Exoscopic Transoral Supraglottic Laryngectomy.

This article, accompanied by technical notes and video, presents a case of an 85-year-old patient with a cT2N0 laryngeal squamous cell carcinoma treated using CO2 transoral laser exoscopic surgery (TOLES). The procedure achieved en bloc tumor removal with negative margins, preserving laryngeal and swallowing functions, demonstrating TOLES as a viable alternative to traditional microsurgery with enhanced visualization and ergonomics. Laryngoscope, 2024.

Is precision medicine the solution to improve organ preservation in laryngeal/hypopharyngeal cancer? A position paper by the Preserve Research Group.

In locally advanced (LA) laryngeal/hypopharyngeal squamous cell carcinoma (LHSCC), larynx preservation (LP) strategies aim at the cure of the disease while preserving a functional larynx, thus avoiding total laryngectomy and the associated impact on the quality of life. In the last decades, apart from transoral and open-neck organ preservation approaches, several non-surgical regimens have been investigated: radiotherapy alone, alternate, concurrent or sequential chemoradiation, and bioradiotherapy. Despite major progress, the identification of reliable and effective predictors for treatment response remains a clinical challenge. This review examines the current state of LP in LA-LHSCC and the need for predictive factors, highlighting the importance of the PRESERVE trial in addressing this gap. The PRESERVE trial represents a pivotal initiative aimed at finding the optimal therapy for laryngeal preservation specific to each patient through a retrospective analysis of data from previous LP trials and prospectively validating findings. The goal of the PRESERVE trial is to develop a comprehensive predictive classifier that integrates clinical, molecular, and multi-omics data, thereby enhancing the precision and efficacy of patient selection for LP protocols.

Artificial intelligence-enhanced opportunistic screening of osteoporosis in CT scan: a scoping Review.

PURPOSE: This scoping review aimed to assess the current research on artificial intelligence (AI)--enhanced opportunistic screening approaches for stratifying osteoporosis and osteopenia risk by evaluating vertebral trabecular bone structure in CT scans. METHODS: PubMed, Scopus, and Web of Science databases were systematically searched for studies published between 2018 and December 2023. Inclusion criteria encompassed articles focusing on AI techniques for classifying osteoporosis/osteopenia or determining bone mineral density using CT scans of vertebral bodies. Data extraction included study characteristics, methodologies, and key findings. RESULTS: Fourteen studies met the inclusion criteria. Three main approaches were identified: fully automated deep learning solutions, hybrid approaches combining deep learning and conventional machine learning, and non-automated solutions using manual segmentation followed by AI analysis. Studies demonstrated high accuracy in bone mineral density prediction (86-96%) and classification of normal versus osteoporotic subjects (AUC 0.927-0.984). However, significant heterogeneity was observed in methodologies, workflows, and ground truth selection. CONCLUSIONS: The review highlights AI's promising potential in enhancing opportunistic screening for osteoporosis using CT scans. While the field is still in its early stages, with most solutions at the proof-of-concept phase, the evidence supports increased efforts to incorporate AI into radiologic workflows. Addressing knowledge gaps, such as standardizing benchmarks and increasing external validation, will be crucial for advancing the clinical application of these AI-enhanced screening methods. Integration of such technologies could lead to improved early detection of osteoporotic conditions at a low economic cost.

Computer Vision and Videomics in Otolaryngology-Head and Neck Surgery: Bridging the Gap Between Clinical Needs and the Promise of Artificial Intelligence.

This article discusses the role of computer vision in otolaryngology, particularly through endoscopy and surgery. It covers recent applications of artificial intelligence (AI) in nonradiologic imaging within otolaryngology, noting the benefits and challenges, such as improving diagnostic accuracy and optimizing therapeutic outcomes, while also pointing out the necessity for enhanced data curation and standardized research methodologies to advance clinical applications. Technical aspects are also covered, providing a detailed view of the progression from manual feature extraction to more complex AI models, including convolutional neural networks and vision transformers and their potential application in clinical settings.

Artificial intelligence for automatic detection and segmentation of nasal polyposis: a pilot study.

