Cytology Slides Research Articles

Artificial intelligence algorithms enhance urine cytology reporting confidence in postoperative follow-up for upper urinary tract urothelial carcinoma.

In Taiwan, the incidence of urothelial carcinoma of the upper urinary tract (UTUC) is high and intravesical recurrence is approximately 22%-47%. Thus, postoperative cystoscopy and urine cytology follow-up, which require experienced cytologists, are needed. The AIxURO system aligns with The Paris System (TPS) guidelines for reporting urinary cytology. This study assessed the benefit of early detection of intravesical recurrence after nephroureterectomy using the AIxURO system. Urine cytology slides (n = 296) from 113 patients with UTUC were retrieved and patient data, pre-operative and postoperative cytology, pathology, and follow-up series for the intravesical recurrence group were collected. Cytology slides were digitized and independently assessed by the AIxURO system, and the results were compared to cytology reports. From January 2022 to August 2023, 113 patients with UTUC underwent nephroureterectomy. Eighty-eight patients (88/113, 77.8%) received 1 or 2 cytology examinations pre-operatively, 44 slides (44/204, 21.5%) were positive and 34 patients (34/113, 30.1%) were diagnosed with UTUC. Postoperative intravesical recurrence was detected in 27 patients (27/113, 23%) at an average of 190.62days. Thirty-four slides (34/56, 60.7%) were negative for UTUC. Eight patients (8/27, 29.6%) met the criteria for early diagnosis of intravesical recurrence. The AIxURO system identified two more patients (10/27, 37.0%) with early intravesical recurrence. The AIxURO system enhanced postoperative urine cytology reporting confidence and could identify some underdiagnosed slides to enhance the early detection of UTUC with intravesical recurrence. AIxURO may be used for post-nephroureterectomy follow-up and reduce the necessity for cystoscopy.

Pitfalls in Diagnosis of Myoepithelial Carcinoma of Salivary Glands: A Study of 3 Cases with Cytologic-histologic Correlation and Molecular Analysis.

Myoepithelial carcinoma (MECA) represents < 1% percent of salivary gland (SG) tumors with a mean age of 55 years. These tumors can arise de novo or in association with pre-existing pleomorphic Adenoma (PA). The cytologic features of MECA overlap with other SG neoplasms including the more common benign entities like PA and myoepithelioma and can pose a diagnostic challenge. A database search for MECA was performed spanning 10 years. 3 cases qualified with available cyto-histologic correlation. All were morphologically MECA with one case diagnosed as MECA ex-PA. The cases were subjected to a comprehensive immunohistochemical and molecular evaluation (Case#1 has been previously reported and published in head and neck pathology in 2021). A comparative analysis of these cases is presented in Table1. All three cases were initially diagnosed as PA on cytology. On review of cytology slides, presence of metachromatic stromal fragments and bland myoepithelial cells was found to be the most common diagnostic pitfall. S100 was positive in all cases while myosin, p63, and GFAP were variably positive. Molecular analysis revealed novel, previously undescribed mutations in the three cases. Additionally, two of three cases expressed PD-L1, suggesting a role for immunotherapy in treatment. Cytomorphology of MECA is poorly described in literature and can pose a diagnostic challenge due to overlapping features with salivary gland benign neoplasms. A conclusive diagnosis on cytology is often not possible. However, a high cellularity, predominant oncocytoid/ myoepithelial cell population on smears and cell block, along with a strong clinical and radiologic suspicion for malignant salivary gland tumor, should alert the cytopathologist and help avoid an erroneous benign diagnosis on cytology.

Prognostic Role of Specific KRAS Mutations Detected in Aspiration and Liquid Biopsies from Patients with Pancreatic Cancer

