Recent advances in artificial intelligence (AI) have provided novel tools for rapid and precise pathologic diagnosis. The introduction of digital pathology has enabled the acquisition of scanned slide images that are essential for the application of AI. The application of AI for improved pathologic diagnosis includes the error-free detection of potentially negligible lesions, such as a minute focus of metastatic tumor cells in lymph nodes, the accurate diagnosis of potentially controversial histologic findings, such as very well-differentiated carcinomas mimicking normal epithelial tissues, and the pathological subtyping of the cancers. Additionally, the utilization of AI algorithms enables the precise decision of the score of immunohistochemical markers for targeted therapies, such as human epidermal growth factor receptor 2 and programmed death-ligand 1. Studies have revealed that AI assistance can reduce the discordance of interpretation between pathologists and more accurately predict clinical outcomes. Several approaches have been employed to develop novel biomarkers from histologic images using AI. Moreover, AI-assisted analysis of the cancer microenvironment showed that the distribution of tumor-infiltrating lymphocytes was related to the response to the immune checkpoint inhibitor therapy, emphasizing its value as a biomarker. As numerous studies have demonstrated the significance of AI-assisted interpretation and biomarker development, the AI-based approach will advance diagnostic pathology.

BACKGROUND: Cytologic diagnosis of pulmonary adenoid cystic carcinoma (AdCC) is frequently challenging and differential diagnosis with small cell carcinoma is often difficult. METHODS: Eleven cytologically diagnosed cases of pulmonary AdCC were collected and reviewed according to fifteen cytomorphologic characteristics: small cell size, cellular uniformity, coarse chromatin, hyperchromasia, distinct nucleolus, frequent nuclear molding, granular cytoplasm, organoid cluster, sheet formation, irregular border of cluster, hyaline globule, hyaline basement membrane material, individual cell necrosis or apoptotic body, and necrotic background. Twenty cases of small cell carcinoma and fifteen cases of non-pulmonary AdCC were also reviewed for the comparison. RESULTS: Statistically significant differences were identified between pulmonary AdCC and small cell carcinoma in fourteen of the fifteen cytomorphologic criteria (differences in sheet formation were not statistically significant). Cellular uniformity, distinct nucleolus, granular cytoplasm, distinct cell border, organoid cluster, hyaline globule, and hyaline basement membrane material were characteristic features of AdCC. Frequent nuclear molding, individual cell necrosis, and necrotic background were almost exclusively identified in small cell carcinoma. Although coarse chromatin and irregular cluster border were observed in both, they favored the diagnosis of small cell carcinoma. Hyaline globules were more frequently seen in non-pulmonary AdCC cases. CONCLUSIONS: Using the fifteen cytomorphologic criteria described by this study, pulmonary AdCC could be successfully distinguished from small cell carcinoma. Such a comprehensive approach to an individual case is recommended for the cytologic diagnosis of pulmonary AdCC.
Adenoids* ; Antibody-Dependent Cell Cytotoxicity ; Basement Membrane ; Carcinoma, Adenoid Cystic* ; Carcinoma, Small Cell* ; Cell Size ; Chromatin ; Cytoplasm ; Diagnosis ; Diagnosis, Differential ; Fungi ; Hyalin ; Lung ; Necrosis ; Organoids

Breast cancer is a significant cause of cancer-related mortality in women worldwide. Early and precise diagnosis is crucial, and clinical outcomes can be markedly enhanced. The rise of artificial intelligence (AI) has ushered in a new era, notably in image analysis, paving the way for major advancements in breast cancer diagnosis and individualized treatment regimens. In the diagnostic workflow for patients with breast cancer, the role of AI encompasses screening, diagnosis, staging, biomarker evaluation, prognostication, and therapeutic response prediction. Although its potential is immense, its complete integration into clinical practice is challenging. Particularly, these challenges include the imperatives for extensive clinical validation, model generalizability, navigating the “black-box” conundrum, and pragmatic considerations of embedding AI into everyday clinical environments. In this review, we comprehensively explored the diverse applications of AI in breast cancer care, underlining its transformative promise and existing impediments. In radiology, we specifically address AI in mammography, tomosynthesis, risk prediction models, and supplementary imaging methods, including magnetic resonance imaging and ultrasound. In pathology, our focus is on AI applications for pathologic diagnosis, evaluation of biomarkers, and predictions related to genetic alterations, treatment response, and prognosis in the context of breast cancer diagnosis and treatment. Our discussion underscores the transformative potential of AI in breast cancer management and emphasizes the importance of focused research to realize the full spectrum of benefits of AI in patient care.

Thymic adenocarcinoma is extremely rare. Although its histologic features have been occasionally reported, a lack of description of the cytologic features has hampered the prompt and accurate diagnosis of this condition. Herein, we describe the cytologic findings and histology of four aspiration cytology specimens of thymic adenocarcinoma. The specimens were obtained from primary tumors, metastatic lymph nodes, and pericardial effusions. All four specimens showed three-dimensional glandular clusters with a loss of polarity and nuclear overlapping. One specimen had extensive extracellular mucinous material. Three specimens contained tumor cells with intracytoplasmic vacuoles. While the specimen with extracellular mucin showed relatively mild cytologic atypia, other specimens exhibited more atypical cytologic changes: irregular nuclear membranes, a coarse chromatin pattern, and prominent nucleoli. The cytologic features were correlated with the histologic features in each case of enteric type thymic adenocarcinoma. The differential diagnosis included other thymic carcinomas, yolk sac tumors, and metastatic adenocarcinoma from the lung or colorectum.
Adenocarcinoma* ; Biopsy, Fine-Needle* ; Chromatin ; Diagnosis ; Diagnosis, Differential ; Endodermal Sinus Tumor ; Lung ; Lymph Nodes ; Mediastinum ; Mucins ; Nuclear Envelope ; Pericardial Effusion ; Thymoma ; Thymus Gland ; Vacuoles

No abstract available.
Hemangioblastoma*

IgG4-related disease (IgG4-RD) may involve multiple organs. Although it usually presents as diffuse organ involvement, localized mass-forming lesions have been occasionally encountered in pancreas. However, the same pattern has been seldom reported in biliary tract. A 61-year-old male showed a hilar bile duct mass with multiple enlarged lymph nodes in imaging studies and he underwent trisectionectomy under impression of cholangiocarcinoma. Gross examination revealed a mass-like lesion around hilar bile duct. Histopathologically, dense lymphoplasmacytic infiltration and storiform fibrosis were identified without evidence of malignancy. Immunohistochemical stain demonstrated rich IgG4-positive plasma cell infiltration. Follow-up imaging studies disclosed multiple enlarged lymph nodes with involvement of pancreas and perisplenic soft tissue. The lesions have been significantly reduced after steroid treatment, which suggests multi-organ involvement of systemic IgG4-RD. Here, we report an unusual localized mass-forming IgG4-related cholangitis as an initial presentation of IgG4-RD, which was biliary manifestation of systemic IgG4-related autoimmune disease.
Autoimmune Diseases ; Bile Ducts ; Biliary Tract ; Cholangiocarcinoma ; Cholangitis* ; Fibrosis ; Follow-Up Studies ; Humans ; Lymph Nodes ; Male ; Middle Aged ; Pancreas ; Plasma Cells