Locally-advanced head and neck squamous cell carcinoma (HNSCC) is mainly defined by the presence of pathologic cervical lymph nodes (LNs) with or without extracapsular spread (ECS). Current radiologic criteria to classify LNs as non-pathologic, pathologic, or pathologic with ECS are primarily shape-based. However, significantly more quantitative information is contained within imaging modalities. This quantitative information could be exploited for classification of LNs in patients with locally-advanced HNSCC by means of artificial intelligence (AI). Currently, various reviews exploring the role of AI in HNSCC are available. However, reviews specifically addressing the current role of AI to classify LN in HNSCC-patients are sparse. The present work systematically reviews original articles that specifically explore the role of AI to classify LNs in locally-advanced HNSCC applying Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines and the Study Quality Assessment Tool of National Institute of Health (NIH). Between 2001 and 2022, out of 69 studies a total of 13 retrospective, mainly monocentric, studies were identified. The majority of the studies included patients with oropharyngeal and oral cavity (9 and 7 of 13 studies, respectively) HNSCC. Histopathologic findings were defined as reference in 9 of 13 studies. Machine learning was applied in 13 studies, 9 of them applying deep learning. The mean number of included patients was 75 (SD ± 72; range 10–258) and of LNs was 340 (SD ± 268; range 21–791). The mean diagnostic accuracy for the training sets was 86% (SD ± 14%; range: 43–99%) and for testing sets 86% (SD ± 5%; range 76–92%). Consequently, all of the identified studies concluded AI to be a potentially promising diagnostic support tool for LN-classification in HNSCC. However, adequately powered, prospective, and randomized control trials are urgently required to further assess AI’s role in LN-classification in locally-advanced HNSCC.

Epithelial to mesenchymal transition (EMT) describes a process where epithelial tumor cells acquire mesenchymal characteristics. EMT often correlates with invasion and an increased cell migration potential by losing cellular polarity and cell-cell junctions. It is mainly induced by tumor-microenvironment factors, such as TGF-beta 1 and IL-6, which activate the increased expression of the EMT-transcription factor (TF) Slug. We previously reported the Slug/Krüppel-like factor 4 (KLF4) switch in EMT in HNSCC, and found, that in human papilloma virus (HPV)-negative HNSCC Slug gene expression was significant higher represented, than in HPV- positive HNSCC.

EMT promotes radio- and chemotherapy resistance in HNSCC in vitro. As EMT has been correlated to the transcription factor Slug in tumor specimens from HNSCC patients, we assessed whether Slug overexpression predicts radio- and chemotherapy resistance and favors upfront surgery in HNSCC patients. Slug expression was determined by IHC scoring in tumor specimens from patients with incident HNSCC. Patients were treated with either definitive radiotherapy or chemoradiotherapy (primary RT/CRT) or upfront surgery with or without postoperative RT or CRT (upfront surgery/PORT). Treatment failure rates and overall survival (OS) were compared between RT/CRT and upfront surgery/PORT in Slug-positive and Slug-negative patients. Slug IHC was positive in 91/354 HNSCC patients. Primary RT/CRT showed inferior response rates (univariate odds ratio (OR) for treatment failure, 3.6; 95% CI, 1.7 to 7.9; p = 0.001) and inferior 5-year OS (univariate, p < 0.001) in Slug-positive patients. The independent predictive value of Slug expression status was confirmed in a multivariable Cox model (p = 0.017). Slug-positive patients had a 3.3 times better chance of survival when treated with upfront surgery/PORT versus primary RT/CRT. For HNSCC patients, Slug IHC represents a novel and feasible predictive biomarker to support upfront surgery.

