Enhancing head and neck tumor management with artificial intelligence: Integration and perspectives

Unsupervised model for structure segmentation applied to brain computed tomography

This article presents an unsupervised method for segmenting brain computed tomography scans. The proposed methodology involves image feature extraction and application of similarity and continuity constraints to generate segmentation maps of the anatomical head structures. Specifically designed for real-world datasets, this approach applies a spatial continuity scoring function tailored to the desired number of structures. The primary objective is to assist medical experts in diagnosis by identifying regions with specific abnormalities. Results indicate a simplified and accessible solution, reducing computational effort, training time, and financial costs. Moreover, the method presents potential for expediting the interpretation of abnormal scans, thereby impacting clinical practice. This proposed approach might serve as a practical tool for segmenting brain computed tomography scans, and make a significant contribution to the analysis of medical images in both research and clinical settings.

Antiapoptotic PON2 expression and its clinical implications in locally advanced oral squamous cell carcinoma

Locally advanced oral squamous cell carcinoma poses a significant challenge in oncology due to its rising incidence and mortality rates. Despite therapeutic progress, understanding molecular intricacies is essential. This study explored the role of PON2, a multifunctional enzyme implicated in antiapoptotic mechanisms. Aberrant PON2 expression in oral cancers raises questions regarding its involvement in evading programmed cell death and treatment resistance. Patients with locally advanced disease were enrolled, and molecular analyses were undertaken on the collected tumor and normal tissues. Utilizing computational datasets, this study used in silico gene expression analysis, differential gene expression analysis in our patient cohort, survival analysis, and gene set enrichment analysis to unravel role of PON2 in disease prognosis. The results showed elevated PON2 levels in advanced tumor stages, correlating with factors such as tobacco exposure, higher tumor grade, and nodal metastasis. Survival analysis revealed prognostic relevance of PON2, with lower expression linked to extended survival rates. Gene set enrichment analysis identified pathways aiding in cancer metastasis influenced by PON2. This study underscores the significance of PON2 expression as a prognostic marker for oral malignancies, with increased expression associated with advanced disease stages. Understanding the molecular profile of the PON2 gene suggests its potential as a valuable biomarker for the management of cancer.

Surgical Management Strategies for Carotid Artery Invasion by Head and Neck Cancer: Ligation Versus Reconstruction

OBJECTIVE

Whether ligation or reconstruction should be performed after radical resection of the tumor and carotid artery in patients with head and neck cancers invading the carotid artery (HNC-CA) has been controversial. This paper provides a review and meta-analysis of the efficacy of these 2 modalities.

DATA SOURCES

PubMed, Cochrane, Web of Science, Scopus, and Ovid databases were searched through August 2023.

REVIEW METHODS

Descriptive, graphical, tabular, and quantitative data were extracted. The statistical outcomes (risk difference, RD) were synthesized under a random-effects model. This study was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analyses reporting guidelines.

RESULTS

A total of 22 papers and 337 patients met the inclusion criteria for the literature review. Statistical analysis showed that the RD of overall survival (OS) rate at 1-year was 32% (95% confidence interval [CI]: 21%-42%) for ligation and 70% (95% CI: 65%-76%) for reconstruction (P < .05). The RD for OS rate at 2-year was 16% (95% CI: 7%-26%) for ligation and 39% (95% CI: 30%-47%) for reconstruction (P < .05). The RD for disease-free survival rate at 1-year was 27% (95% CI: 17%-38%) for ligation and 60% (95% CI: 51%-70%) for reconstruction (P < .05). There were no statistically significant differences (P > .05) between the 2 surgical modalities in terms of locoregional recurrence rate, carotid blowout rate, surgery-related complications rate, neurological complications rate, and perioperative mortality rate.

CONCLUSION

This review demonstrates the significant advantage of carotid artery reconstruction surgery in short-term patient survival, thus making it a recommended option for HNC-CA patients undergoing radical surgery.

An introduction to machine learning and generative artificial intelligence for otolaryngologists-head and neck surgeons: a narrative review

PURPOSE

Despite the robust expansion of research surrounding artificial intelligence (AI) and machine learning (ML) and their applications to medicine, these methodologies often remain opaque and inaccessible to many otolaryngologists. Especially, with the increasing ubiquity of large-language models (LLMs), such as ChatGPT and their potential implementation in clinical practice, clinicians may benefit from a baseline understanding of some aspects of AI. In this narrative review, we seek to clarify underlying concepts, illustrate applications to otolaryngology, and highlight future directions and limitations of these tools.

