Liquid-based Cytology Samples Research Articles

Application of mass cytometry in multiparametric characterization of precancerous cervical lesions.

Cervical cancer (CC) is the fourth most common malignant tumor in women worldwide. Detecting different biomarkers together on single cells by novel method mass cytometry could contribute to more precise screening. Liquid-based cytology (LBC) cervical samples were collected (N = 53) from women categorized as normal and precancerous lesions. Human papillomavirus was genotyped by polymerase chain reaction, while simultaneous examination of the expression of 29 proteins was done by mass cytometry (CyTOF). Differences in cluster abundances were assessed with Spearman's rank correlation as well as high dimensional data analysis (t-SNE, FlowSOM). Cytokeratin (ITGA6, Ck5, Ck10/13, Ck14, Ck7) expression patterns allowed determining the presence of different cells in the cervical epithelium. FlowSOM analysis enabled to phenotype cervical cells in five different metaclusters and find new markers that could be important in CC screening. The markers Ck18, Ck18, and CD63 (Metacluster 3) showed significantly increasing associated with severity of the precancerous lesions (Spearman rank correlation rho 0.304, p = 0.0271), while CD71, KLF4, LRIG1, E-cadherin, Nanog and p53 (Metacluster 1) decreased with severity of the precancerous lesions (Spearman rank correlation rho -0.401, p = 0.0029). Other metaclusters did not show significant correlation, but metacluster 2 (Ck17, MCM, MMP7, CD29, E-cadherin, Nanog, p53) showed higher abundance in low- and high-grade intraepithelial lesion cases. CyTOF appears feasible and should be considered when examining novel biomarkers on cervical LBC samples. This study enabled us to characterize different cells in the cervical epithelium and find markers and populations that could distinguish precancerous lesions.

Advancing Precision Oncology: Whole-Exome Sequencing in Endometrial Cancer Liquid-Based Cytology.

Diagnostic strategies for endometrial cancer have been evolving, with cytologic analysis being considered a key method in integrated oncologic diagnostics because of its less invasive nature and adaptability to various assessments. Liquid-based cytology (LBC) has emerged as a promising method for intact DNA preservation; it exhibits improved efficiency in advanced sequencing applications such as next-generation sequencing. However, despite the use of LBC in panel assays, its application in whole-exome sequencing (WES) for comprehensive genomic profiling remains underexplored. To investigate whether molecular classification is possible based on WES using DNA derived from LBC specimens. We combined WES with targeted gene panel analysis to compare genomic findings of LBC and traditional tissue samples obtained from 7 cases of endometrial cancer. We investigated pathogenic mutations, tumor mutational burden, and microsatellite instability, and achieved molecular classification with high accuracy. We found a substantial concordance between LBC and traditional tissue samples in terms of pathogenic mutation detection, with a 95% match in the LBC samples and 94% in the tissue samples. Notably, our results highlight the importance of combining WES with panel-based analysis in identifying the ultramutated status of a case that had been missed during panel analysis. Our findings emphasize the potential of LBC samples in the precise and noninvasive genomic analysis of cases of endometrial cancer and offer a new avenue for developing diagnostic and therapeutic strategies in precision oncology.

P21-2 Detection of HPV from the residual of liquid-based cytology samples using multiplex digital PCR: a pilot study

P21-2 Detection of HPV from the residual of liquid-based cytology samples using multiplex digital PCR: a pilot study

Diagnostic and Predictive Immunocytochemistry in Lung Cancer

Background Immunocytochemistry (ICC) is suitable for use on a range of cytology preparations, such as cell blocks, air-dried slides, ethanol-fixed slides, direct smears, cytospins, and liquid-based cytology (LBC) samples. However, it must be standardized against the gold standard of formalin-fixed paraffin-embedded tissues with adequate number of positive and negative controls. The role of ICC in lung cancer is crucial, as most lung cancer specimens are cytology samples. Accurate diagnosis and testing of certain biomarkers rely heavily on both diagnostic and predictive ICC. Summary Key ICC markers important in lung cancer include, but are not limited to, diagnostic ICCs such as TTF-1, p40, Napsin A, and p63, as well as predictive ICCs like ALK, ROS-1, PD-L1, and NTRK. Key Messages With proper validation, immunocytochemistry for lung cancer can be effectively performed on direct smears, cytospins, and other specimens, even when resources for preparing cell blocks are unavailable. This is particularly true for diagnostic antibodies, but it is important to exercise caution with predictive immunocytochemistry. Nonetheless, a low threshold for molecular testing should be maintained. PD-L1 ICC can be challenging and should ideally be performed on formalin-fixed cell blocks or biopsies when available.