Background/Objectives: Although the overall survival prognosis of patients in advanced stages of pancreatic ductal adenocarcinoma (PDAC) is poor, typically ranging from days to months from diagnosis, there are rare cases of patients remaining in therapy for longer periods of time. Early estimations of survival prognosis would allow rational decisions on complex therapy interventions, including radical surgery and robust systemic therapy regimens. Understandably, there is great interest in finding prognostic markers that can be used for patient stratification. We determined the role of various KRAS mutations in the prognosis of PDAC patients using biopsy samples and circulating tumor DNA. Methods: A total of 118 patients with PDAC, clinically confirmed by endoscopic ultrasound-guided fine-needle aspiration biopsy (EUS-FNB), were included in the study. DNA was extracted from cytological slides following a standard cytology evaluation to ensure adequacy (viability and quantity) and to mark the tumor cell fraction. Circulating tumor DNA (ctDNA) was extracted from plasma samples of 45 patients in stage IV of the disease. KRAS mutations in exons 12 and 13 were detected by denaturing capillary electrophoresis (DCE), revealing a minute presence of mutation-specific heteroduplexes. Kaplan–Meier survival curves were calculated for individual KRAS mutation types. Results:KRAS mutations were detected in 90% of tissue (106/118) and 44% of plasma (20/45) samples. All mutations were localized at exon 2, codon 12, with G12D (GGT &gt; GAT) being the most frequent at 44% (47/106) and 65% (13/20), followed by other types including G12V (GGT &gt; GTT) at 31% (33/106) and 10% (2/20), G12R (GGT &gt; CGT) at 17% (18/106) and 10% (2/20), G12C (GGT/TGT) at 5% (5/106) and 0% (0/20) and G12S (GGT/AGT) at 1% (1/106) and 5% (1/20) in tissue and plasma samples, respectively. Two patients had two mutations simultaneously (G12V + G12S and G12D + G12S) in both types of samples (2%, 2/106 and 10%, 2/20 in tissue and plasma samples, respectively). The median survival of patients with the G12D mutation in tissues was less than half that of other patients (median survival 101 days, 95% CI: 80–600 vs. 228 days, 95% CI: 184–602), with a statistically significant overall difference in survival (p = 0.0080, log-rank test), and furthermore it was less than that of all combined patients with other mutation types (101 days, 95% CI: 80–600 vs. 210 days, 95% CI: 161–602, p = 0.0166). For plasma samples, the survival of patients with this mutation was six times shorter than that of patients without the G12D mutation (27 days, 95% CI: 8–334 vs. 161 days, 95% CI: 107–536, p = 0.0200). In contrast, patients with detected KRAS G12R in the tissue survived nearly twice as long as other patients in the aggregate (286 days, 95% CI: 70–602 vs. 162 days, 95% CI: 122–600, p = 0.0374) or patients with other KRAS mutations (286 days, 95% CI: 70–602 vs. 137 days, 95% CI: 107–600, p = 0.0257). Conclusions: Differentiation of specific KRAS mutations in EUS-FNB and ctDNA (above all, the crucial G12D and G12R) is feasible in routine management of PDAC patients and imperative for assessment of prognosis.

A Retrospective Cytomorphologic Analysis of Salivary Gland Fine Needle Aspirates Classified as Salivary Gland Neoplasm of Uncertain Malignant Potential: A 6-year Institutional Experience.

The Milan System for Reporting Salivary Gland Cytopathology is an effective reporting system for salivary gland fine needle aspirations with well-established risks of malignancy. Salivary gland neoplasm of uncertain malignant potential (SUMP) comprises a heterogenous group of lesions which have features that can be recognized as at least neoplastic but preclude further classification into benign or malignant. In this study, we reviewed the cytomorphologic features of salivary gland fine needle aspirations diagnosed as SUMP at our institution (over the past 6 years) and correlated those with the final diagnosis on surgical follow up. A retrospective search was performed to identify cases classified as SUMP at our institution from January 2018 to February 2024. Cytology slides were reviewed, and cases were subclassified based on key cytomorphologic features into the following categories: (1) basaloid, (2) oncocytic, (3) with clear cell features and (4) mixed features (myoepithelial/oncocytoid/squamoid features). Histologic diagnosis was recorded if available. A total of 36 cases of SUMP were identified; 31/36 had surgical follow up; final diagnosis included 22 benign lesions (2 non-neoplastic and 20 benign neoplasms), and nine malignant lesions. The overall risk of neoplasm and risk of malignancy were 93.5% and 29% respectively, with the oncocytic sub-category recording the highest ROM (42.8%). Mucoepidermoid carcinoma was the most common malignant diagnosis and pleomorphic adenoma the most common benign diagnoses. Our study supports the subclassification of SUMP lesions based on key cytomorphologic features, thereby aiding in refining this ambiguous entity and providing a precise risk assessment.

Follicular neoplasms with nuclear atypia versus other types of atypia: Should follicular neoplasms be stratified according to the presence of nuclear atypia?

