Clinical evaluation of an artificial intelligence-assisted cytological system among screening strategies for a cervical cancer high-risk population.

BACKGROUND: Primary cervical cancer screening and treating precancerous lesions are effective ways to prevent cervical cancer. However, the coverage rates of human papillomavirus (HPV) vaccines and routine screening are low in most developing countries and even some developed countries. This study aimed to explore the benefit of an artificial intelligence-assisted cytology (AI) system in a screening program for a cervical cancer high-risk population in China. METHODS: A total of 1231 liquid-based cytology (LBC) slides from women who underwent colposcopy at the Chinese PLA General Hospital from 2018 to 2020 were collected. All women had received a histological diagnosis based on the results of colposcopy and biopsy. The sensitivity (Se), specificity (Sp), positive predictive value (PPV), negative predictive value (NPV), false-positive rate (FPR), false-negative rate (FNR), overall accuracy (OA), positive likelihood ratio (PLR), negative likelihood ratio (NLR) and Youden index (YI) of the AI, LBC, HPV, LBC + HPV, AI + LBC, AI + HPV and HPV Seq LBC screening strategies at low-grade squamous intraepithelial lesion (LSIL) and high-grade squamous intraepithelial lesion (HSIL) thresholds were calculated to assess their effectiveness. Receiver operating characteristic (ROC) curve analysis was conducted to assess the diagnostic values of the different screening strategies. RESULTS: The Se and Sp of the primary AI-alone strategy at the LSIL and HSIL thresholds were superior to those of the LBC + HPV cotesting strategy. Among the screening strategies, the YIs of the AI strategy at the LSIL + threshold and HSIL + threshold were the highest. At the HSIL + threshold, the AI strategy achieved the best result, with an AUC value of 0.621 (95% CI, 0.587-0.654), whereas HPV testing achieved the worst result, with an AUC value of 0.521 (95% CI, 0.484-0.559). Similarly, at the LSIL + threshold, the LBC-based strategy achieved the best result, with an AUC of 0.637 (95% CI, 0.606-0.668), whereas HPV testing achieved the worst result, with an AUC of 0.524 (95% CI, 0.491-0.557). Moreover, the AUCs of the AI and LBC strategies at this threshold were similar (0.631 and 0.637, respectively). CONCLUSIONS: These results confirmed that AI-only screening was the most authoritative method for diagnosing HSILs and LSILs, improving the accuracy of colposcopy diagnosis, and was more beneficial for patients than traditional LBC + HPV cotesting.

The International System for Reporting Serous Fluid Cytopathology: A Systematic Review and Meta-Analysis of Diagnostic Test Accuracy Studies.

This is the first systematic review and meta-analysis of The International System (TIS) for reporting serous fluid cytopathology. Our aims were to present the pooled malignancy rate of each TIS reporting category and the diagnostic accuracy of cytology using this system. Database search using a predefined strategy was followed by study selection, data extraction, study quality assessment, and statistical analysis. Data derived from 16 eligible studies were pooled. The pooled rates of malignancy were as follows: 27% (95% CI; 16%-41%) for "nondiagnostic" (ND), 11% (95% CI; 7%-18%) for negative for malignancy" (NFM), 49% (95% CI; 37%-61%) for "atypia of undetermined significance" (AUS), 90% (95% CI; 81%-95%) for "suspicious for malignancy" (SFM), and 100% (95% CI; 98%-100%) for "positive for malignancy" (MAL). Studies performed exclusively in cancer hospitals showed higher pooled malignancy rates, compared with academic and community hospitals serving the general population, in the ND [40% (95% CI; 21%-62%) vs. 22% (95% CI; 11%-39%)], NFM [20% (95% CI; 13%-30%) vs. 9% (95% CI; 5%-17%)], and AUS categories [55% (95% CI; 47%-63%) vs. 46% (95% CI; 31%-62%)]. Notably, the difference was significant in the NFM category ( P =0.04). When both SFM and MAL cytology interpretations were considered as malignant outcomes, the pooled sensitivity and specificity were 68.74% (95% CI; 59.90%-76.39%) and 98.81% (95% CI; 98.18%-99.22%), respectively. In addition, the diagnostic odds ratio (DOR) was found to be 170.7 (95% CI; 96.2-303.3). Despite its strengths, our study also had some limitations. Therefore, future large-scale longitudinal studies could strengthen the findings of this review.

Consistency in the Distribution of Bethesda System for Reporting Thyroid Cytology Categories Over 9 Years: A Single Institute, Retrospective Study.

