Universal paediatric videolaryngoscopy and glottic view grading: a prospective observational study.

BACKGROUND: Although videolaryngoscopy has been proposed as a default technique for tracheal intubation in children, published evidence on universal videolaryngoscopy implementation programmes is scarce. We aimed to determine if universal, first-choice videolaryngoscopy reduces the incidence of restricted glottic views and to determine the diagnostic performance of the Cormack and Lehane classification to discriminate between easy and difficult videolaryngoscopic tracheal intubations in children. METHODS: We conducted a prospective observational study within a structured universal videolaryngoscopy implementation programme. We used C-MAC™ (Karl Storz, Tuttlingen, Germany) videolaryngoscopes in all anaesthetised children undergoing elective tracheal intubation for surgical procedures. The direct and videolaryngoscopic glottic views were classified using a six-stage grading system. RESULTS: There were 904 tracheal intubations in 809 children over a 16-month period. First attempt and overall success occurred in 607 (67%) and 903 (> 99%) tracheal intubations, respectively. Difficult videolaryngoscopic tracheal intubation occurred in 47 (5%) and airway-related adverse events in 42 (5%) tracheal intubations. Direct glottic view during laryngoscopy was restricted in 117 (13%) and the videolaryngoscopic view in 32 (4%) tracheal intubations (p < 0.001). Videolaryngoscopy improved the glottic view in 57/69 (83%) tracheal intubations where the vocal cords were only just visible, and in 44/48 (92%) where the vocal cords were not visible by direct view. The Cormack and Lehane classification discriminated poorly between easy and difficult videolaryngoscopic tracheal intubations with a mean area under the receiver operating characteristic curve of 0.68 (95%CI 0.59-0.78) for the videolaryngoscopic view compared with 0.80 (95%CI 0.73-0.87) for the direct glottic view during laryngoscopy (p = 0.005). CONCLUSIONS: Universal, first-choice videolaryngoscopy reduced substantially the incidence of restricted glottic views. The Cormack and Lehane classification was not a useful tool for grading videolaryngoscopic tracheal intubation in children.

Preoperative Acetaminophen For Microsuspension Laryngoscopy Reduces Postoperative Opioid Use.

OBJECTIVES: The opioid crisis has prompted consideration of analgesic prescriptions. This study explored the value of preoperative acetaminophen for pain control following microsuspension laryngoscopy (MSL) and compared the results with a previous study of pain and opioid use following MSL (Tsang et al.). METHODS: A prospective open-label clinical trial was conducted in patients undergoing MSL. All patients were administered preoperative acetaminophen. Short-form McGill Pain Questionnaire (SF-MPQ), pain visual analogue scale (VAS), and present pain intensity (PPI) scores were collected preoperatively and on postoperative days (PODs) 1, 3, 7, and 14. Statistical analysis identified variables associated with opioid use or increased pain scores, and compared outcomes with Tsang et al. RESULTS: Eighty-nine patients were included (mean age 52.8 ± 17.3 years, 40 males). All patients received preoperative 1 g acetaminophen (77 (86.5%) orally) with no adverse effects. On POD1, opioid usage was 10%. Median [IQR] pain scores were 5 [2-11], 21 [12.3-56.8], and 3 [2-3.3] on SF-MPQ, VAS, and PPI, respectively. Post-Anesthesia Care Unit (PACU) opioid requirements significantly correlated with POD1 opioid consumption (τb = 0.214; p ≤ 0.05), and significant associations with PACU opioid administration were found for total anesthesia time (OR (95%CI) = 1.271 (1.043-1.548), p = 0.017) and total laryngoscope suspension time (OR (95%CI) = 0.791 (0.651-0.962, p = 0.019)). This cohort demonstrated reduced opioid usage on POD1 compared with Tsang et al (23%). CONCLUSIONS: Preoperative acetaminophen is a safe intervention, resulting in decreased postoperative opioid use following MSL. Anesthesia time correlated with need for postoperative opioids. LEVEL OF EVIDENCE: Level 4 Laryngoscope, 2024.