The third edition of The Bethesda System (TBS) subclassifies the atypia of undetermined significance (AUS) category on the basis of the presence of nuclear atypia (AUS-Nuclear). This approach is supported by studies showing significant differences in the risk of malignancy (ROM) between AUS-Nuclear and those without (AUS-Other). Although aspirates of follicular neoplasms (FNs) are characterized by marked architectural atypia, TBS recognizes the infrequent occurrence of FNs with mild nuclear atypia (FN-Nuclear). Furthermore, limited studies have shown significant differences in ROM between FN-Nuclear and those without (FN-Other). This study explored potential differences in ROM, molecular-derived risk of malignancy (MDROM), and molecular alterations between FN-Nuclear and FN-Other. A retrospective database search identified 93 FN aspirates. Cytology slides, molecular reports, and histologic follow-ups were reviewed. Both groups' benign call rate (BCR), positive call rate (PCR), MDROM, and ROM were computed and compared. Eighty-six percent of aspirates (80 of 93) comprised FN-Other, whereas 14% (13 of 93) were FN-Nuclear. The BCR and PCR for FN-Other were 51% and 49%, respectively. In contrast, they were 23% and 77% for FN-Nuclear, respectively. The MDROM significantly differed between FN-Other (30%) and FN-Nuclear (56%) (p<.05). HRAS mutation was the most common molecular alteration in FN-Nuclear, whereas mutations in NRAS/KRAS and copy number alterations were more common in FN-Other. The ROM1/ROM2 in FN-Other and FN-Nuclear were 16%/31% and 54%/88%, respectively. These results reveal that FN-Nuclear exhibits significantly higher MDROM and ROM than FN-Other, which provides support for a subclassification scheme for FNs based on the presence of nuclear atypia.

Assessment of Ki-67 Proliferative Index in Cytological Samples of Nodal B-Cell Lymphomas.

The Ki-67 proliferative index (PI) is part of the diagnosis of nodal B-cell lymphoma (nBCL), but its determination in cytological samples is not standardized. We aimed to establish an approach for the accurate determination of the Ki-67 PI in cytological slides to differentiate between indolent and aggressive nBCLs. Patients diagnosed with nBCL by fine-needle aspiration biopsy and subsequent excision biopsy were included. Cell suspensions were prepared from biopsy samples for CD3/Ki-67 double immunocytochemical staining and flow-cytometric verification of lymphoma B-cell counts. The Ki-67 PI was assessed by manual counting and eyeballing in cytology and eyeballing in histology. The cut-off values for the differentiation between aggressive and indolent lymphomas were determined for each method. A strong correlation between manual and flow-cytometric counting of lymphoma B cells was confirmed (interclass correlation coefficient (IC coef.) = 0.78). The correlation of the Ki-67 PI determined in cytological and histological slides was also strong (IC coef. > 0.80). Histologically, 55 cases were classified as indolent and 31 as aggressive nBCLs. KI-67 PI cut-off values of 28.5%, 27.5%, and 35.5% were established for manual counting and eyeballing in cytology and eyeballing in histology, respectively, with high sensitivity and specificity. The Ki-67 PI, assessed by manual counting and eyeballing in cytological samples, accurately differentiates between indolent and aggressive nBCLs.

Integrated On-Slide Positive Controls for Immunocytochemistry on Cytology Slides.