Artificial Intelligence Recognition Model Using Liquid-Based Cytology Images to Discriminate Malignancy and Histological Types of Non-Small-Cell Lung Cancer

Introduction: Artificial intelligence image recognition has applications in clinical practice. The purpose of this study was to develop an automated image classification model for lung cancer cytology using a deep learning convolutional neural network (DCNN). Methods: Liquid-based cytology samples from 8 normal parenchymal (N), 22 adenocarcinoma (ADC), and 15 squamous cell carcinoma (SQCC) surgical specimens were prepared, and 45 Papanicolaou-stained slides were scanned using whole-slide imaging. The final dataset of 9,141 patches consisted of 2,737 N, 4,756 ADC, and 1,648 SQCC samples. Densenet-121 was used as the DCNN to classify N versus malignant (ADC+SQCC) and ADC versus SQCC images. AdamW optimizer and 5-fold cross-validation were used in the training. Results: For malignancy prediction, the sensitivity, specificity, and accuracy were 0.97, 0.85, and 0.94, respectively, in the patch-level classification, and 0.92, 0.88, and 0.91, respectively, in the case-level classification. For SQCC prediction, the sensitivity, specificity, and accuracy were 0.86, 0.91, and 0.90, respectively, in the patch-level classification and 0.73, 0.82, and 0.78, respectively, in the case-level classification. Conclusion: The DCNN model performed excellently in predicting malignancy and histological types of lung cancer. This model may be useful for predicting cytopathological diagnosis in clinical situations by reinforcing training.

TP53 somatic evolution in cervical liquid-based cytology and blood from individuals with and without ovarian cancer and BRCA1 or BRCA2 germline mutations.

Somatic TP53 mutations are prevalent in normal tissue but little is known about their association with cancer risk. Cervical liquid-based cytology (LBC), commonly known as Pap test, provides an accessible gynecological sample to test the value of TP53 somatic mutations as a biomarker for high-grade serous ovarian cancer (HGSC), a cancer type mostly driven by TP53 mutations. We used ultra-deep duplex sequencing to analyze TP53 mutations in LBC and blood samples from 70 individuals (30 with and 40 without HGSC) undergoing gynecologic surgery, 30 carrying BRCA1 or BRCA2 germline pathogenic variants (BRCApv). Only 30% of the tumor mutations were found in LBC samples. However, TP53 pathogenic mutations were identified in nearly all LBC and blood samples, with only 5.4% of mutations in LBC (20/368) also found in the corresponding blood sample. TP53 mutations were more abundant in LBC than in blood and increased with age in both sample types. BRCApv carriers with HGSC had more TP53 clonal expansions in LBC than BRCApv carriers without cancer. Our results show that, while not useful for direct cancer detection, LBC samples capture TP53 mutation burden in the gynecological tract, presenting potential value for cancer risk assessment in individuals at higher hereditary risk for ovarian cancer.

Proof of Concept Study: Comparability of Microbiome Diversity in Self- and Physician-Collected HPV-Positive and HPV-Negative Cervicovaginal Samples.