BACKGROUND: The Bethesda System for Reporting Thyroid Cytopathology (BSRTC) has evolved since it was first introduced in 2009 to become a worldwide accepted cytologic analysis reference, due to its simplicity and reproducibility. To date, the consistency of BSRTC throughout time has yet to be investigated. METHODS: Retrospective single institution case series with chart review of all patients who underwent fine-needle aspirations for a thyroid nodule in our institution between the years 2010 and 2018 with a documented BSRTC classification. Data collection included demographics, risk factors, sonographic evaluation, nodule size, and final pathology when feasible. The main outcome is the difference in the rates of BSRTC categories benign, atypia of undetermined significance (AUS), follicular neoplasm, suspicious for malignancy, and malignant (BSRTC II-VI, respectively) between the study years. RESULTS: A total of 2830 thyroid nodules were included. BSRTC II-VI distribution was 83.9% (2373), 8.2%, (232), 2.7% (75), 3.3% (93), and 2.0% (57), respectively. There was no significant change in the overall trend of each BSRTC category distribution throughout the study. There was a significant increase in the benign cytology rate (BSRTC II) in 2011 compared to 2015 and 2018 (76.4% compared to 88.7% and 87.6%, respectively. P < .005) alongside a significant decline in the AUS category rate (BSRTC III) between the same years (13.0% compared to 4.8% and 5.5%, respectively. P < .005). CONCLUSION: BSRTC showed consistency throughout the study across all observed categories. An overlap between AUS and benign may exist, possibly due to the heterogenic definition of AUS as reflected in the 2023 BSRTC subclassification for AUS.

Knowledge of cytology results affects the performance of colposcopy: a crossover study.

OBJECTIVE: To determine whether knowledge of cytology affects the colposcopist's diagnostic accuracy in the identification of cervical intraepithelial neoplasia grade 2 and worse (≥ CIN2). METHOD: In this cross-over study, healthcare professionals interpreted colposcopy images from 80 patient cases with known histological diagnoses. For each case, 2 images taken with a colposcope were provided (native and after acetic acid application). Inclusion criteria consisted of women with a transformation zone type 1 or 2, who had both a cytological and histological diagnosis. Cases were distributed across two online surveys, one including and one omitting the cytology. A wash-out period of six weeks between surveys was implemented. Colposcopists were asked to give their diagnosis for each case as < CIN2 or ≥ CIN2 on both assessments. Statistical analysis was conducted to compare the two interpretations. RESULTS: Knowledge of cytology significantly improved the sensitivity when interpreting colposcopic images, from 51.1% [95%CI: 39.3 to 62.8] to 63.7% [95%CI: 52.1 to 73.9] and improved the specificity from 63.5% [95%CI: 52.3 to 73.5] to 76.6% [95%CI: 67.2 to 84.0]. Sensitivity was higher by 38.6% when a high-grade cytology (ASC-H, HSIL, AGC) was communicated compared to a low-grade cytology (inflammation, ASC-US, LSIL). Specificity was higher by 31% when a low-grade cytology was communicated compared to a high-grade. CONCLUSIONS: Our data suggests that knowledge of cytology increases sensitivity and specificity for diagnosis of ≥ CIN2 lesions at colposcopy. Association between cytology and histology may have contributed to the findings.

Preoperative predictive factors for positive peritoneal cytology results in patients with pancreatic ductal adenocarcinomas: a retrospective study.

BACKGROUND: The clinical importance of positive peritoneal cytology results in patients with pancreatic ductal adenocarcinomas remains controversial. We evaluated the prognosis of these patients and the predictive preoperative risk factors for positive peritoneal cytology results. METHODS: We retrospectively reviewed patients who underwent curative-intent surgery at our institution between May 2010 and June 2020. Preoperative risk factors for positive peritoneal cytology results were identified using logistic regression analysis. A scoring model was constructed using the total number of significant independent predictors for positive peritoneal cytology results. RESULTS: Of 233 patients, 18 (7.7%) had positive peritoneal cytology results. The recurrence-free survival and cancer-specific survival were markedly worse in patients with positive peritoneal cytology results than in those with negative peritoneal cytology results (recurrence-free survival: 6.0 months vs. 16.6 months, p = 0.050; cancer-specific survival: 19.4 months vs. 47.5 months, p = 0.034). Tumor location (odds ratio: 3.760, 95% confidence interval: 1.099-11.818, p = 0.023), tumor size > 25 mm (odds ratio: 3.410, 95% confidence interval: 1.031-11.277, p = 0.046), preoperative serosal invasion (odds ratio: 5.193, 95% confidence interval: 1.099-24.531, p = 0.038), and preoperative carcinoembryonic antigen level > 5.6 ng/mL (odds ratio: 3.816, 95% confidence interval: 1.248-10.667, p = 0.019) were identified as significant independent predictive factors. Our predictive model's optimal cutoff and positive predictive values for positive peritoneal cytology results were 3 and 27.9%, respectively. CONCLUSIONS: The indications for curative-intent surgery should be considered carefully in patients with high-risk factors for positive peritoneal cytology results.