Integrated on-slide positive controls are a standard quality assurance and quality control measure for immunohistochemistry on formalin-fixed paraffin-embedded tissue sections. They ensure identical analytical conditions for the control and patient samples. Our aim was to develop a procedure for preparing integrated on-slide positive controls for immunocytochemistry (ICC) on methanol-fixed cytospins. Leftover diagnostic cytology samples with sufficient cells and confirmed expression of Calretinin, MOC31, TTF1, and hormone receptors were used as control samples. Cells from the control samples were deposited on the peripheral part of objective slides using standard cytocentrifuge equipment. Cytospins were immediately fixed in methanol for at least 30 min and then covered with polyethylene glycol (PEG). Completely dry and solid PEG was removed from the central part of the objective slides and stored at room temperature. Patient samples were subsequently added to the central part of a PEG-protected slide, with an appropriate positive control placed on the peripheral part, and then fixed in methanol. ICC was performed on the Ventana/Roche automated platform ULTRA, using optimized and validated protocols for TTF1, hormone receptors, and double immunostaining for Calretinin/MOC31. The quality of ICC reactions for both deposits on the same slide and potential cell carryover was evaluated retrospectively. In the period from October 2021 to December 2023, the majority of integrated positive controls (364/368, 99%) consistently exhibited unequivocally positive reactions for TTF-1 (n = 93), hormone receptors (n = 84), and double staining for Calretinin/MOC31 (n = 191), with easily interpretable ICC reactions on corresponding patient samples. No obvious carryover of cells from the control sample to the patient sample was observed during this period. A novel approach developed for preparing integrated on-slide positive controls for ICC on methanol-fixed cytospins using standard cytocentrifugation is low-cost and can be widely applied in diagnostic cytology laboratories. Simultaneous ICC procedures for the control and patient samples on the same slide ensure identical analytical conditions for both samples, providing the highest level of quality control while reducing costs. Interpreting both ICC reactions on the same slide is time-efficient and convenient.

Evaluating artificial intelligence-enhanced digital urine cytology for bladder cancer diagnosis.

This study evaluated the diagnostic effectiveness of the AIxURO platform, an artificial intelligence-based tool, to support urine cytology for bladder cancer management, which typically requires experienced cytopathologists and substantial diagnosis time. One cytopathologist and two cytotechnologists reviewed 116 urine cytology slides and corresponding whole-slide images (WSIs) from urology patients. They used three diagnostic modalities: microscopy, WSI review, and AIxURO, per The Paris System for Reporting Urinary Cytology (TPS) criteria. Performance metrics, including TPS-guided and binary diagnosis, inter- and intraobserver agreement, and screening time, were compared across all methods and reviewers. AIxURO improved diagnostic accuracy by increasing sensitivity (from 25.0%-30.6% to 63.9%), positive predictive value (PPV; from 21.6%-24.3% to 31.1%), and negative predictive value (NPV; from 91.3%-91.6% to 95.3%) for atypical urothelial cell (AUC) cases. For suspicious for high-grade urothelial carcinoma (SHGUC) cases, it improved sensitivity (from 15.2%-27.3% to 33.3%), PPV (from 31.3%-47.4% to 61.1%), and NPV (from 91.6%-92.7% to 93.3%). Binary diagnoses exhibited an improvement in sensitivity (from 77.8%-82.2% to 90.0%) and NPV (from 91.7%-93.4% to 95.8%). Interobserver agreement across all methods showed moderate consistency (κ=0.57-0.61), with the cytopathologist demonstrating higher intraobserver agreement than the two cytotechnologists across the methods (κ=0.75-0.88). AIxURO significantly reduced screening time by 52.3%-83.2% from microscopy and 43.6%-86.7% from WSI review across all reviewers. Screening-positive (AUC+) cases required more time than negative cases across all methods and reviewers. AIxURO demonstrates the potential to improve both sensitivity and efficiency in bladder cancer diagnostics via urine cytology. Its integration into the cytopathological screening workflow could markedly decrease screening times, which would improve overall diagnostic processes.

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

BackgroundPrimary 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.MethodsA 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.ResultsThe 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).ConclusionsThese 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 additive diagnostic value of cytology in fine needle biopsy of pancreatic adenocarcinoma: A tertiary center experience.

Endoscopic ultrasound guide fine needle biopsy (EUS-FNB) is the main diagnostic tool for pancreatic adenocarcinoma. In most instances, only histology is obtained via FNB, without sending cytological slides. The aim of our study was to assess the additive diagnostic yield of cytology performed through FNB. We conducted a retrospective study of all patients with histological diagnosis of pancreatic adenocarcinoma who were diagnosed by EUS-FNB. Overall, 80 patients were included in the study period. The overall concordance between cytology and histology all FNB needles was 78.2%. Notably, cytological assessment improved the diagnostic yield for malignancy by 12.8%. The overall kappa coefficient correlation between histology and cytology was .501, 95% CI 0.361-0.641. However, the kappa correlation for suspicious of malignancy and malignant was excellent of .872, 95% CI 0.733-1, suggesting that cytology is crucial when histology is inconclusive. Further analysis showed that the Acquire and Sharkcore needles outperformed the Procore needle in term of concordance between cytology and histology (kappa correlation of .527, 95% CI 0.331-0.724, .515, 95% CI 0.265-0.764, and .297, 95% CI -0.051-0.646), respectively. Performing cytology specimen when using FNB improves the diagnostic yield in pancreatic adenocarcinoma.