Recent studies have revealed the impact of human papillomavirus (HPV) infections on the cervicovaginal microbiome; however, few have explored the utility of self-collected specimens (SCS) for microbiome detection, obtained using standardised methods for HPV testing. Here, we present a proof-of-concept analysis utilising Oxford Nanopore sequencing of the 16S rRNA gene in paired samples collected either by the patient using an Evalyn Brush or collected by a physician using liquid-based cytology (LBC). We found no significant differences in the α-diversity estimates between the SCS and LBC samples. Similarly, when analysing β-diversity, we observed a close grouping of paired samples, indicating that both collection methods detected the same microbiome features. The identification of genera and Lactobacillus species in each sample allowed for their classification into community state types (CSTs). Notably, paired samples had the same CST, while HPV-positive and -negative samples belonged to distinct CSTs. As previously described in other studies, HPV-positive samples exhibited heightened bacterial diversity, reduced Lactobacillus abundance, and an increase in genera like Sneathia or Dialister. Altogether, this study showed comparable results between the SCS and LBC samples, underscoring the potential of self-sampling for analysing the microbiome composition in cervicovaginal samples initially collected for HPV testing in the context of cervical cancer screening.

Integrity of RNA in long-term-stored cervical liquid-based cytology samples: implications for biomarker research.

Biobanks of cervical screening (LBC) samples annotated with disease status are an invaluable resource to support the development of tools for the risk stratification of disease. Although there is growing interest in the assessment of RNA-based biomarkers, little is known on the suitability and durability of stored clinical samples (commonly used in cervical screening) to support RNA-based research. RNA was extracted from 260 stored LBC samples. Storage at -80°C or -25°C allowed isolation of sufficient RNA for further analysis. RNA was found to be substantially degraded according to Agilent Bioanalyser data. Despite this, RT-qPCR was successful in 95% samples tested. These data suggest that biobanked LBC samples are suitable for RNA-based assessment even if stored for up to 14years.

Staining Pattern of Alcian Blue in Endometrial Cytology: Utility in Distinguishing Grade 1-Endometrial Endometrioid Carcinoma from Endometrial Glandular Stromal Breakdown.

In endometrial cytology, differentiating endometrial glandular stromal breakdown (EGBD) from endometrial endometrioid carcinoma (G1-EEC) is often difficult. In this study, we provided a new focus on chondroitin sulfate (CS), a major substrate component of the endometrial stroma, and assessed the diagnostic utility of Alcian Blue (AB) staining in the differential diagnosis in liquid-based cytological (LBC) samples. LBC specimens from 19 patients with a proliferative endometrium, 36 with EGBD, and 30 with G1-EEC who underwent endometrial cytology were stained with AB (pH 1.0), and their reactivity was observed. In addition, immunocytochemical staining of CS and CD31 was performed for five cases each to evaluate their interrelationship with blood vessels. Regarding the 30 G1-EEC cases, at least one of the three representative staining patterns was observed by AB staining: dot-like, microtubular, and finely branched linear patterns. Moreover, the inner portion of the tubular material observed by AB staining expressed CD31. Conversely, in the 36 EGBD cases, only five metaplastic clusters with irregular protrusions and condensed stromal clusters (CSCs) showed a dot-like positive pattern, and background CSCs did not show reactivity to AB staining in any of the cases. Furthermore, the vascular structure expressing CD31 in cell clusters was also unclear. We demonstrated that AB staining shows different staining patterns in G1-EEC and EGBD, reflecting their different tissue structures. Our data provide new insights into endometrial cell diagnosis changes and demonstrate that AB staining is a potential new diagnostic aid tool for the differentiation of G1-EEC from EGBD.

Human papillomavirus negative high grade cervical lesions and cancers: Suggested guidance for HPV testing quality assurance

