Comparison of Morphological Similarities and Differences between Liquid-Based Cytology and Conventional Techniques of Serous Effusion Cytology Specimens

Baykus, Nurhan; Özekinci, Selver; Erdem, Zeynep Betül; Vurgun, Eren; Yildiz, Fetin

doi:10.1159/000521052

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The problem with that approach is that Papanicolaou stains fade over time [43], so using old slides can hinder the quality of the obtained images. We also avoided using liquid-based cytology in this work since it can lead to the loss of markedly useful diagnostic background information including debris and inflammation [44,45].…”

Section: Discussionmentioning

confidence: 99%

A Novel Validated Real-World Dataset for the Diagnosis of Multiclass Serous Effusion Cytology according to the International System and Ground-Truth Validation Data

Abd-Almoniem,

Abd-Alsabour,

Elsheikh

et al. 2024

Acta Cytologica

View full text Add to dashboard Cite

Introduction: The application of artificial intelligence (AI) algorithms in serous fluid cytology is lacking due to the deficiency in standardized publicly available datasets. Here, we develop a novel public serous effusion cytology dataset. Furthermore, we apply AI algorithms on it to test its diagnostic utility and safety in clinical practice. Methods: The work is divided into three phases. Phase 1 entails building the dataset based on the multitiered evidence-based classification system proposed by the International System (TIS) of serous fluid cytology along with ground-truth tissue diagnosis for malignancy. To ensure reliable results of future AI research on this dataset, we carefully consider all the steps of the preparation and staining from a real-world cytopathology perspective. In phase 2, we pay special consideration to the image acquisition pipeline to ensure image integrity. Then we utilize the power of transfer learning using the convolutional layers of the VGG16 deep learning model for feature extraction. Finally, in phase 3, we apply the random forest classifier on the constructed dataset. Results: The dataset comprises 3,731 images distributed among the four TIS diagnostic categories. The model achieves 74% accuracy in this multiclass classification problem. Using a one-versus-all classifier, the fallout rate for images that are misclassified as negative for malignancy despite being a higher risk diagnosis is 0.13. Most of these misclassified images (77%) belong to the atypia of undetermined significance category in concordance with real-life statistics. Conclusion: This is the first and largest publicly available serous fluid cytology dataset based on a standardized diagnostic system. It is also the first dataset to include various types of effusions and pericardial fluid specimens. In addition, it is the first dataset to include the diagnostically challenging atypical categories. AI algorithms applied on this novel dataset show reliable results that can be incorporated into actual clinical practice with minimal risk of missing a diagnosis of malignancy. This work provides a foundation for researchers to develop and test further AI algorithms for the diagnosis of serous effusions.

show abstract

Section: Discussionmentioning

confidence: 99%

A Novel Validated Real-World Dataset for the Diagnosis of Multiclass Serous Effusion Cytology according to the International System and Ground-Truth Validation Data

Abd-Almoniem,

Abd-Alsabour,

Elsheikh

et al. 2024

Acta Cytologica

View full text Add to dashboard Cite

show abstract

Metastatic germ cell tumors in serous cavities and cerebrospinal fluid: A single‐center experience

Hou,

Collins,

Liang

et al. 2024

Cancer Cytopathology

View full text Add to dashboard Cite

BackgroundMetastatic germ cell tumors (GCTs) involving body cavity effusions and cerebrospinal fluid (CSF) are rare. Diagnosis is challenging because of limited morphological and clinicopathological information in the literature.MethodsA database search of our institution from 1990 to 2024 identified 27 cases of metastatic GCTs, comprising five pediatric and 22 adolescent and adult patients, in serous cavities or the CSF, including peritoneal (15), pleural (nine), CSF (two), and pericardial (one) fluid.ResultsThe most common primary site was the testis (n = 10), followed by the ovaries (n = 7), mediastinum (n = 4), retroperitoneum (n = 3), pineal gland (n = 2), and sacrum/coccyx (n = 1). The primary tumors in 14 patients were mixed GCTs (six with a seminoma component), followed by immature teratomas (six), yolk sac tumors (three), embryonal carcinomas (two), pure seminomas (one), and postpubertal teratomas (one). The median interval between primary tumor diagnosis and diagnosis of fluid positivity was 7 months (range: 0–134 months). In nine cases, the malignant fluid was diagnosed simultaneously with or within 1 month of the primary tumor. GCT subtyping was performed on 23 of the 27 cytological specimens. Twenty‐four patients (89%) also had metastases to other sites. Thirteen patients died of the disease (48%), with a median survival time of 4 months.ConclusionsMetastatic GCTs in serous effusions and CSF are often associated with disseminated disease and poor prognosis. Subtyping can be performed by cytomorphology combined with immunohistochemistry.

show abstract

Comparison of Morphological Similarities and Differences between Liquid-Based Cytology and Conventional Techniques of Serous Effusion Cytology Specimens

Cited by 2 publications

References 10 publications

A Novel Validated Real-World Dataset for the Diagnosis of Multiclass Serous Effusion Cytology according to the International System and Ground-Truth Validation Data

A Novel Validated Real-World Dataset for the Diagnosis of Multiclass Serous Effusion Cytology according to the International System and Ground-Truth Validation Data

Metastatic germ cell tumors in serous cavities and cerebrospinal fluid: A single‐center experience

Contact Info

Product

Resources

About