State of the Art and Science of Immunocytochemistry.

Immunocytochemistry (ICC) is a widely available and extensively used ancillary method in diagnostic cytopathology with great variability in all test phases and a low level of adequate quality management. The non-standardized ICC landscape is now challenged with the introduction of the new European (EU) In Vitro Diagnostic Medical Devices Regulation (IVDR). According to this regulation, ICC on cytological slides falls under the category of Laboratory-Developed Tests (LDT), which requires rigorous standardization, validation, and thorough quality management. Complete standardization of pre-analytical and analytical steps in ICC is impossible due to the complexity of the method and the constantly evolving antibodies, detection systems, and platforms. However, similar to the approach in immunohistochemistry, improving and standardizing "best practices" in quality management will result in high-quality, correct, accurate, and reliable ICC results. In this review, the current challenges of ICC in diagnostic cytopathology will be discussed, along with practical insights into ICC standardization and validation. Control slides prepared in the same manner as the patient samples, optimized ICC protocols, and participation in external quality control for ICC are the pillars of good quality management and essential to ensure safe and reliable patient diagnostics.

Advances in diagnostic liquid-based cytology.

Liquid-based cytology (LBC) has changed the landscape of gynaecological cytology. A growing demand exists for LBC in diagnostic cytology, particularly for ancillary testing, such as immunocytochemistry and molecular testing. Ancillary testing solely based on conventional preparation (CP) methods remains challenging. Recently, the increased demand for specialist testing and minimally invasive techniques, such as endoscopic ultrasonography fine-needle aspiration, to obtain cellular samples has led to an increasing demand for ancillary testing on cytology LBC supernatant, slides and cell block (CB). This facilitates the diagnosis and prognosis in cytology samples enabling personalized treatment. An understanding of the history and future prospects of LBC is crucial for its application in routine diagnostics by cytopathologists and cytotechnologists. In this review, we initiated an internet search using the keyword 'liquid-based cytology', and we conducted a literature review to discuss the usefulness of combined diagnosis of LBC and CP, immunocytochemistry and molecular testing and assessed the quality of nucleic acids in diagnostic LBC. High-quality and cell-rich diagnostic LBC surpassed the CP method alone in terms of reliability and versatility of ancillary testing in cytological diagnosis. Conclusively, diagnostic LBC lends itself to various new technologies and is expected to continue evolving with innovations in the future.

Performance of P16INK4a immunocytochemical stain in facilitating cytology interpretation of HSIL for HPV-positive women aged 50 and above.

Few articles have focused on the cytological misinterpretation of high-grade squamous intraepithelial lesion (HSIL). Due to estrogen deficiency, cervical epithelial cells in postmenopausal women tend to show atrophic change that looks like HSIL on Papanicolaou-stained cytology slides, resulting in a higher rate of cytological misinterpretation. P16INK4a immunocytochemical staining (P16 cytology) can effectively differentiate diseased cells from normal atrophic ones with less dependence on cell morphology. To evaluate the role of P16 cytology in differentiating cytology HSIL from benign atrophy in women aged 50 years and above. Included in this analysis were women in a cervical cancer screening project conducted in central China who tested positive for high-risk human papillomavirus (hr-HPV) and returned back for triage with complete data of primary HPV testing, liquid-based cytology (LBC) analysis, P16 immuno-stained cytology interpretation, and pathology diagnosis. The included patients were grouped by age: ≥50 (1,127 cases) and <50 years (1,430 cases). The accuracy of LBC and P16 cytology in the detection of pathology ≥HSIL was compared between the two groups, and the role of P16 immuno-stain in differentiating benign cervical lesions from cytology ≥HSIL was further analyzed. One hundred sixty-seven women (14.8%; 167/1,127) in the ≥50 group and 255 (17.8%, 255/1,430) in the <50 group were pathologically diagnosed as HSIL (Path-HSIL). LBC [≥Atypical Squamous Cell Of Undetermined Significance (ASCUS)] and P16 cytology (positive) respectively detected 63.9% (163/255) and 90.2% (230/255) of the Path-≥HSIL cases in the <50 group and 74.3% (124/167) and 93.4% (124/167) of the Path-≥HSIL cases in the ≥50 group. LBC matched with pathology in 105 (41.2%) of the 255 Path-≥HSIL cases in the <50 group and 93 (55.7%) of the 167 Path-≥HSIL cases in the ≥50 group. There were five in the <50 group and 14 in the ≥50 group that were Path-≤LSIL cases, which were interpreted by LBC as HSIL, but negative in P16 cytology. P16 cytology facilitates differentiation of Path-≤LSIL from LBC-≥HSIL for women 50 years of age and above. It can be used in the lower-resource areas, where qualified cytologists are insufficient, as the secondary screening test for women aged ≥50 to avoid unnecessary biopsies and misinterpretation of LBC primary or secondary screening.

