The present review discusses the transformative role of AI in the diagnosis and management of head and neck cancers (HNCs). Methods: It explores how AI technologies, including ML, DL, and CNNs, are applied in various diagnostic tasks, such as medical imaging, molecular profiling, and predictive modeling. Results: This review highlights AI’s ability to improve diagnostic accuracy and efficiency, particularly in analyzing medical images like CT, MRI, and PET scans, where AI sometimes outperforms human radiologists. This paper also emphasizes AI’s application in histopathology, where algorithms assist in whole-slide image (WSI) analysis, tumor-infiltrating lymphocytes (TILs) quantification, and tumor segmentation. AI shows promise in identifying subtle or rare histopathological patterns and enhancing the precision of tumor grading and treatment planning. Furthermore, the integration of AI with molecular and genomic data aids in mutation analysis, prognosis, and personalized treatment strategies. Conclusions: Despite these advancements, the review identifies challenges in AI adoption, such as data standardization and model interpretability, and calls for further research to fully integrate AI into clinical practice for improved patient outcomes.

Central nervous system (CNS) tumors represent a formidable clinical challenge due to their molecular complexity and varied prognostic outcomes. This review delves into the pivotal role of the epigenetic marker H3K27me3 in the development and treatment of CNS tumors. H3K27me3, specifically the trimethylation of lysine 27 on the histone H3 protein, plays a crucial role in regulating gene expression and maintaining chromatin architecture (e.g., in X-chromosome inactivation). Notably, a reduction in H3K27me3 levels, frequently tied to mutations in the H3 gene family such as H3F3A and HIST1H3B, is evident in diverse brain tumor variants, including the diffuse midline glioma characterized by the H3K27M mutation and certain pediatric high-grade gliomas. The loss of H3K27me3 has been linked to more aggressive behavior in meningiomas, with the trimethylation loss associated with significantly shorter recurrence-free survival (RFS) among grade 2 meningiomas, albeit not within grade 1 tumors. Pediatric posterior fossa ependymomas characterized by a lowered H3K27me3 and DNA hypomethylation exhibit poor prognosis, underscoring the prognostic significance of these epigenetic alterations in CNS tumors. Comprehending the role of H3K27me3 in CNS tumors is vital for advancing diagnostic tools and therapeutic interventions, with the goal of enhancing patient outcomes and quality of life. This review underscores the importance of ongoing investigations into H3K27me to refine and optimize management strategies for CNS tumors, paving the way for improved personalized medicine practices in oncology.

This study aimed to evaluate the performance of ChatGPT‐4.0 as a diagnostic support tool for pathologists in identifying different types of gliomas based on histopathological data and to compare its performance with that of another artificial intelligence tool (Gemini 2.5 Pro). A retrospective analysis was performed on 25 cases with histopathological descriptions. The dataset, anonymized for patient confidentiality, included clinical details such as age, sex, and site, along with two histological images for each case, obtained from the archive files of the Anatomic Pathology section, Department of Medical, Surgical Sciences and Advanced Technologies “G.F. Ingrassia” University of Catania, Italy. ChatGPT‐4.0 was tasked with generating diagnoses, which were classified as correct, similar, or different when compared to the pathologists' conclusions and the diagnoses provided by Gemini. ChatGPT‐4.0 achieved a diagnostic accuracy of 88%, correctly identifying 22 out of 25 cases. No significant differences in diagnostic performance were observed between male and female patients. The AI performed exceptionally well in diagnosing glioblastomas, with a 100% accuracy rate, while two oligodendrogliomas and one astrocytoma IDH‐mutant G3 were misdiagnosed. A comparative evaluation with Gemini 2.5 Pro was also conducted, although its contribution was limited to a qualitative comparison based on the same dataset. ChatGPT‐4.0 demonstrated moderate accuracy in the histopathological diagnosis of gliomas, with little variability depending on glioma subtype. While its performance highlights potential for future integration into clinical workflows, significant improvements are required to ensure its reliability and effectiveness in diagnostic applications.Trial Registration: ce 165/2015/PO

Background: Adrenal cortical carcinoma (ACC) is a rare and aggressive malignant tumor with an estimated prevalence of 0.5–2 cases per million people. For patients with advanced or metastatic disease, the prognosis is very poor, and death usually occurs in the first 24 months after diagnosis. Some cases of ACC with invasion of the inferior vena cava (IVC) and the right atrium (RA) have been reported. Methods: We herein report an additional case of IVC and RA involvement in ACC in a 61-year-old woman with no relevant past medical history. Results: The patient underwent heart surgery to remove neoplastic thrombi in the IVC and RA; abdominal surgery to remove the adrenal mass was performed one month later, when the patient’s clinical condition was stable. Conclusions: The histologic and immunohistochemical features, as well as the differential diagnosis, are highlighted herein.

Growing scientific evidence suggests a link between the expression of toll-like receptor 4 (TLR4) and cervical cancer carcinogenesis. Specifically, a close relation between TLR4 expression and FIGO stage, lymph node metastases, and tumor size has been reported in cervical cancer. In the present study, we aimed to evaluate the relationship between TLR4 expression levels and human papillomavirus (HPV) infection and/or high-risk (hr) HPV integration status in patients with a histological diagnosis of high-grade squamous intraepithelial lesion (H-SIL), and squamous cell carcinoma (SCC) of the uterine cervix. Sixty biopsies of cervical neoplasia, comprising H-SIL (n = 20) and SCC (n = 40), were evaluated for TLR4 expression by immunohistochemistry. All samples were positive for high-risk HPV as confirmed by in situ hybridization (ISH) and broad-spectrum PCR followed by Sanger sequencing analysis. The intensity of TLR4 staining was higher in tissues negative for intraepithelial lesion or malignancy (NILM) than in H-SIL, and further reduced in SCC. Moreover, statistically significant differences have been observed in the percentage of TLR4 expression between NILM and H-SIL and between H-SIL and SCC, with higher percentages of expression in H-SIL than in SCC. Our results showed a significant downregulation of TLR4 in HPV-related H-SIL and SCC, compared to NILM. These data support the hypothesis that TLR4 expression is suppressed in HPV-driven oncogenesis.

Background: This review examines the expanding influence of artificial intelligence (AI) in the detection and management of uveal melanoma (UM). Methods: This work delves into the application of AI technologies such as machine learning (ML), deep learning (DL), and convolutional neural networks (CNNs) in various diagnostic procedures, molecular profiling, and predictive analysis. Results: The discussion underscores AI’s potential to enhance diagnostic precision and efficiency. Particular focus is placed on its role in histopathological assessments of UM, where algorithms facilitate the analysis of whole-slide images (WSIs). AI contributes to more accurate tumor classification, assists in planning treatments, and improves the prediction of the prognostic indicators and molecular characteristics of the tumor. Conclusions: Despite these promising developments, this review acknowledges existing hurdles to AI implementation, including issues with data standardization and the interpretability of AI models. It emphasizes the need for further research to fully integrate AI into clinical workflows, ultimately aiming to improve patient care and outcomes.