ABSTRACT Background Cytology artificial intelligence (AI) systems often depend on whole‐slide images (WSIs) or high‐magnification cell images and are commonly optimized for a single specimen type. We developed CYTOLONE‐v2, a contrastive language‐image pretraining (CLIP)–based hierarchical classification framework for cervical and urinary cytology that is designed for individual‐field inference without WSI input. Methods CYTOLONE‐v1.1, previously trained for cervical cytology, was further trained by low‐rank adaptation using WSI‐derived urinary cytology fields equivalent to ×10 magnification. The 90‐case source cohort was divided at the case level into training (72 cases; 360 fields) and validation (18 cases; 90 fields) subsets. Five diagnosis‐representative fields were manually selected from each case. Field‐level performance was evaluated in an independent urinary test cohort of 40 cases (20 Reactive change and 20 Urothelial carcinoma; 200 fields), and retention was assessed using an independent cervical cytology test set. Results In urinary cytology, CYTOLONE‐v2 achieved field‐level accuracies of 64.0% for Anomaly and Malignancy and 72.5% for Diagnosis. At the Diagnosis level, sensitivity for urothelial carcinoma was 99.0% (95% confidence interval [CI], 96.7%–100%), whereas specificity against Reactive change was 46.0% (95% CI, 30.0%–62.0%). Cervical cytology accuracy was retained at the Anomaly level (94.8% vs. 94.7% with CYTOLONE‐v1.1), decreased modestly at the Malignancy level (91.2% vs. 93.5%), and decreased more at the Bethesda and Diagnosis levels. Conclusions CYTOLONE‐v2 demonstrates the technical feasibility of extending a hierarchical cytology classification framework from cervical to urinary cytology. The findings are limited to selected WSI‐derived fields and a Reactive change‐versus‐Urothelial carcinoma test cohort; external, case‐level, direct‐microscopy and prospective workflow validation is required before clinical utility can be established.
ABSTRACT Pulmonary alveolar proteinosis (PAP) is a rare disorder characterized by abnormal accumulation of surfactant within the alveoli, leading to impaired gas exchange and progressive respiratory symptoms. We report a 40‐year‐old stone grinder presenting with chronic cough, dyspnea, weight loss and hypoxemia. High‐resolution computed tomography showed bilateral ground‐glass opacities, while bronchoalveolar lavage (BAL) yielded characteristic milky fluid. Cytological examination demonstrated PAS‐positive eosinophilic material with foamy macrophages, confirming secondary PAP related to silica exposure. Lung biopsy was not feasible because of the patient's condition. Whole lung lavage resulted in marked clinical, radiological and oxygenation improvement, highlighting BAL cytology's diagnostic value.
ABSTRACT Perivascular epithelioid cell tumours (PEComas) are rare mesenchymal neoplasms with characteristic myomelanocytic differentiation and limited descriptions in fine‐needle aspiration (FNA) specimens. A woman in her 30s with a history of ALK‐positive anaplastic large cell lymphoma in remission was found to have a 2.1‐cm hepatic mass during evaluation of persistent liver function abnormalities. Ultrasound‐guided FNA demonstrated a cellular neoplasm composed of loosely cohesive clusters and singly dispersed epithelioid to spindle cells with abundant eosinophilic cytoplasm, mild to moderate nuclear atypia and prominent nucleoli. Immunohistochemical studies showed positivity for smooth muscle actin, caldesmon, HMB‐45 and Melan‐A, supporting a myomelanocytic phenotype. Molecular testing identified pathogenic TSC2 splice‐site mutations. Subsequent resection confirmed hepatic PEComa, epithelioid angiomyolipoma variant. This case highlights the characteristic cytomorphologic, immunophenotypic and molecular features of hepatic PEComa and demonstrates the value of FNA with ancillary testing in establishing a preoperative diagnosis and excluding morphologic mimics.
BACKGROUND:Ovarian neoplasms are a significant cause of morbidity among women, particularly in resource-limited rural settings where access to advanced diagnostic facilities is often restricted. Intraoperative cytology provides a rapid and cost-effective diagnostic adjunct that may facilitate timely surgical decision-making. AIM:To evaluate the diagnostic utility of minimally invasive techniques of cytology in ovarian tumours in a rural tertiary care centre. MATERIALS AND METHODS:This study has been conducted by the Departments of Pathology, Obstetrics and Gynecology, by analysing cytological samples obtained from ovarian cysts/tumours retrospectively between June 2023 and December 2025. This includes specimen of ovarian mass/cysts submitted for touch/imprint, scrape and crush smears, along with fine-needle aspiration cytology (FNAC) for intra-operative cytological (IOC) assessment. FNA aspirates from ovarian masses obtained intra-operatively were centrifuged at 3500 rpm for 2-3 min and sediment smears were examined. Cytological diagnoses obtained intra-operatively were compared with histopathological findings, which served as the gold standard. Data were analysed for age distribution, concordance between cytology and histology, and diagnostic performance parameters including sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). RESULTS:A total of 79 cases have been included in the study, and nine cases were excluded due to lack of relevant data for histopathological correlation. The age of patients ranged between 14 and 77 years, with a peak incidence in the 41-50-year age group (31.4%). Cytology showed concordance with histopathology in 61 out of 70 cases (87.1%), while 9 cases (12.9%) were discordant. For detection of malignancy, cytology demonstrated a sensitivity of 80%, specificity of 100%, PPV of 100% and NPV of 98.1%, with an overall diagnostic accuracy of 98.3%. No false-positive cases were identified, while one false-negative case was noted. The kappa coefficient was 0.88 with diagnostic accuracy being 98.3%. CONCLUSION:Cytology is a rapid, reliable and highly specific diagnostic tool for ovarian tumours, particularly valuable in rural tertiary care settings where access to advanced diagnostics may be limited. Its high specificity and PPV make it especially useful for differentiating between benign and malignant complex ovarian cysts and aiding early clinical decision-making.
BACKGROUND:Extramedullary blast proliferation (EBP) occurs in approximately 4%-16% of patients with chronic myeloid leukaemia (CML) in blast phase and may precede overt marrow blast transformation. Although myeloid lineage predominates, lymphoid blast crises account for approximately 20%-30% of cases, with T-lineage differentiation representing only a small minority. Accurate recognition is important because EBP defines blast-phase disease irrespective of the bone marrow blast percentage. CASE PRESENTATION:A 40-year-old man presented with generalized lymphadenopathy, hepatosplenomegaly, anaemia, and marked leukocytosis. Bone marrow examination demonstrated CML in chronic phase, while fluorescence in situ hybridization confirmed BCR::ABL1 fusion. Fine needle aspiration cytology (FNAC) from a cervical lymph node revealed a monomorphic population of intermediate-sized blasts with a high nuclear-cytoplasmic ratio and scant agranular cytoplasm. Flow cytometric immunophenotyping performed on the aspirate demonstrated expression of cytoplasmic CD3, CD5, CD7, CD34, CD38, CD33, and CD117, with absence of myeloperoxidase, CD4, and CD8, establishing a diagnosis of extramedullary T-lymphoblastic blast crisis. CONCLUSIONS:This case highlights the value of FNAC combined with flow cytometry in diagnosing extramedullary blast proliferation. Awareness of this rare manifestation is essential because it may represent the first evidence of blast-phase transformation despite chronic-phase morphology on bone marrow examination.