PURPOSE: Accurate diagnosis and quantification of polyps and symptoms are pivotal for planning the therapeutic strategy of Chronic rhinosinusitis with nasal polyposis (CRSwNP). This pilot study aimed to develop an artificial intelligence (AI)-based image analysis system capable of segmenting nasal polyps from nasal endoscopy videos. METHODS: Recorded nasal videoendoscopies from 52 patients diagnosed with CRSwNP between 2019 and 2022 were retrospectively analyzed. Images extracted were manually segmented on the web application Roboflow. A dataset of 342 images was generated and divided into training (80%), validation (10%), and testing (10%) sets. The Ultralytics YOLOv8.0.28 model was employed for automated segmentation. RESULTS: The YOLOv8s-seg model consisted of 195 layers and required 42.4 GFLOPs for operation. When tested against the validation set, the algorithm achieved a precision of 0.91, recall of 0.839, and mean average precision at 50% IoU (mAP50) of 0.949. For the segmentation task, similar metrics were observed, including a mAP ranging from 0.675 to 0.679 for IoUs between 50% and 95%. CONCLUSIONS: The study shows that a carefully trained AI algorithm can effectively identify and delineate nasal polyps in patients with CRSwNP. Despite certain limitations like the focus on CRSwNP-specific samples, the algorithm presents a promising complementary tool to existing diagnostic methods.

Computer Vision Foundation Models in Endoscopy: Proof of Concept in Oropharyngeal Cancer.

OBJECTIVES: To evaluate the performance of vision transformer-derived image embeddings for distinguishing between normal and neoplastic tissues in the oropharynx and to investigate the potential of computer vision (CV) foundation models in medical imaging. METHODS: Computational study using endoscopic frames with a focus on the application of a self-supervised vision transformer model (DINOv2) for tissue classification. High-definition endoscopic images were used to extract image patches that were then normalized and processed using the DINOv2 model to obtain embeddings. These embeddings served as input for a standard support vector machine (SVM) to classify the tissues as neoplastic or normal. The model's discriminative performance was validated using an 80-20 train-validation split. RESULTS: From 38 endoscopic NBI videos, 327 image patches were analyzed. The classification results in the validation cohort demonstrated high accuracy (92%) and precision (89%), with a perfect recall (100%) and an F1-score of 94%. The receiver operating characteristic (ROC) curve yielded an area under the curve (AUC) of 0.96. CONCLUSION: The use of large vision model-derived embeddings effectively differentiated between neoplastic and normal oropharyngeal tissues. This study supports the feasibility of employing CV foundation models like DINOv2 in the endoscopic evaluation of mucosal lesions, potentially augmenting diagnostic precision in Otorhinolaryngology. LEVEL OF EVIDENCE: 4 Laryngoscope, 2024.

The predictive role of PD-L1 in head and neck cancer: A systematic review and meta-analysis.

This systematic review and meta-analysis investigates the predictive and prognostic role of PD-L1 expression in treating head and neck squamous cell carcinoma (HNSCC). Recognizing the importance of PD-L1 in patient response to treatment, the main objective was to assess its impact on overall survival and progression-free survival in HNSCC patients. A thorough search of databases such as PubMed, Scopus, and Web of Science from 2010 to 2022, along with relevant articles and references, yielded 120 studies. Of these, 7 met the criteria focusing on HNSCC patients, PD-L1 expression evaluation, and treatment with PD-1 or PD-L1 inhibitors. Data extraction followed PRISMA guidelines and involved independent review and consensus for discrepancies. The primary outcomes analyzed were overall survival and progression-free survival in relation to PD-L1 expression levels in patients undergoing immunotherapy.Theseven randomized controlled trials selected had a total of 4,477 participants. Results showed that patients with positive PD-L1 expression experienced improved overall survival when treated with PD-1 or PD-L1 inhibitors, particularly those with high PD-L1 expression. However, PD-L1 expression did not significantly affect progression-free survival. These findings suggest that PD-L1 expression can be a predictive marker for better overall survival in HNSCC patients treated with immunotherapy. However, its influence on progression-free survival remains unclear, indicating the need for further research.

Evaluation of DNA methylation levels of SEPT9 and SHOX2 in plasma of patients with head and neck squamous cell carcinoma using droplet digital PCR.