In head and neck squamous cell carcinoma (HNSCC) pathologic cervical lymph nodes (LN) remain important negative predictors. Current criteria for LN-classification in contrast-enhanced computed-tomography scans (contrast-CT) are shape-based; contrast-CT imagery allows extraction of additional quantitative data (“features”). The data-driven technique to extract, process, and analyze features from contrast-CTs is termed “radiomics”. Extracted features from contrast-CTs at various levels are typically redundant and correlated. Current sets of features for LN-classification are too complex for clinical application. Effective eliminative feature selection (EFS) is a crucial preprocessing step to reduce the complexity of sets identified. We aimed at exploring EFS-algorithms for their potential to identify sets of features, which were as small as feasible and yet retained as much accuracy as possible for LN-classification. In this retrospective cohort-study, which adhered to the STROBE guidelines, in total 252 LNs were classified as “non-pathologic” (n = 70), “pathologic” (n = 182) or “pathologic with extracapsular spread” (n = 52) by two experienced head-and-neck radiologists based on established criteria which served as a reference. The combination of sparse discriminant analysis and genetic optimization retained up to 90% of the classification accuracy with only 10% of the original numbers of features. From a clinical perspective, the selected features appeared plausible and potentially capable of correctly classifying LNs. Both the identified EFS-algorithm and the identified features need further exploration to assess their potential to prospectively classify LNs in HNSCC.

Current literature regarding survival and treatment outcome of SBRT in patients with pulmonary oligometastatic head and neck squamous cell carcinoma (HNSCC) is limited. Additionally, most of the published studies include metastatic lesions deriving also from primaries with histologies other than SCC when investigating the outcome of SBRT. The aim of the present retrospective study is to explore local control (LC) of treated metastases, progression-free survival (PFS), and overall survival (OS) of exclusively pulmonary oligometastatic HNSCC-patients treated with SBRT. Between 2006 and 2021, a total of 46 patients were treated with SBRT for a maximum of four pulmonary oligometastases (PM) concurrently (mean PM per patient = 2.0; range 1 to 6 PM, total of 92). Of these, 17 patients (37.0%) developed new pulmonary metastases after their first SBRT. Repeated courses of SBRT were required once in 15 patients (88.2%) and twice in 2 patients (11.8%). Median follow-up was 17 months (range, 0–109 months). One year after completion of SBRT, LC rate, PFS, and OS were 98.7%, 37.9%, and 79.5%, respectively. After two years, LC rate, PFS, and OS were 98.7%, 28.7%, and 54.9%; as well as 98.7%, 16.7%, and 31.0% after five years. Radiochemotherapy (HR 2.72, p < 0.001) or radiotherapy as primary treatment (HR 8.60; p = 0.003), as well as reduced patient performance status (HR 48.30, p = 0.002), were associated with lower PFS. Inferior OS correlated with poor performance status (HR 198.51, p < 0.001) and surgery followed by radiochemotherapy (HR 4.18, p = 0.032) as primary treatment, as well as radiotherapy alone (HR 7.11, p = 0.020). Treatment of more than one PM is an independent predictor of impaired OS (HR 3.30, p = 0.016). SBRT of HNSCC-derived PMs results in excellent LC rates and encouraging OS rates of 54.9% at two years along with good tolerability (no more than grade 2 toxicities). Favourable outcome and low toxicity also apply to repeated courses of SBRT of newly emerging PMs.

Background/Objectives: Head and neck squamous cell carcinoma (HNSCC) diagnosis and treatment rely heavily on computed tomography (CT) imaging to evaluate tumor characteristics and lymph node (LN) involvement, crucial for staging, prognosis, and therapy planning. Conventional LN evaluation methods based on morphological criteria such as size, shape, and anatomical location often lack sensitivity for early metastasis detection. This study leverages radiomics to extract quantitative features from CT images, addressing the limitations of subjective assessment and aiming to enhance LN classification accuracy while potentially reducing reliance on invasive histopathology. Methods: We analyzed 234 LNs from 27 HNSCC patients, deriving 120 features per node, resulting in over 25,000 data points classified into reactive, pathologic, and pathologic with extracapsular spread classes. Considering the challenges of high dimensionality and limited dataset size, more than 44,000 experiments systematically optimized machine learning models, feature selection methods, and hyperparameters, including ensemble approaches to strengthen classification robustness. A Pareto front strategy was employed to balance diagnostic accuracy with significant feature reduction. Results: The optimal model, validated via 5-fold cross-validation, achieved a balanced accuracy of 0.90, an area under the curve (AUC) of 0.93, and an F1-score of 0.88 using only five radiomics features. Conclusions: This interpretable approach aligns well with clinical radiology practice, demonstrating strong potential for clinical application in noninvasive LN classification in HNSCC.