Diagnostic clues and pitfalls in salivary gland fine-needle aspiration cytology.

Salivary gland tumors (SGT) display morphological diversity and pose diagnostic challenges. Preoperative fine needle aspiration cytology (FNAC) is a minimally invasive and efficient diagnostic test. However, due to the limited sample size, the final diagnosis may not be established based on FNAC alone. Although cytomorphology and architecture are usually preserved on FNAC, morphologic changes specific to FNAC can complicate the diagnosis. The Milan System for Reporting Salivary Gland Cytopathology categorizes complex FNAC interpretations. Because the cytological diagnosis is closely linked to the histological diagnosis, a multidimensional approach considering the possibility of several differential diagnoses is necessary. From the standpoint of treatment, distinguishing high-grade malignancy from low-grade malignancy is more important than distinguishing malignancy from benign tumors.

The efficacy and assessment value of the level of thyroglobulin wash-out after fine-needle aspiration cytodiagnosis in the evaluation of lymph node metastasis in papillary thyroid carcinoma.

OBJECTIVE: The purpose of this study was to evaluate the efficacy and clinical value of US, FNAC,FNA-Tg and FNAC + FNA-Tg, as well as the cutoff values of FNA-Tg to evaluate LN metastasis. METHODS: We analyzed the diagnostic value of different US signs, the efficiency of US, FNAC, FNA-Tg and FNAC + FNA-Tg among the LN- and LN + groups, and the cutoff value of FNA-Tg to evaluate LN metastasis. We punctured LNs multiple times and measured the levels of FNA-Tg. Furthermore, the LNs were marked with immunohistochemical Tg and LCA to distinguish the presence of Tg in the para-cancerous tissue of the LNs. RESULTS: The s-Tg and FNA-Tg of the LN + group were higher than those of the LN- group (P = 0.018, ≤ 0.001). The LN + group had more abnormal US signs than the LN- group. The cutoff value of FNA-Tg was 3.2 ng/mL. US had a high sensitivity (92.42), but the specificity was not satisfactory (55.1). FNA-Tg had a higher sensitivity (92.42 vs. 89.39), specificity (100 vs. 93.88), and accuracy (92.42 vs. 83.27) than FNAC. However, the sensitivity of FNAC + FNA-Tg increased further, while the specificity and accuracy decreased slightly. The presence of Tg in the normal lymphocytes adjacent to the cancer was confirmed. CONCLUSION: Ultrasonography provides a noninvasive, dynamic, multidimensional assessment of LNs. With a cutoff value of 3.2 ng/mL, FNA-Tg has higher accuracy and a lower false-negative rate than various single diagnoses. However, FNAC combined with FNA-Tg does not cause additional pain to patients and offers a higher diagnostic efficacy and clinical value.

Some uncommon cystic lesions in the anterior head and neck region: Pitfalls to be avoided on cytology.

Cystic lesions of the anterior head and neck region are a challenging and frequent finding on cytological smears. The scant amount of cellular material in cystic slides poses the greatest difficulty to interpretation, so that frequently they are diagnosed as inadequate or with minimal cellular component. Despite the majority of cystic lesions being benign, a minor portion consist of malignant cystic entities. In these latter cases, the evidence of very scant malignant cells can be misdiagnosed and/or underestimated, leading to a false negative diagnosis. Many papers have already described and detailed the range of possible benign and malignant cystic lesions in head and neck. In the current review we have focused on the less common entities that often lead to serious misinterpretation.

Cytology of a parietal swelling in a 52-year-old man.

Primary FNA diagnosis of brown tumour is challenging because overlapping of cytomorphologic features with other giant cell lesions. Clinical information, imaging and laboratory tests benefits the correct diagnosis.

Interobserver variability in cytopathology: How much do we agree?