BackgroundSome high-grade cervical lesions and cervical cancers (HSIL+) test negative for human papillomavirus (HPV). The HPV-negative fraction varies between 0.03 % and 15 % between different laboratories. Monitoring and extended re-analysis of HPV-negative HSIL+ could thus be helpful to monitor performance of HPV testing services. We aimed to a) provide a real-life example of a quality assurance (QA) program based on re-analysis of HPV-negative HSIL+ and b) develop international guidance for QA of HPV testing services based on standardized identification of apparently HPV-negative HSIL+ and extended re-analysis, either by the primary laboratory or by a national HPV reference laboratory (NRL). MethodsThere were 116 initially HPV-negative cervical specimens (31 histopathology specimens and 85 liquid-based cytology samples) sent to the Swedish HPV Reference Laboratory for re-testing. Based on the results, an international QA guidance was developed through an iterative consensus process. ResultStandard PCR testing detected HPV in 55.2 % (64/116) of initially “HPV-negative” samples. Whole genome sequencing of PCR-negative samples identified HPV in an additional 7 samples (overall 61.2 % HPV positivity). Reasons for failure to detect HPV in an HSIL+ lesion are listed and guidance to identify cases for extended re-testing, including which information should be included when referring samples to an NRL are presented. ConclusionMonitoring the proportion of and reasons for failure to detect HPV in HSIL+ will help support high performance and quality improvement of HPV testing services. We encourage implementation of QA strategies based on re-analysis of “HPV negative” HSIL+ samples.

Performance of BD Onclarity HPV assay on FLOQSwabs vaginal self-samples.

Human papillomavirus (HPV) testing on self-collected vaginal samples has been shown to improve women's participation to cervical cancer screening programs, particularly in regions with limited access to health care. Nevertheless, the introduction of self-sampling in cervical cancer screening programs requires prior clinical validation of the HPV assay in combination with a self-sample collection device, including also the laboratory workflow and automation required for high-throughput testing in screening. In this study, the performance of BD Onclarity HPV on FLOQSwab-collected vaginal self-samples has been compared to clinician-taken liquid-based cytology samples, to detect high-grade cervical intraepithelial neoplasia using two high-throughput platforms, BD Viper LT and BD COR. The study findings have shown a similar performance of BD Onclarity on testing self-collected samples, confirming the validation of the proposed pre-analytical and analytical protocols for their use in cervical cancer screening programs based on self-collected vaginal samples.

The detection of PD-L1 expression on liquid-based cytology in pleural effusion of lung adenocarcinoma and its prognostic evaluation: Between paired liquid-based cytology and cell block samples.

Programmed death-ligand 1 (PD-L1) expression levels measured by immunohistochemistry have been proven to predict the outcome of immunotherapy in lung adenocarcinoma (LUAD). However, data on PD-L1 expression on liquid-based cytology (LBC) in malignant pleural effusion (MPE) is scarce. This study cohort included 60 cases with MPE suffering from LUAD. PD-L1 SP263 assay was used for immunocytochemistry (ICC) on LBC and matched cell block (CB) to validate ICC protocols on LBC slides. Clinical outcomes were analyzed based on immunotherapy and PD-L1 tumor proportion scores (TPS) on LBC slides and CBs. PD-L1 expression with TPS ≥1% was lower in LBCs than in CBs (33 of 60 [55.0%] vs. 35 of 60 [58.3%]; p = .687). Even with the TPS ≥50% threshold, PD-L1 expression was lower in LBCs (10 of 60 [16.7%] vs. 15 of 60 [25%]; p = .125). Epidermal growth factor receptor (EGFR) exon 20 mutation, tumor cell proportion, and pleural fluid neutrophil-to-lymphocyte ratio were related to PD-L1 expression on CBs (p = .013, p = 0.022, and p = .011), respectively. Patients with subsequent immune checkpoint inhibitor therapy remained a better prognostic in subgroups of PD-L1 positive expression on LBC slides (TPS ≥1%, p = .041). LBC specimens had comparable performance to CBs in PD-L1 assessment and predicting treatment response to PD-L1-defined therapy.

Predictive Value of Various Atypical Cells for the Detection of Human Papillomavirus in Cervical Smears.