Digital Cytology in Veterinary Education: A Comprehensive Survey of Its Application and Perception among Undergraduate and Postgraduate Students.

The COVID-19 pandemic accelerated technological changes in veterinary education, particularly in clinical pathology and anatomic pathology courses transitioning from traditional methods to digital pathology (DP). This study evaluates the personal effectiveness and satisfaction, as well as the advantages and disadvantages, of DP, in particular digital cytology (DC), as a teaching method among European veterinary students, both at the undergraduate and postgraduate level, who attended digital pathology courses during and before the pandemic. A further aim is to discuss the differences between the two student groups. A Google Form survey consisting of 11 multiple-choice questions was emailed to pathology teachers and distributed to their students. Results indicated that undergraduate students showed greater digital pathology training, favouring DC as the most effective learning modality. In contrast, postgraduate students reported less digital slide training, and their preference for learning cytology was split between DC alone and DC integrated with traditional microscopy. All students experienced whole slide imaging for learning cytology slides prevalently, and they stated that DC enhanced their learning experience. While DC demonstrates personal effectiveness and satisfaction as a teaching method, it is important to not replace pathology training with light microscopy completely, as almost a third of the students indicated.

Flow cytometry for meningeal infiltration in B acute lymphoblastic leukemia in a low middle income country.

Meningeal infiltration in children with B acute lymphoblastic leukemia is one of the most serious complications. Timely diagnosis not only significantly enhances treatment efficacy but also leads to improve patient outcome and reduce risk of relapse. This is particularly crucial in low to middle income countries facing health constraints, where optimizing resources is essential. Conventional cytology (CC) study of cerebrospinal fluid (CSF) is considered in different countries to be the Gold-standard despite its low sensitivity (< 50%). The study of CSF by multiparametric flow cytometry (MFC) appears to be an alternative. The aim of our study was to assess MFC analytical performance compared with CC. Our cross sectional study was conducted over a six-month period in the biological hematology department. CSF samples underwent analysis for the presence of blasts using both CC and MFC. Cytological slides of the CSF were prepared by cytocentrifugation in a Shandon Cytospin 4™. Flow cytometric analysis was performed on the BD FACSLyric™ flow cytometer. All statistical analyses were performed using SPSS version 21.0 (SPSS Inc.). Agreement between the two methods was made using the Kappa index and χ2 test. This study was approved by the local ethics committee. Sixty CSF samples from 39 children with B acute lymphoblastic leukemia were analyzed. Meningeal infiltration was detected respectively in 20% of cases by MFC and 5% of cases by CC, with a significant difference p = 0.006. Comparing the two methods, the Kappa coefficient was 0.35, indicating weak agreement between the two methods. Moreover, MFC positivity was higher even for hypocellular samples. Of the 51 hypocellular samples, eight were positive by MFC while they were negative by CC. MFC shows better sensitivity while retaining good specificity for the detection of meningeal involvement. MFC could therefore be a complementary method to CC for detecting blast cells in the central nervous system.

Revisiting the utility of identifying nuclear grooves as unique nuclear changes by an object detector model.