Head and neck squamous cell carcinoma (HNSCC) is the seventh most commonly diagnosed cancer globally. HNSCC develops from the mucosa of the oral cavity, pharynx and larynx. Methylation levels of septin 9 (SEPT9) and short stature homeobox 2 (SHOX2) genes in circulating cell­free DNA (ccfDNA) are considered epigenetic biomarkers and have shown predictive value in preliminary reports in HNSCC. Liquid biopsy is a non­invasive procedure that collects tumor­derived molecules, including ccfDNA. In the present study, a droplet digital PCR (ddPCR)­based assay was developed to detect DNA methylation levels of circulating SEPT9 and SHOX2 in the plasma of patients with HNSCC. The assay was first set up using commercial methylated and unmethylated DNA. The dynamic changes in the methylation levels of SEPT9 and SHOX2 were then quantified in 20 patients with HNSCC during follow­up. The results highlighted: i) The ability of the ddPCR­based assay to detect very low copies of methylated molecules; ii) the significant decrease in SEPT9 and SHOX2 methylation levels in the plasma of patients with HNSCC at the first time points of follow­up with respect to T0; iii) a different trend of longitudinally DNA methylation variations in small groups of stratified patients. The absolute and precise quantification of SEPT9 and SHOX2 methylation levels in HNSCC may be useful for studies with translational potential.

Long-term health-related quality of life in head and neck cancer survivors: A large multinational study.

Head and neck cancer (HNC) patients suffer from a range of health-related quality of life (HRQoL) issues, but little is known about their long-term HRQoL. This study explored associations between treatment group and HRQoL at least 5 years' post-diagnosis in HNC survivors. In an international cross-sectional study, HNC survivors completed the European Organization for Research and Treatment of Cancer (EORTC) quality of life core questionnaire (EORTC-QLQ-C30) and its HNC module (EORTC-QLQ-H&N35). Meaningful HRQoL differences were examined between five treatment groups: (a) surgery, (b) radiotherapy, (c) chemo-radiotherapy, (d) radiotherapy ± chemotherapy and neck dissection and (e) any other surgery (meaning any tumour surgery that is not a neck dissection) and radiotherapy ± chemotherapy. Twenty-six sites in 11 countries enrolled 1105 survivors. They had a median time since diagnosis of 8 years, a mean age of 66 years and 71% were male. After adjusting for age, sex, tumour site and UICC stage, there was evidence for meaningful differences (10 points or more) in HRQoL between treatment groups in seven domains (Fatigue, Mouth Pain, Swallowing, Senses, Opening Mouth, Dry Mouth and Sticky Saliva). Survivors who had single-modality treatment had better or equal HRQoL in every domain compared to survivors with multimodal treatment, with the largest differences for Dry Mouth and Sticky Saliva. For Global Quality of Life, Physical and Social Functioning, Constipation, Dyspnoea and Financial Difficulties, at least some treatment groups had better outcomes compared to a general population. Our data suggest that multimodal treatment is associated with worse HRQoL in the long-term compared to single modality.

Real-Time Laryngeal Cancer Boundaries Delineation on White Light and Narrow-Band Imaging Laryngoscopy with Deep Learning.

OBJECTIVE: To investigate the potential of deep learning for automatically delineating (segmenting) laryngeal cancer superficial extent on endoscopic images and videos. METHODS: A retrospective study was conducted extracting and annotating white light (WL) and Narrow-Band Imaging (NBI) frames to train a segmentation model (SegMENT-Plus). Two external datasets were used for validation. The model's performances were compared with those of two otolaryngology residents. In addition, the model was tested on real intraoperative laryngoscopy videos. RESULTS: A total of 3933 images of laryngeal cancer from 557 patients were used. The model achieved the following median values (interquartile range): Dice Similarity Coefficient (DSC) = 0.83 (0.70-0.90), Intersection over Union (IoU) = 0.83 (0.73-0.90), Accuracy = 0.97 (0.95-0.99), Inference Speed = 25.6 (25.1-26.1) frames per second. The external testing cohorts comprised 156 and 200 images. SegMENT-Plus performed similarly on all three datasets for DSC (p = 0.05) and IoU (p = 0.07). No significant differences were noticed when separately analyzing WL and NBI test images on DSC (p = 0.06) and IoU (p = 0.78) and when analyzing the model versus the two residents on DSC (p = 0.06) and IoU (Senior vs. SegMENT-Plus, p = 0.13; Junior vs. SegMENT-Plus, p = 1.00). The model was then tested on real intraoperative laryngoscopy videos. CONCLUSION: SegMENT-Plus can accurately delineate laryngeal cancer boundaries in endoscopic images, with performances equal to those of two otolaryngology residents. The results on the two external datasets demonstrate excellent generalization capabilities. The computation speed of the model allowed its application on videolaryngoscopies simulating real-time use. Clinical trials are needed to evaluate the role of this technology in surgical practice and resection margin improvement. LEVEL OF EVIDENCE: III Laryngoscope, 134:2826-2834, 2024.