It is thought that numerous genotypes of human papillomavirus (HPV) are associated with various atypical cells, such as multinucleated cells, koilocytes, binucleated cells, parakeratotic cells, and giant cells, in the cervix. We previously showed the specificity of HPV genotypes for koilocytes and multinucleated cells. Therefore, in this study, we analyzed the association among HPV genotypes and binucleated cells, parakeratotic cells, and giant cells in Papanicolaou (Pap) smears. We detected HPV genotypes and atypical cells in 651 cases of liquid-based cytology with an abnormal Pap smear. The HPV genotypes associated with atypical cells were evaluated using stepwise logistic regression with backward elimination and a likelihood ratio test for model construction. Polymerase chain reaction was used to determine the HPV genotypes in whole liquid-based cytology samples and microdissected cell samples from Pap smear slides. Binucleated cells were significantly associated with HPV genotype 42. Moreover, parakeratotic cells were significantly associated with certain HPV genotypes, such as HPV40. However, it was difficult to detect specific HPV genotypes by the manual microdissection-polymerase chain reaction method despite the presence of binucleated cells and parakeratotic cells. Thus, the presence of binucleated cells, parakeratotic cells, and giant cells in Pap smears may not be predictive of cervical lesions above low-grade squamous intraepithelial lesions or infection with highly carcinogenic HPV genotypes.

A review of the directly sampled endometrial cytology on LBC samples: Classification, microscopic criteria and beyond.

The Yokohama System for Reporting Endometrial Cytology (TYS) has been proposed by an expert meeting under the auspices of the International Academy of Cytology (IAC) in May 2016 at the IAC in Yokohama. Since its introduction, the TYS has been receiving worldwide acceptance, and this review aims to assess its global impact. The adoption of endometrial cytology as a diagnostic procedure has been hampered in the past by difficulties arising in interpreting the cellular findings due to a number of factors (such as excess blood, cellular overlapping and the complex physiology of endometrium). Recently, the use of liquid-based cytology (LBC), with its ability to remove blood and mucus and to distribute cells uniformly in a thin layer on the slide, has provided an opportunity to re-evaluate the role of endometrial cytology. LBC is a useful tool in the cytologic diagnosis and follow-up of endometrial abnormalities, which remains complementary to the emerging molecular diagnostic cytopathology. The study of LBC from endometrial cytology could be challenging since it is affected by numerous look-alikes and diagnostic pitfalls. This review discusses these various entities and takes into consideration the ancillary techniques that may be useful in the diagnostic procedure. In conclusion, our review of the published data suggests that the TYS is a valid classification scheme that has been widely accepted by cytopathologists globally, is highly reproducible and makes a valuable contribution to clinical therapeutic management. At present, molecular cytopathology is a rapidly evolving field of modern cytopathology, which underlines the effective interplay between genomics and cytology. This review aims to provide a comprehensive review of the drawbacks of endometrial cytopathology, particularly in terms of endometrial cancer diagnosis and molecular testing.

Identification of cancer driver mutations in liquid-based cytology samples for the screening of endometrial diseases

BackgroundEndometrial cancer (EC) is one of the leading causes of cancer death among women and early detection is crucial for its successful treatment. We previously showed that cytological examination combined with genetic analysis using liquid-based cytology (LBC) samples improved the diagnostic sensitivity of EC.MethodsAmong 218 individuals who underwent endometrial screening by LBC, 208 samples were analysed by cancer-panel sequencing. Excluding 13 samples with low sequence coverage, we further analysed 195 samples.ResultsAmong the 195 women analysed, 39 and 15 were eventually shown to suffer from malignant endometrial and non-endometrial neoplasms, respectively. Driver mutation(s) were found in nine of the 15 cytology-negative patients with endometrial malignancy, corroborating that combination of cytological and genetic analyses should increase the sensitivity of the diagnosis of malignant endometrial neoplasms. Importantly, driver alterations were found in 32 of 125 women without malignant or premalignant diseases, which raises caution for the interpretation of genetic alterations detected in the endometrial samples. Comparison between the driver mutations in the 32 subjects and those in the 29 endometrial malignancies unveiled that the number of mutations and mutations in PTEN, CTNNB1, and TP53 may be applied for the assessment and prediction of development of EC.ConclusionsThe genetic analysis combined with liquid-based cytology is useful to improve the diagnostic sensitivity of endometrial neoplasms. However, caution must be taken when cancer-associated mutation(s) are detected in the genetic analysis. Further investigation may clarify the risk of malignant endometrial neoplasms in women with driver mutation(s).

Clinical performance of the novel full-genotyping OncoPredict HPV Quantitative Typing assay using the VALGENT framework.

