Oral squamous cell carcinoma (OSCC) is a common malignancy of the head and neck region. OSCC has a relatively low survival rate and the incidence of the disease is increasing in some geographic areas. Staging and grading of OSCC are established prerequisites for management, as they influence risk stratification and are the first step toward personalized treatment. The current AJCC/UICC TNM staging (8th edition, 2017) of OSCC has included significant modifications through the incorporation of depth of invasion in the T stage and extracapsular spread/extranodal extension in the N stage. Further modifications for AJCC 8 have been suggested. On the other hand, the World Health Organization (WHO) classification (4th edition, 2017) still endorses a simple, differentiation-based histopathologic grading system of OSCC (despite its low prognostic value) and ignores factors such as tumor growth pattern and dissociation, stromal reactions (desmoplasia, local immune response), and tumor-stroma ratio. The various controversies and possible developments of the current staging and grading criteria of OSCC are briefly discussed in this update together with possible applications of artificial intelligence in the context of screening and risk stratification.

Chemoradiotherapy has emerged as a gold standard in advanced squamous cell carcinoma of the head and neck (SCCHN). Because 50% of advanced stage patients relapse after nonsurgical primary treatment, the role of salvage surgery (SS) is critical because surgery is generally regarded as the best treatment option in patients with recurrent resectable SCCHN. Surgeons are increasingly confronted with considering operation among patients with significant effects of failed non-surgical primary treatment. Wide local excision to achieve clear margins must be balanced with the morbidity of the procedure, the functional consequences of organ mutilation, and the likelihood of success. Accurate selection of patients suitable for surgery is a major issue. It is essential to establish objective criteria based on functional and oncologic outcomes to select the best candidates for SS. The authors propose first to understand preoperative prognostic factors influencing survival. Predictive modeling based on preoperative information is now available to better select patients having a good chance to be successfully treated with surgery. Patients with a high comorbidity index, advanced oropharyngeal or hypopharyngeal primary tumors, and both local and regional recurrence have a very limited likelihood of success with salvage surgery and should be strongly considered for other treatments. Following SS, identifying patients with postoperative prognostic factors predicting high risk of recurrence is essential because those patients could benefit of adjuvant treatment or be included in clinical trials. Finally, defining HPV tumor status is needed in future studies including recurrent oropharyngeal SCC patients.

Introduction Several studies have emphasized the potential of artificial intelligence (AI) and its subfields, such as machine learning (ML), as emerging and feasible approaches to optimize patient care in oncology. As a result, clinicians and decision-makers are faced with a plethora of reviews regarding the state of the art of applications of AI for head and neck cancer (HNC) management. This article provides an analysis of systematic reviews on the current status, and of the limitations of the application of AI/ML as adjunctive decision-making tools in HNC management. Methods Electronic databases (PubMed, Medline via Ovid, Scopus, and Web of Science) were searched from inception until November 30, 2022. The study selection, searching and screening processes, inclusion, and exclusion criteria followed the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines. A risk of bias assessment was conducted using a tailored and modified version of the Assessment of Systematic Review (AMSTAR-2) tool and quality assessment using the Risk of Bias in Systematic Reviews (ROBIS) guidelines. Results Of the 137 search hits retrieved, 17 fulfilled the inclusion criteria. This analysis of systematic reviews revealed that the application of AI/ML as a decision aid in HNC management can be thematized as follows: (1) detection of precancerous and cancerous lesions within histopathologic slides; (2) prediction of the histopathologic nature of a given lesion from various sources of medical imaging; (3) prognostication; (4) extraction of pathological findings from imaging; and (5) different applications in radiation oncology. In addition, the challenges in implementation of AI/ML models for clinical evaluations include the lack of standardized methodological guidelines for the collection of clinical images, development of these models, reporting of their performance, external validation procedures, and regulatory frameworks. Conclusion At present, there is a paucity of evidence to suggest the adoption of these models in clinical practice due to the aforementioned limitations. Therefore, this manuscript highlights the need for development of standardized guidelines to facilitate the adoption and implementation of these models in the daily clinical practice. In addition, adequately powered, prospective, randomized controlled trials are urgently needed to further assess the potential of AI/ML models in real-world clinical settings for the management of HNC.

Purpose: To review the current options in the management of Warthin tumors (WTs) and to propose a working management protocol. Methods: A systematic literature search was conducted using PubMed and ScienceDirect database. A total of 141 publications were selected and have been included in this review. Publications were selected based on relevance, scientific evidence, and actuality. Results: The importance of parotid WTs is increasing due to its rising incidence in many countries, becoming the most frequently encountered benign parotid tumor in certain parts of the world. In the past, all WTs were treated with surgery, but because of their slow growth rate, often minimal clinical symptoms, and the advanced age of many patients, active observation has gradually become more widely used. In order to decide on active surveillance, the diagnosis of WT must be reliable, and clinical, imaging, and cytological data should be concordant. There are four clear indications for upfront surgery: uncertain diagnosis; cosmetic problems; clinical complaints, such as pain, ulceration, or recurrent infection; and the patient’s wish to have the tumor removed. In the remaining cases, surgery can be elective. Active surveillance is often suggested as the first approach, with surgery being considered if the tumor progresses and/or causes clinical complaints. The extent of surgery is another controversial topic, and the current trend is to minimize the resection using partial parotidectomies and extracapsular dissections when possible. Recently, non-surgical options such as microwave ablation, radiofrequency ablation, and ultrasound-guided ethanol sclerotherapy have been proposed for selected cases. Conclusions: The management of WT is gradually shifting from superficial or total parotidectomy to more conservative approaches, with more limited resections, and to active surveillance in an increasing number of patients. Additionally, non-surgical treatments are emerging, but their role needs to be defined in future studies.