Thyroid cartilage infiltration in advanced laryngeal cancer: prognostic implications and predictive modelling.

Objective: Detection of laryngeal cartilage invasion is of great importance in staging of laryngeal squamous cell carcinoma (LSCC). The role of prognosticators in locally advanced laryngeal cancer are still widely debated. This study aimed to assess the impact of volume of thyroid cartilage infiltration, as well as other histopathologic variables, on patient survival. Materials and methods: We retrospectively analysed 74 patients affected by pT4 LSCC and treated with total laryngectomy between 2005 and 2021 at the Department of Otorhinolaryngology - Head and Neck Surgery of the University of Brescia, Italy. We considered as potential prognosticators histological grade, perineural (PNI) and lympho-vascular invasion (LVI), thyroid cartilage infiltration, and pTN staging. Pre-operative CT or MRI were analysed to quantify the volume of cartilage infiltration using 3D Slicer software. Results: The 1-, 3-, and 5-year disease free survivals (DFS) were 76%, 66%, and 64%, respectively. Using machine learning models, we found that the volume of thyroid cartilage infiltration had high correlation with DFS. Patients with a higher volume (>670 mm3) of infiltration had a worse prognosis compared to those with a lower volume. Conclusions: Our study confirms the essential role of LVI as prognosticator in advanced LSCC and, more innovatively, highlights the volume of thyroid cartilage infiltration as another promising prognostic factor.

Reliability of large language models in managing odontogenic sinusitis clinical scenarios: a preliminary multidisciplinary evaluation.

PURPOSE: This study aimed to evaluate the utility of large language model (LLM) artificial intelligence tools, Chat Generative Pre-Trained Transformer (ChatGPT) versions 3.5 and 4, in managing complex otolaryngological clinical scenarios, specifically for the multidisciplinary management of odontogenic sinusitis (ODS). METHODS: A prospective, structured multidisciplinary specialist evaluation was conducted using five ad hoc designed ODS-related clinical scenarios. LLM responses to these scenarios were critically reviewed by a multidisciplinary panel of eight specialist evaluators (2 ODS experts, 2 rhinologists, 2 general otolaryngologists, and 2 maxillofacial surgeons). Based on the level of disagreement from panel members, a Total Disagreement Score (TDS) was calculated for each LLM response, and TDS comparisons were made between ChatGPT3.5 and ChatGPT4, as well as between different evaluators. RESULTS: While disagreement to some degree was demonstrated in 73/80 evaluator reviews of LLMs' responses, TDSs were significantly lower for ChatGPT4 compared to ChatGPT3.5. Highest TDSs were found in the case of complicated ODS with orbital abscess, presumably due to increased case complexity with dental, rhinologic, and orbital factors affecting diagnostic and therapeutic options. There were no statistically significant differences in TDSs between evaluators' specialties, though ODS experts and maxillofacial surgeons tended to assign higher TDSs. CONCLUSIONS: LLMs like ChatGPT, especially newer versions, showed potential for complimenting evidence-based clinical decision-making, but substantial disagreement was still demonstrated between LLMs and clinical specialists across most case examples, suggesting they are not yet optimal in aiding clinical management decisions. Future studies will be important to analyze LLMs' performance as they evolve over time.

Classifying Vocal Folds Fixation from Endoscopic Videos with Machine Learning.

Vocal folds motility evaluation is paramount in both the assessment of functional deficits and in the accurate staging of neoplastic disease of the glottis. Diagnostic endoscopy, and in particular videoendoscopy, is nowadays the method through which the motility is estimated. The clinical diagnosis, however, relies on the examination of the videoendoscopic frames, which is a subjective and professional-dependent task. Hence, a more rigorous, objective, reliable, and repeatable method is needed. To support clinicians, this paper proposes a machine learning (ML) approach for vocal cords motility classification. From the endoscopic videos of 186 patients with both vocal cords preserved motility and fixation, a dataset of 558 images relative to the two classes was extracted. Successively, a number of features was retrieved from the images and used to train and test four well-grounded ML classifiers. From test results, the best performance was achieved using XGBoost, with precision = 0.82, recall = 0.82, F1 score = 0.82, and accuracy = 0.82. After comparing the most relevant ML models, we believe that this approach could provide precise and reliable support to clinical evaluation.Clinical Relevance- This research represents an important advancement in the state-of-the-art of computer-assisted otolaryngology, to develop an effective tool for motility assessment in the clinical practice.