Clinical validation of human papillomavirus (HPV) assays according to international criteria is prerequisite for their implementation in cervical cancer screening. OncoPredict HPV Quantitative Typing (QT) assay (Hiantis Srl, Milan, Italy) is a novel full-genotyping multiplex real-time PCR quantitative assay targeting E6/E7 genes, allowing individual viral load determination of 12 high-risk (HR) HPV types. Quality controls for sample adequacy, efficiency of nucleic acid extraction and PCR inhibition are included in the assay. Clinical performance of OncoPredict HPV QT test was assessed as part of the "Validation of HPV Genotyping Tests" (VALGENT-2) framework, consisting of 1300 cervical liquid-based cytology (LBC) samples of women aged between 20 and 60 years who had originally attended for routine cervical screening in Scotland. The clinical accuracy of the OncoPredict HPV QT (index test) for the detection of CIN2+ was assessed relative to the GP5+/6+ Enzyme ImmunoAssay (GP5+/6+ EIA) (comparator test), using noninferiority criteria. Intra- and interlaboratory reproducibility of the assay was assessed on a subpopulation, comprising 526 samples. The relative sensitivity and specificity for OncoPredict HPV QT vs GP5+/6+-PCR-EIA were 1.01 (95% CI: 0.99-1.03) and 1.03 (95% CI: 1.0-1.06) respectively. The P-values for noninferiority were ≤0.001. The intra- and inter-laboratory reproducibility demonstrated a high concordance (>98.7%) with kappas for individual types ranging from 0.66 to 1.00. OncoPredict HPV QT fulfills the international validation criteria for the use of HPV tests in cervical cancer screening.

Exploring the prevalence of Human Papillomavirus (HPV) genotypes in PAP smear samples of women in northern region of United Arab Emirates (UAE): HPV Direct Flow CHIP system-based pilot study.

The aim of this study was to explore the prevalence of low and high-risk HPV genotypes in PAP smear samples of women in northern region of the UAE using HPV direct flow CHIP method. A cross-sectional retrospective study was conducted between September 2021 to April 2022. A total of 104 liquid-based cervical cytology samples were obtained from women aged 20-59 years attending the Gynaecology out-patient department of Thumbay University Hospital and other hospitals of Northern Emirates of UAE, processed for the routine cytological examination to identify and differentiate morphological changes of the PAP smear samples. HPV genotyping was performed using HPV direct flow CHIP method. In total, 112 HPV genotypes were detected in 63 women (60.57%) included 18 abnormal cytological and 45 normal epithelial samples. 63 LR and 49 HR HPV genotypes were identified in all the 63 positive samples. Highest rate of infection with multiple LR and HR HPV genotypes were detected in women aged 40-49 years (25.9%) and 20-29 years (23.5%). Infection by HPV6 (13.46%), HPV11 (9.61%), HPV16 (9.61%), HPV62/81 (7.69%) and HPV45 (7.69%) were the most common genotypes. A moderate increase than expected incidence of HPV45 and 62/81 (7.69%) were detected. Co-infection with multiple low and high-risk genotypes is present in 20.2% cases; in that, HPV6 (15.9%) was the most common followed by HPV62/81 (12.7%) and HPV16 (11.11%). The prevalence of HPV18 was found to be 1.6%. The genotypes 6, 45, 16, 11, 67, 62/81 were the most common HPV infections in the women between the age group of 21 and 59-years-old. A moderate increase of HPV45, 62/81 and much less prevalence of HPV18 were detected in the study population. 43.27% of the normal epithelia were positive to different low and high-risk HPV genotypes. This finding highlights the importance of molecular genotyping of HPV to emphasize the cervical screening triage.

Genotypic characterization of HPV serotypes in cervical samples from Indian women: a multi centric study.

