing cytology.

Peritoneal washing cytology (CY) in patients with pancreatic cancer is mainly used for staging; however, it may also be used to evaluate the intraperitoneal status to predict a more accurate prognosis. Here, we investigated the potential of deep learning of CY specimen images for predicting the 1-year prognosis of pancreatic cancer in CY-positive patients. CY specimens from 88 patients with prognostic information were retrospectively analyzed. CY specimens scanned by the whole slide imaging device were segmented and subjected to deep learning with a Vision Transformer (ViT) and a Convolutional Neural Network (CNN). The results indicated that ViT and CNN predicted the 1-year prognosis from scanned images with accuracies of 0.8056 and 0.8009 in the area under the curve of the receiver operating characteristic curves, respectively. Patients predicted to survive 1 year or more by ViT showed significantly longer survivals by Kaplan-Meier analyses. The cell nuclei found to have a negative prognostic impact by ViT appeared to be neutrophils. Our results indicate that AI-mediated analysis of CY specimens can successfully predict the 1-year prognosis of patients with pancreatic cancer positive for CY. Intraperitoneal neutrophils may be a novel prognostic marker and therapeutic target for CY-positive patients with pancreatic cancer.

Urinary Tract Cytopathology: Current and Future Impact on Patient Care.

Urine cytology is a non-invasive, cost-efficient, and sensitive test to detect high-grade urothelial carcinoma. The Paris System (TPS) for Reporting Urinary Cytology is an evidence-based system that uses the risk of malignancy to guide patient management. Since its inception, TPS has standardized urine cytology reports, facilitating communication among pathologists and between pathologists and clinicians. It is imperative to correlate the urine cytology findings with the concurrent tissue sample to avoid false-negative and false-positive results when possible. Several ancillary tests and artificial intelligence algorithms are being developed to increase the accuracy of urine cytology interpretation.

Precision Medicine in Cytopathology.

Over the last decade, cancer diagnostics has undergone a notable transformation with increasing complexity. Minimally invasive diagnostic tests, driven by advanced imaging and early detection protocols, are redefining patient care and reducing the need for more invasive procedures. Modern cytopathologists now safeguard patient samples for vital biomarker and molecular testing. In this article, we explore ancillary testing modalities and the role of biomarkers in organ-specific contexts, underscoring the transformative impact of precision medicine. Finally, the advent of more than 80 Food and Drug Administration-approved predictive biomarkers signals a new era, guiding cancer care toward personalized and targeted strategies.

Pulmonary Cytopathology: Current and Future Impact of Microscopy and Immunohistochemistry.

With the advancement of tissue procurement techniques, in-depth knowledge of morphology is crucial for cytopathologists to diagnose neoplastic and nonneoplastic lung diseases optimally. Cytopathologists must also be well versed in immunohistochemistry/immunocytochemistry markers and their interpretation for an accurate diagnosis.

Positive peritoneal lavage fluid cytology based on isolation by size of epithelial tumor cells indicates a high risk of peritoneal metastasis.

Background: Peritoneal metastasis (PM) is the most prevalent type of metastasis in patients with gastric cancer (GC) and has an extremely poor prognosis. The detection of free cancer cells (FCCs) in the peritoneal cavity has been demonstrated to be one of the worst prognostic factors for GC. However, there is a lack of sensitive detection methods for FCCs in the peritoneal cavity. This study aimed to use a new peritoneal lavage fluid cytology examination to detect FCCs in patients with GC, and to explore its clinical significance on diagnosing of occult peritoneal metastasis (OPM) and prognosis. Methods: Peritoneal lavage fluid from 50 patients with GC was obtained and processed via the isolation by size of epithelial tumor cells (ISET) method. Immunofluorescence and fluorescence in situ hybridization (FISH) were used to identify FCCs expressing chromosome 8 (CEP8), chromosome 17 (CEP17), and epithelial cell adhesion molecule (EpCAM). Results: Using a combination of the ISET platform and immunofluorescence-FISH, the detection of FCCs was higher than that by light microscopy (24.0% vs. 2.0%). Samples were categorized into positive and negative groups, based on the expressions of CEP8, CEP17, and EpCAM. Statistically significant relationships were demonstrated between age (P = 0.029), sex (P = 0.002), lymphatic invasion (P = 0.001), pTNM stage (P = 0.001), and positivity for FCCs. After adjusting for covariates, patients with positive FCCs had lower progression-free survival than patients with negative FCCs. Conclusion: The ISET platform highly enriched nucleated cells from peritoneal lavage fluid, and indicators comprising EpCAM, CEP8, and CEP17 confirmed the diagnosis of FCCs. As a potential detection method, it offers an opportunity for early intervention of OPM and an extension of patient survival.