Among other structures, nuclear grooves are vastly found in papillary thyroid carcinoma (PTC). Considering that the application of artificial intelligence in thyroid cytology has potential for diagnostic routine, our goal was to develop a new supervised convolutional neural network capable of identifying nuclear grooves in Diff-Quik stained whole-slide images (WSI) obtained from thyroid fineneedle aspiration. We selected 22 Diff-Quik stained cytological slides with cytological diagnosis of PTC and concordant histological diagnosis. Each of the slides was scanned, forming a WSI. Images that contained the region of interest were obtained, followed by pre-formatting, annotation of the nuclear grooves and data augmentation techniques. The final dataset was divided into training and validation groups in a 7:3 ratio. This is the first artificial intelligence model based on object detection applied to nuclear structures in thyroid cytopathology. A total of 7,255 images were obtained from 22 WSI, totaling 7,242 annotated nuclear grooves. The best model was obtained after it was submitted 15 times with the train dataset (14th epoch), with 67% true positives, 49.8% for sensitivity and 43.1% for predictive positive value. The model was able to develop a structure predictor rule, indicating that the application of an artificial intelligence model based on object detection in the identification of nuclear grooves is feasible. Associated with a reduction in interobserver variability and in time per slide, this demonstrates that nuclear evaluation constitutes one of the possibilities for refining the diagnosis through computational models.

Evaluating Urine Cytology Slide Digitization Efficiency: A Comparative Study Using an Artificial Intelligence-Based Heuristic Scanning Simulation and Multiple Z-Plane Scanning

Introduction: Digitizing cytology slides presents challenges because of their three-dimensional features and uneven cell distribution. While multi-Z-plane scan is a prevalent solution, its adoption in clinical digital cytopathology is hindered by prolonged scanning times, increased image file sizes, and the requirement for cytopathologists to review multiple Z-plane images. Methods: This study presents heuristic scan as a novel solution, using an artificial intelligence (AI)-based approach specifically designed for cytology slide scanning as an alternative to the multi-Z-plane scan. Both the 21 Z-plane scan and the heuristic scan simulation methods were used on 52 urine cytology slides from three distinct cytopreparations (Cytospin, ThinPrep, and BD CytoRich™ [SurePath]), generating whole-slide images (WSIs) via the Leica Aperio AT2 digital scanner. The AI algorithm inferred the WSI from 21 Z-planes to quantitate the total number of suspicious for high-grade urothelial carcinoma or more severe cells (SHGUC+) cells. The heuristic scan simulation calculated the total number of SHGUC+ cells from the 21 Z-plane scan data. Performance metrics including SHGUC+ cell coverage rates (calculated by dividing the number of SHGUC+ cells identified in multiple Z-planes or heuristic scan simulation by the total SHGUC+ cells in the 21 Z-planes for each WSI), scanning time, and file size were analyzed to compare the performance of each scanning method. The heuristic scan's metrics were linearly estimated from the 21 Z-plane scan data. Additionally, AI-aided interpretations of WSIs with scant SHGUC+ cells followed The Paris System guidelines and were compared with original diagnoses. Results: The heuristic scan achieved median SHGUC+ cell coverage rates similar to 5 Z-plane scans across three cytopreparations (0.78–0.91 vs. 0.75–0.88, p = 0.451–0.578). Notably, it substantially reduced both scanning time (137.2–635.0 s vs. 332.6–1,278.8 s, p < 0.05) and image file size (0.51–2.10 GB vs. 1.16–3.10 GB, p < 0.05). Importantly, the heuristic scan yielded higher rates of accurate AI-aided interpretations compared to the single Z-plane scan (62.5% vs. 37.5%). Conclusion: We demonstrated that the heuristic scan offers a cost-effective alternative to the conventional multi-Z-plane scan in digital cytopathology. It achieves comparable SHGUC+ cell capture rates while reducing both scanning time and image file size, promising to aid digital urine cytology interpretations with a higher accuracy rate compared to the conventional single (optimal) plane scan. Further studies are needed to assess the integration of this new technology into compatible digital scanners for practical cytology slide scanning.

The current state of digital cytology and artificial intelligence (AI): global survey results from the American Society of Cytopathology Digital Cytology Task Force