Human papilloma virus (HPV infection) plays a important role in causing cervical cancer. Out of 184 different HPV genotypes, 40 diverse types only can cause anogenital infection. HPV present in >99% of cervical cancers with high risk types (16, 18) associated with cancer and Low risk types (6, 11) are associated with genital warts. Aim of the study is to determine the epidemiology of HPV infection in Indian women's population. Three hundred and thirty four liquid based cytology (LBC) samples were collected across India from the different age groups of Indian women. Pap smear, PCR and gene sequencing tests were performed for the collected LBC samples. Low risk serotype 6 (16.7%) were detected compared to other high risk serotypes. Majority of positive cases were observed in the age group between 19 and 39 groups. Northern part of India contributes high (7.1%) in HPV infection compared to other regions of India. Reports from these studies covered few regions of India showing a wide range in the prevalence of HPV infection and serotype distribution due to diversified socio economic and geo climatic conditions. This study aims to identify the epidemiology of HPV in the Indian population and concludes that early and periodic screening of women for HPV can avoid the risk of cervical cancer at the early stage of infection.

Improving Mobile-Based Cervical Cytology Screening: A Deep Learning Nucleus-Based Approach for Lesion Detection

Liquid-based cytology (LBC) plays a crucial role in the effective early detection of cervical cancer, contributing to substantially decreasing mortality rates. However, the visual examination of microscopic slides is a challenging, time-consuming, and ambiguous task. Shortages of specialized staff and equipment are increasing the interest in developing artificial intelligence (AI)-powered portable solutions to support screening programs. This paper presents a novel approach based on a RetinaNet model with a ResNet50 backbone to detect the nuclei of cervical lesions on mobile-acquired microscopic images of cytology samples, stratifying the lesions according to The Bethesda System (TBS) guidelines. This work was supported by a new dataset of images from LBC samples digitalized with a portable smartphone-based microscope, encompassing nucleus annotations of 31,698 normal squamous cells and 1395 lesions. Several experiments were conducted to optimize the model’s detection performance, namely hyperparameter tuning, transfer learning, detected class adjustments, and per-class score threshold optimization. The proposed nucleus-based methodology improved the best baseline reported in the literature for detecting cervical lesions on microscopic images exclusively acquired with mobile devices coupled to the µSmartScope prototype, with per-class average precision, recall, and F1 scores up to 17.6%, 22.9%, and 16.0%, respectively. Performance improvements were obtained by transferring knowledge from networks pre-trained on a smaller dataset closer to the target application domain, as well as including normal squamous nuclei as a class detected by the model. Per-class tuning of the score threshold also allowed us to obtain a model more suitable to support screening procedures, achieving F1 score improvements in most TBS classes. While further improvements are still required to use the proposed approach in a clinical context, this work reinforces the potential of using AI-powered mobile-based solutions to support cervical cancer screening. Such solutions can significantly impact screening programs worldwide, particularly in areas with limited access and restricted healthcare resources.

Cytological features of oral malignant lymphoma in scraping liquid-based cytology: Cases of plasmablastic lymphoma and anaplastic lymphoma kinase-positive anaplastic large cell lymphoma

The main purpose of cytological examination in the oral region is to screen for squamous cell carcinoma or intraepithelial neoplasms; thus, the background tends to be considered a deterrent for microscopy. From this perspective, liquid-based cytology (LBC) is favorable for preparing clear samples with few backgrounds. However, background hemocytes are sometimes of critical importance in the diagnosis. We report two cases of oral malignant lymphoma, plasmablastic lymphoma, and anaplastic large cell lymphoma in which careful observation of the background in scraping LBC sample contributed to the early diagnosis. Atypical lymphoid cells were observed only in a very small part of the LBC samples from the presented patients; however, cytological findings, such as large lymphoid cells with outstanding nucleoli, large mitotic cells, or intermediate-to-large lymphoid cells with pleomorphic nuclei were sufficient for obtaining a cytological diagnosis of malignant lymphoma. Although the number and cell size of leukocytes in LBC with Papanicolaou staining were significantly different from those in air-dried conventional smears with Romanovsky staining, which are commonly preferred for the discrimination of hemocytes, the corresponding cytological features could be observed. Therefore, attention should be paid to the background as well as squamous epithelium to prepare for such unexpected cases. The LBC examination with Papanicolaou staining alone can suggest the possibility of malignant lymphoma.