Interobserver variability remains a major challenge for cytopathologists despite the development of standardized reporting and classification systems. Indeed, whereas moderate-to-good interobserver agreement is generally achievable when the differential diagnosis between benign and malignant entities is straightforward, high levels of variability make the diagnostic interpretation of atypical and suspicious samples not consistent. This review explores the landscape of interobserver agreement in cytopathology across different anatomical sites.

World Health Organization reporting system for lung cytopathology-A brief correspondence.

The WHO lung cytopathology reporting system has been published recently and is now a five-tier category system without any subcategorization. WHO reporting system also encourages the application of ancillary diagnostic tests like cell block preparation, immunocytochemistry, and rapid on-site evaluation for better categorization of specimens and further management. This correspondence aims to provide a brief outline of the lung reporting system. Lung cytopathology reporting system use standardized nomenclature and usage of the terminologies harmonizing with the WHO Blue Book, and table and flow diagram may be helpful for the readers.

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.

Second edition of the Milan System for Reporting Salivary Gland Cytopathology: Refining the role of salivary gland FNA.

The use of standardised reporting systems for non-gynaecologic cytopathology has made enormous gains in popularity during the past decade, including for thyroid fine-needle aspiration, urine cytology, serous effusions, pancreas, lymph nodes, lung and more. In February 2018, the first edition of the Atlas of the Milan System for Reporting Salivary Gland Cytopathology (MSRSGC) was published. The MSRSGC defines six diagnostic fine-needle aspiration categories encompassing the spectrum of non-neoplastic, benign and malignant lesions of the salivary glands. The goal of the MSRSGC is to combine each diagnostic category with a defined risk of malignancy and a specific clinical and/or surgical management algorithm. Since its initial publication in 2018, more than 200 studies and commentaries have been published, confirming the role of the MSRSGC. The second edition of the MSRSGC, published in July 2023, includes refined risks of malignancy based on systematic reviews and meta-analyses, a new chapter summarising the use of salivary gland imaging, new advances in ancillary testing and updates in nomenclature.

Review of the impact of the International System for Serous Fluid Cytopathology.

The International System for Reporting Serous Fluid Cytology (TIS) has been proposed by an expert working team composed of the International Academy of Cytology and the American Society of Cytopathology, following an international survey. Since its introduction, the TIS has gained worldwide acceptance, and this review aims to assess its global impact. A literature search revealed 25 studies which have presented data on the impact of the TIS. Most of them provide data, including risk of malignancy (ROM) for each diagnostic category, separately for pleural, peritoneal and pericardial effusions, while a few do not separate them. A few studies focus on specific diagnoses like mesothelioma on specific types of fluids or more specific issues like the optimal fluid volume for cytology or interobserver variability. A synopsis of the data from the literature search is presented in four tables. The ROM assessment is discussed, as well as interobserver variability and the use of ancillary diagnostic immunochemistry. In conclusion, our review of the published data suggests that the TIS is a valid classification scheme that has been widely accepted by pathologists globally, is highly reproducible and makes a valuable contribution to clinical therapeutic management.

The urgency of Burkitt lymphoma diagnosis in fluid cytology-A tertiary care experience.

BACKGROUND: Burkitt lymphoma (BL) is an aggressive high-grade B-cell non-Hodgkin lymphoma commonly diagnosed in young age and is known to involve extra nodal sites. But the involvement of body fluids by BL is an uncommon presentation. Rapid diagnosis of BL is vital to prevent complications like tumour lysis syndrome. Cytological examination of body fluids continues to be an indispensable tool for rapid diagnosis of BL. OBJECTIVES: In this study, we aim to study the clinical, cytomorphological and immunophenotypic characteristics of BL involving serous effusions and other fluids. MATERIALS AND METHODS: In this retrospective study, 17 cases reported as BL in fluid cytology from 2016 to 2022 were collected and reviewed. We performed a comprehensive analysis of the clinical data, cytomorphological features, immunophenotyping data along with the haematological workup of these cases. We have also compared with the histopathological diagnosis for those cases where biopsy was available. RESULTS: BL more commonly involved ascitic fluid (52%), followed by pleural fluid (4 cases) and cerebrospinal fluid (CSF; 4 cases). Primary diagnosis of BL in fluid was done in 88% of the cases. Bone marrow involvement was noted in two cases. Cytological smears showed discrete monomorphous population of medium-sized atypical lymphoid cells with frequent apoptotic bodies. Classic cytoplasmic punched out vacuoles were observed in 88% of the cases. Immunophenotyping data was available for 12 cases in which tumour cells showed positivity for CD20 (100%), CD10 (4 of 7 cases), BCL6 (3 of 5 cases) and cMYC (7 of 7 cases-100%) and were negative for Terminal deoxynucleotidyl transferase (TdT) (11 of 11 cases). Mean Ki67 labelling index was 95%. Histopathological diagnosis was available for 9 cases, and there was 100% agreement between cytological and histopathological diagnosis in 7 cases. CONCLUSION: Precise diagnosis of BL can be rendered in body fluids by identification of classic cytomorphological features and by performing supportive ancillary tests in fluids for immunophenotyping.