The integration of whole slide imaging (WSI) and artificial intelligence (AI) with digital cytology has been growing gradually. Therefore, there is a need to evaluate the current state of digital cytology. This study aimed to determine the current landscape of digital cytology via a survey conducted as part of the American Society of Cytopathology (ASC) Digital Cytology White Paper Task Force. A survey with 43 questions pertaining to the current practices and experiences of WSI and AI in both surgical pathology and cytology was created. The survey was sent to members of the ASC, the International Academy of Cytology (IAC), and the Papanicolaou Society of Cytopathology (PSC). Responses were recorded and analyzed. In total, 327 individuals participated in the survey, spanning a diverse array of practice settings, roles, and experiences around the globe. The majority of responses indicated there was routine scanning of surgical pathology slides (n = 134; 61%) with fewer respondents scanning cytology slides (n = 150; 46%). The primary challenge for surgical WSI is the need for faster scanning and cost minimization, whereas image quality is the top issue for cytology WSI. AI tools are not widely utilized, with only 16% of participants using AI for surgical pathology samples and 13% for cytology practice. Utilization of digital pathology is limited in cytology laboratories as compared to surgical pathology. However, as more laboratories are willing to implement digital cytology in the near future, the establishment of practical clinical guidelines is needed.

Interobserver agreement in the interpretation of anal cytology.

Anal cytology represents a tool for anal cancer screening in high-risk populations. In addition to accuracy, the reproducibility of the interpretation is of key importance. The authors evaluated the agreement of anal cytologic interpretation between two cytopathologists. Liquid-based cytologic slides from human immunodeficiency virus (HIV)-negative men who have sex with men (MSM) were evaluated by two readers with at least 10 years of expertise in cervical cytology. Cases with a discordant interpretation were reviewed, and a consensus was reached. Human papillomavirus (HPV) genotyping was performed using a proprietary HPV genotyping test. Unweighted and weighted Cohen kappa and 95% confidence interval (CI) values were calculated. Overall, 713 slides that were adequate for interpretation were evaluated (MSM: median age, 33 years). An HPV test was performed on 620 samples (87.0%). Considering a dichotomous interpretation (negative for intraepithelial lesion or malignancy vs. atypical squamous cells of undetermined significance or worse), the crude agreement between the two readers was 93.3% (kappa=0.82; 95% CI, 0.77-0.87). Once a consensus for discordant cases was reached, the best agreement was found for the negative for intraepithelial lesion or malignancy category (511 of 528 samples; 96.8%), whereas the atypical squamous cells of undetermined significance category showed the lowest agreement (90 of 117 samples, 76.9%). Considering the individual cytologic categories, overall agreement was 92.1% (kappa=0.85; 95% CI, 0.81-0.89). The discordant interpretations were not associated with high-risk HPV infection, HPV16 infection, or MSM age. The results indicating excellent interobserver agreement in this study substantiate the use of anal cytology in the setting of human immunodeficiency virus-negative MSM.

Diagnostic utility of immunocytochemistry by using liquid-based cytology (LBC) slides.

Cytological specimens, such as fine needle aspirations (FNAs) and exfoliative cytology samples, are minimally invasive options for diagnostic purposes. Liquid-based cytology (LBC), originally designed for cervical cytology, has gained prominence as an alternative technique for non-gynecological cytology. Immunocytochemistry (ICC) is an ancillary method used when diagnosis becomes challenging due to morphological overlap or the need for cellular origin clarification. This study aims to assess the diagnostic utility of ICC when applied to LBC slides and evaluate its effectiveness in relation to the waiting (lag) time of residual material. A total of 74 cases in which ICC was applied to LBC slides were studied over one year in a reference pathology laboratory (Prof. Dr. Cemil Tascioglu, Pathology Laboratory, City Hospital, Istanbul, Turkey). Cases in which immunohistochemistry (IHC) was performed on formalin-fixed paraffin-embedded cell blocks were excluded. The SurePath PAP method was used for the main LBC cytology slides. For the ICC study, 1-4 PAP-stained LBC slides were obtained from each case's residual material and stained with a primary antibody. The positive immunostaining was obtained in 81% of cases. The samples were categorized into groups based on the waiting time of residual LBC material for ICC analysis: 1-5 days, 6-10 days, 11-20 days, and 21-38 days. Comparative analysis revealed a decline in ICC efficacy as the waiting (lag) time increased. Additionally, a statistically significant difference was observed between the 11-20 days and 21-38 days groups (P < 0.05). An analysis of 142 LBC slides stained by ICC revealed that nuclear markers exhibited higher positivity compared to non-nuclear markers, although no significant difference was detected between the two groups. High positivity rates can be obtained in ICC studies performed on additional slides obtained from residual LBC material within the first 20 days. ICC applied to LBC slides is an important and useful alternative for diagnostic and prognostic markers in cases without a cell block or with a cell block without sufficient number of cells.