Training high-performance deep learning classifier for diagnosis in oral cytology using diverse annotations.

The uncertainty of true labels in medical images hinders diagnosis owing to the variability across professionals when applying deep learning models. We used deep learning to obtain an optimal convolutional neural network (CNN) by adequately annotating data for oral exfoliative cytology considering labels from multiple oral pathologists. Six whole-slide images were processed using QuPath for segmenting them into tiles. The images were labeled by three oral pathologists, resulting in 14,535 images with the corresponding pathologists' annotations. Data from three pathologists who provided the same diagnosis were labeled as ground truth (GT) and used for testing. We investigated six models trained using the annotations of (1) pathologist A, (2) pathologist B, (3) pathologist C, (4) GT, (5) majority voting, and (6) a probabilistic model. We divided the test by cross-validation per slide dataset and examined the classification performance of the CNN with a ResNet50 baseline. Statistical evaluation was performed repeatedly and independently using every slide 10 times as test data. For the area under the curve, three cases showed the highest values (0.861, 0.955, and 0.991) for the probabilistic model. Regarding accuracy, two cases showed the highest values (0.988 and 0.967). For the models using the pathologists and GT annotations, many slides showed very low accuracy and large variations across tests. Hence, the classifier trained with probabilistic labels provided the optimal CNN for oral exfoliative cytology considering diagnoses from multiple pathologists. These results may lead to trusted medical artificial intelligence solutions that reflect diverse diagnoses of various professionals.

Cytological features of ependymal and choroid plexus tumours.

Ependymal and choroid plexus tumours arise in anatomically related regions. Their intraoperative differential diagnosis is large and depends on factors such as age, tumour site and clinical presentation. Squash cytology can provide valuable information in this context. Cytological features of conventional ependymomas, subependymomas and myxopapillary ependymomas as well as choroid plexus tumours are reviewed and illustrated. Differential diagnostic considerations integrating morphological and clinical information are discussed.

A deep learning framework for predicting endometrial cancer from cytopathologic images with different staining styles.

Endometrial cancer screening is crucial for clinical treatment. Currently, cytopathologists analyze cytopathology images is considered a popular screening method, but manual diagnosis is time-consuming and laborious. Deep learning can provide objective guidance efficiency. But endometrial cytopathology images often come from different medical centers with different staining styles. It decreases the generalization ability of deep learning models in cytopathology images analysis, leading to poor performance. This study presents a robust automated screening framework for endometrial cancer that can be applied to cytopathology images with different staining styles, and provide an objective diagnostic reference for cytopathologists, thus contributing to clinical treatment. We collected and built the XJTU-EC dataset, the first cytopathology dataset that includes segmentation and classification labels. And we propose an efficient two-stage framework for adapting different staining style images, and screening endometrial cancer at the cellular level. Specifically, in the first stage, a novel CM-UNet is utilized to segment cell clumps, with a channel attention (CA) module and a multi-level semantic supervision (MSS) module. It can ignore staining variance and focus on extracting semantic information for segmentation. In the second stage, we propose a robust and effective classification algorithm based on contrastive learning, ECRNet. By momentum-based updating and adding labeled memory banks, it can reduce most of the false negative results. On the XJTU-EC dataset, CM-UNet achieves an excellent segmentation performance, and ECRNet obtains an accuracy of 98.50%, a precision of 99.32% and a sensitivity of 97.67% on the test set, which outperforms other competitive classical models. Our method robustly predicts endometrial cancer on cytopathologic images with different staining styles, which will further advance research in endometrial cancer screening and provide early diagnosis for patients. The code will be available on GitHub.