Myelomatous meningitis diagnosed by cerebrospinal fluid cytology examination.

Myelomatous meningitis diagnosed by CSF cytology. The combined use of cytology with immunocytochemistry can identify the presence of multiple myeloma cells in cerebrospinal fluid specimens.

Cytological diagnosis of pineoblastoma in cerebrospinal fluid.

A rare case of pineoblastoma on cerebrospinal fluid cytology was reported in a 15-year-old girl. In the current paper, a rare case of pienoblastoma on CSF cytology has been described.

Artificial intelligence algorithm accurately assesses oestrogen receptor immunohistochemistry in metastatic breast cancer cytology specimens: A pilot study.

OBJECTIVE: The Visiopharm artificial intelligence (AI) algorithm for oestrogen receptor (ER) immunohistochemistry (IHC) in whole slide images (WSIs) has been successfully validated in surgical pathology. This study aimed to assess its efficacy in cytology specimens. METHODS: The study cohort comprised 105 consecutive cytology specimens with metastatic breast carcinoma. ER IHC WSIs were seamlessly integrated into the Visiopharm platform from the Image Management System (IMS) during our routine digital workflow, and an AI algorithm was employed for analysis. ER AI scores were compared with pathologists' manual consensus scores. Optimization steps were implemented and evaluated to reduce discordance. RESULTS: The overall concordance between pathologists' scores and AI scores was excellent (99/105, 94.3%). Six cases exhibited discordant results, including two false-negative (FN) cases due to abundant histiocytes incorrectly counted as negatively stained tumour cells by AI, two FN cases owing to weak staining, and two false-positive (FP) cases where pigmented macrophages were erroneously counted as positively stained tumour cells by AI. The Pearson correlation coefficient of ER-positive percentages between pathologists' and AI scores was 0.8483. Optimization steps, such as lowering the cut-off threshold and additional training using higher input magnification, significantly improved accuracy. CONCLUSIONS: The automated ER AI algorithm demonstrated excellent concordance with pathologists' assessments and accurately differentiated ER-positive from ER-negative metastatic breast carcinoma cytology cases. However, precision in identifying tumour cells in cytology specimens requires further enhancement.

Optic nerve pilomyxoid astrocytoma: Intraoperative squash smear cytology of a rare entity.

Pilomyxoid astrocytoma [PMA] is a rare, recently described variant of pilocytic astrocytoma with unique clinical and histopathological characteristics. It typically affects the optico-chiasmatic and hypothalamic region in infants and young children. Though the pilocytic astrocytoma is the commonest tumor of the optic nerve, pilomyxoid astrocytoma arising from the intraorbital part of the optic nerve is extremely rare. To the best of our knowledge, only one case of introrbital optic nerve pilomyxoid astrocytoma has been described in the English literature. We report two cases of pilomyxoid astrocytoma arising from the intraorbital optic nerve, diagnosed on intraoperative squash smear cytology and later confirmed on histopathology. Like in other locations, optic nerve pilomyxoid astrocytoma behaves in an aggressive manner.

Immunocytochemical markers, molecular testing and digital cytopathology for aspiration cytology of metastatic breast carcinoma.

Fine-needle aspiration cytology (FNAC) is a versatile diagnostic procedure uniquely suited for tissue biopsy of breast carcinomas and axillary metastases and/or recurrences. With the expanding treatment options and accompanying theragnostic tests, it is crucial to recognize the developments on ancillary testing and digital cytopathology techniques related to aspiration cytology of metastatic breast carcinoma. In this review, we aim to summarize and update the evidence of immunocytochemistry, for the detection of carcinoma cells (epithelial markers), confirmation of breast primary (breast-specific markers), assessment of surrogate immunostains (hormone receptors, ki-67 proliferative index and HER2) and theragnostic biomarkers, with discussion on potential diagnostic pitfalls, followed by the application of molecular tests, and digital cytopathologic techniques for assessing metastatic breast carcinoma in cytology.