Treatment and outcomes of minor salivary gland cancers of the larynx and trachea: a systematic review.

Objectives: Malignant minor salivary glands carcinomas (MiSGC) of the larynx and trachea are rare tumours and published evidence is sparse. We conducted a systematic review to describe shareable treatment strategies and oncological outcomes of these neoplastic entities. Methods: Full text English manuscripts published from January 1st 2000 to December 14th 2022 were included. Data on demographics, treatments and outcomes were collected. A pooled analysis of 5-year overall survival (OS) was performed. Results: Seventeen articles and 365 patients met the inclusion criteria. The most common subsites involved were subglottic and distal trachea. Adenoid cystic carcinoma was, by far, the most frequent histotype. The first-choice treatment strategy was surgery (86.8%), while adjuvant treatments were delivered in 57.4% of patients. Only 12.9% were treated with definitive radiotherapy with/without chemotherapy. The mean follow-up was 68.3 months. One hundred nine (34.9%) deaths were recorded and 62.4% were cancer-related. Five-year OS ranged from 20% to 100% and, at pooled analysis, it was 83% (range, 78-87%). Conclusions: In case of MiSGC of the larynx and trachea, surgery remains the mainstay of treatment. Adjuvant treatments are frequently delivered. Survival estimates are good overall, but highly heterogeneous.

Revisiting the concept of neoadjuvant and induction therapy in head and neck cancer with the advent of immunotherapy.

The treatment of locally advanced (LA) Head and Neck Squamous Cell Carcinoma (HNSCC) is based on surgery followed by (chemo)radiation or on curative (chemo)radiation, depending on site and stage. Despite optimal locoregional treatment, about 50% of patients recur, with a huge impact on prognosis and substantial morbidity. The advent of immunotherapy (IT) with immune checkpoint inhibitors (ICIs) changed the paradigm of systemic treatment for recurrent/metastatic (RM) disease, showing activity, efficacy, and safety in both platinum-resistant and platinum-naïve patients. Such data led clinicians to design clinical trials to investigate early administration of IT even in the neoadjuvant or window of opportunity setting. In this review, we examine the published and ongoing trials investigating IT in the neoadjuvant setting for LA HNSCC. We address the current challenges of this treatment modality: optimal patient selection for neoadjuvant IT; choosing the appropriate systemic approach to enhance response without compromising tolerability; determining the ideal study endpoint, with a focus on major pathological response as a potential surrogate for overall survival; evaluating treatment response through imaging, considering the discordance between radiological and pathological assessments; and the influence of neoadjuvant IT response on locoregional treatment de-escalation strategies.

Instance segmentation of upper aerodigestive tract cancer: site-specific outcomes.

Objective: To achieve instance segmentation of upper aerodigestive tract (UADT) neoplasms using a deep learning (DL) algorithm, and to identify differences in its diagnostic performance in three different sites: larynx/hypopharynx, oral cavity and oropharynx. Methods: A total of 1034 endoscopic images from 323 patients were examined under narrow band imaging (NBI). The Mask R-CNN algorithm was used for the analysis. The dataset split was: 935 training, 48 validation and 51 testing images. Dice Similarity Coefficient (Dsc) was the main outcome measure. Results: Instance segmentation was effective in 76.5% of images. The mean Dsc was 0.90 ± 0.05. The algorithm correctly predicted 77.8%, 86.7% and 55.5% of lesions in the larynx/hypopharynx, oral cavity, and oropharynx, respectively. The mean Dsc was 0.90 ± 0.05 for the larynx/hypopharynx, 0.60 ± 0.26 for the oral cavity, and 0.81 ± 0.30 for the oropharynx. The analysis showed inferior diagnostic results in the oral cavity compared with the larynx/hypopharynx (p < 0.001). Conclusions: The study confirms the feasibility of instance segmentation of UADT using DL algorithms and shows inferior diagnostic results in the oral cavity compared with other anatomic areas.