METHODS

Recent literature regarding AI principles and otolaryngologic applications of ML and LLMs was reviewed via search in PubMed and Google Scholar.

RESULTS

Significant recent strides have been made in otolaryngology research utilizing AI and ML, across all subspecialties, including neurotology, head and neck oncology, laryngology, rhinology, and sleep surgery. Potential applications suggested by recent publications include screening and diagnosis, predictive tools, clinical decision support, and clinical workflow improvement via LLMs. Ongoing concerns regarding AI in medicine include ethical concerns around bias and data sharing, as well as the "black box" problem and limitations in explainability.

CONCLUSIONS

Potential implementations of AI in otolaryngology are rapidly expanding. While implementation in clinical practice remains theoretical for most of these tools, their potential power to influence the practice of otolaryngology is substantial.

LEVEL OF EVIDENCE: 4

Emerging pharmacotherapy trends in preventing and managing oral mucositis induced by chemoradiotherapy and targeted agents

INTRODUCTION

The introduction of targeted therapy and immunotherapy has tremendously changed the clinical outcomes and prognosis of cancer patients. Despite innovative pharmacological therapies and improved radiotherapy (RT) techniques, patients continue to suffer from side effects, of which oral mucositis (OM) is still the most impactful, especially for quality of life.

AREAS COVERED

We provide an overview of current advances in cancer pharmacotherapy and RT, in relation to their potential to cause OM, and of the less explored and more recent literature reports related to the best management of OM. We have analyzed natural/antioxidant agents, probiotics, mucosal protectants and healing coadjuvants, pharmacotherapies, immunomodulatory and anticancer agents, photobiomodulation and the impact of technology.

EXPERT OPINION

The discovery of more precise pathophysiologic mechanisms of CT and RT-induced OM has outlined that OM has a multifactorial origin, including direct effects, oxidative damage, upregulation of immunologic factors, and effects on oral flora. A persistent upregulated immune response, associated with factors related to patients' characteristics, may contribute to more severe and long-lasting OM. The goal is strategies to conjugate individual patient, disease, and therapy-related factors to guide OM prevention or treatment. Despite further high-quality research is warranted, the issue of prevention is paramount in future strategies.

Tumor hypoxia and role of hypoxia-inducible factor in oral cancer

BACKGROUND

Head and neck cancer (HNC) is one of the most frequent malignancies in Asian males with a poor prognosis. Apart from well-known prognostic indicators, markers of tumor hypoxia can help us predict response to treatment and survival.

METHODS

A review of the literature on the present evidence and potential clinical importance of tumor hypoxia in head and neck cancer was carried out. The data obtained from the literature search is presented as a narrative review.

RESULTS

The literature shows possible associations between prognosis and low tumor oxygenation. Intermediate hypoxia biomarkers like HIF-1, GLUT-1, miRNA, and lactate, can help in predicting the response to therapy and survival as their altered expression is related to prognosis.

CONCLUSIONS

Hypoxia is common in HNC and can be detected by use of biomarkers. The tumors that show expression of hypoxia biomarkers have poor prognosis except for patients with human papilloma virus-associated or VHL-associated cancers. Therapeutic targeting of hypoxia is emerging; however, it is still in its nascent stage, with increasing clinical trials hypoxia is set to emerge as an attractive therapeutic target in HNC.

Clinical Advances and Future Directions of Oncolytic Virotherapy for Head and Neck Cancer

Oncolytic viruses (OVs), without harming normal tissues, selectively infect and replicate within tumor cells, to release immune molecules and tumor antigens, achieving immune-mediated destruction of tumors and making them one of the most promising immunotherapies for cancer. Many clinical studies have demonstrated that OVs can provide clinical benefits for patients with different types of tumors, at various stages, including metastatic and previously untreatable cases. When OVs are used in combination with chemotherapy, radiotherapy, immunotherapy, and other treatments, they can synergistically enhance the therapeutic effects. The concept of oncolytic virotherapy (OVT) was proposed in the early 20th century. With advancements in genetic engineering, genetically modified viruses can further enhance the efficacy of cancer immunotherapy. In recent years, global research on OV treatment of malignant tumors has increased dramatically. This article comprehensively reviews the findings from relevant research and clinical trials, providing an overview of the development of OVT and its application in the clinical treatment of head and neck cancer. The aim is to offer insights for future clinical and fundamental research on OVT.