Introduction: Adenoid cystic carcinoma (AdCC) is a rare tumour as it accounts for about 10% of all salivary gland neoplasms. It occurs in all age groups with a predominance of women, but no risk factors have been identified to date. Although AdCC behaves as a slow-growing tumour, it is characterized by multiple and late recurrences. Therefore, we aim to update the knowledge of the treatment options in advanced and recurrent cases. Materials and Methods: We performed a systematic literature review to provide a synthesis of the practical knowledge required for AdCC non-surgical management. Altogether, 99 out of the 1208 available publications were selected for analysis. Results: AdCC is described as a basaloid tumour consisting of epithelial and myoepithelial cells. Immunohistochemistry is useful for diagnosis (PS100, Vimentin, CD117, CKit, muscle actin, p63) and for prognosis (Ki67). Identified mutations could lead to therapeutic opportunities (MYB-NFIB, Notch 1). The work-up is mainly based on neck and chest CT scan and MRI, and PET-CT with 18-FDG or PSMA can be considered. Surgical treatment remains the gold standard in resectable cases. Post-operative intensity modulated radiotherapy is the standard of care, but hadron therapy may be used in specific situations. Based on the available literature, no standard chemotherapy regimen can be recommended. Conclusion: There is currently no consensus on the use of chemotherapy in AdCC, either concomitantly to RT in a postoperative setting or at a metastatic stage. Further, the available targeted therapies do not yet provide significant tumour response.

Background: Diagnosis of head and neck (HN) squamous dysplasias and carcinomas is critical for patient care, cure, and follow‐up. It can be challenging, especially for grading intraepithelial lesions. Despite recent simplification in the last WHO grading system, the inter‐ and intraobserver variability remains substantial, particularly for nonspecialized pathologists, exhibiting the need for new tools to support pathologists.Methods: In this study we investigated the potential of deep learning to assist the pathologist with automatic and reliable classification of HN lesions following the 2022 WHO classification system. We created, for the first time, a large‐scale database of histological samples (>2000 slides) intended for developing an automatic diagnostic tool. We developed and trained a weakly supervised model performing classification from whole‐slide images (WSI). We evaluated our model on both internal and external test sets and we defined and validated a new confidence score to assess the predictions that can be used to identify difficult cases.Results: Our model demonstrated high classification accuracy across all lesion types on both internal and external test sets (respectively average area under the curve [AUC]: 0.878 (95% confidence interval [CI]: [0.834–0.918]) and 0.886 (95% CI: [0.813–0.947])) and the confidence score allowed for accurate differentiation between reliable and uncertain predictions.Conclusion: Our results demonstrate that the model, associated with confidence measurements, can help in the difficult task of classifying HN squamous lesions by limiting variability and detecting ambiguous cases, taking us one step closer to a wider adoption of AI‐based assistive tools.

(1) Background: In head and neck squamous cell carcinoma, tumor hypoxia has been associated with radio/chemoresistance and poor prognosis, whereas human papillomavirus (HPV)-positive status has a positive impact on treatment response and survival outcomes. The aim of this study was to evaluate the expression and the potential prognostic value of hypoxia-induced endogenous markers in patients treated for squamous cell carcinoma of the nasal cavity and paranasal sinuses (SNSCC), and their correlation with HPV status. (2) Methods: In this monocentric study, patients treated in a curative intent for a SNSCC were screened retrospectively. Protein expression of CA-IX, GLUT-1, VEGF, VEGF-R1, and HIF-1α was determined by immunohistochemical staining, scored, and then correlated with overall survival (OS) and locoregional recurrence free survival (LRRFS). HPV status was assessed and correlated with hypoxic markers. (3) Results: 40 patients were included. A strong expression of CA-IX, GLUT-1, VEGF, and VEGF-R1 was detected in 30%, 32.5%, 50%, and 37.5% of cases, respectively. HIF-1α was detected in 27.5% of cases. High CA-IX expression was associated in univariate analysis with poor OS (p = 0.035), but there was no significant association between GLUT-1, VEGF, VEGF-R1, and HIF-1α expression, and OS/LRRFS. There was no correlation found between HPV status and hypoxia-induced endogenous markers (all p > 0.05). (4) Conclusions: This study provides data on the expression of hypoxia-induced endogenous markers in patients treated for SNSCC and underlines the potential role of CA-IX as a prognostic biomarker for SNSCC.

Ten percent of head and neck cancers (HNCs) differ from the common upper aerodigestive tract squamous-cell carcinoma. These rare HNCs can be rare because of their histology or anatomical location. The federation of clinical data warehouses (CDWs) holds potential for advancing our understanding of these pathologies. This study aimed to develop a multimodal algorithm to identify rare HNC patients in a CDW. We carried out a cross-sectional study on the CDW of a conglomerate of 38 university hospitals. We developed a multimodal classification algorithm to identify rare HNC patients by integrating International Classification of Diseases, 10th revision (ICD-10) codes, Association for the Development of Computer Science in Cytology and Pathological Anatomy (ADICAP) codes and free-text data from pathology reports using natural language processing (NLP). Algorithm performance was evaluated by an HNC medical expert using a validation set of 100 manually annotated cases. Of 333 852 cancer patients, 9141 were identified as HNC patients based on ICD-10 and ADICAP codes. The multimodal algorithm using ICD-10 or ADICAP codes or NLP-processed free text classified 4515 patients as rare HNC patients, with 2168 identified by a minimum of two data sources. It showed a 91% sensitivity and a 95% specificity when relying on multiple data sources, with a 76% positive predictive value observed for rare histology identification compared with 43% for rare topography. This study demonstrates the feasibility and utility of a multimodal electronic health record-based approach to identify rare HNC patients in a CDW. Incorporating free-text and structured data improves the reliability of such cohort identification.