In-office Laryngeal Procedures: a Modern Perspective for Vocal Fold Interventions

Introduction: The purpose of this article is to discuss in-office laryngeal procedures as an alternative to surgical intervention under general anesthesia. In-office procedures have become more common due to technological advancements. As a result, these approaches are less invasive and more patient-friendly, with increased pain tolerance and reduced procedure time and cost. Methods: We conducted a thematic analysis of published reports regarding the best known and performed in-office laryngeal interventions. Three questions guided our analysis: What laryngological procedures can be performed in the office setting? What are the advantages of in-office laryngology procedures compared to operating room surgical procedures? Why aren't more in-office procedures performed in some Latin American countries? Discussion: Despite being performed more frequently, there is still controversy whether in-office procedures should be performed as often due to the risk of complications. Furthermore, procedures that are done in the office setting are more popular in some countries than in others, even though their benefit has been well demonstrated. This article describes various in-office procedures, including biopsy, vocal fold injections, and laser surgery. We also discuss what factors might contribute to having office-procedures being performed more frequently in some countries than others. Conclusion: Awake interventions offer numerous benefits, including shorter procedure time, reduced costs, and lower patient morbidity. These advantages have significantly transformed the treatment of laryngeal diseases in modern laryngology practice in a global manner.

Introducción: El propósito de este artículo es discutir los procedimientos laríngeos en el consultorio como una alternativa a la intervención quirúrgica bajo anestesia general. Los procedimientos en consultorio se han vuelto más comunes debido a los avances tecnológicos. Como resultado, estos enfoques son menos invasivos y más amigables para el paciente, con mayor tolerancia al dolor y reducción del tiempo y costo del procedimiento. Métodos: Realizamos un análisis temático de los informes publicados sobre las intervenciones laríngeas más conocidas y realizadas. Tres preguntas guiaron nuestro análisis: ¿Qué procedimientos laringológicos se pueden realizar en el consultorio y cuales sin los más frecuentes?, ¿cuáles son las ventajas de los procedimientos laringológicos fuera del quirófano frente a los que se realizan bajo anestesia general?, ¿por qué no se realizan más procedimientos laringológicos en el consultorio en la mayoría de los países en Latinoamérica? Discusión: A pesar de que se realizan con mayor frecuencia, aún existe controversia sobre si los procedimientos en consultorio deben realizarse con tanta frecuencia debido al riesgo de complicaciones. Además, los procedimientos que se realizan en el consultorio son más populares en algunos países que en otros, aunque sus beneficios han sido bien demostrados. Este artículo describe varios procedimientos en el consultorio, incluida la biopsia, las inyecciones de cuerdas vocales y la cirugía con láser. También se discutieron los factores que podrían contribuir a que los procedimientos en el consultorio se realicen con más frecuencia en algunos países que en otros. Conclusión: Las intervenciones con pacientes despiertos ofrecen numerosos beneficios, incluido un tiempo de procedimiento más corto, costos reducidos y una menor morbilidad para el paciente. Estas ventajas han transformado significativamente el tratamiento de las enfermedades laríngeas en la práctica de la laringología moderna a nivel mundial.

To compare the efficacy of the between-the-fingers grip with the conventional pen-holding grip to hold an endotracheal tube for orotracheal intubation: A randomised controlled trial.

Background and Aims: Correctly holding the endotracheal tube (ETT) is essential for successful tracheal intubation. The study's primary objective was to compare the between-the-fingers grip with the conventional pen-holding grip regarding the number of attempts required for orotracheal intubation and usage of external aids. Methods: Three hundred patients undergoing elective surgeries under general anaesthesia were randomised according to the method to hold the ETT to Group C (conventional grip) and Group M (modified, between-the-fingers grip) during oro-tracheal intubation. A designated anaesthetist blinded to the groups performed laryngoscopy in all the patients, and difficult Cormack-Lehane grade 3b and 4 (n = 24) were excluded. Then, the group was revealed to the anaesthetist, and intubation was done accordingly; the number of attempts, use of backward upward rightward pressure (BURP), and time taken were noted. The sample size was estimated using the software G*Power version 3.1.9.2. Statistical Package for Social Sciences, version 23 (SPSS-23, IBM, Chicago, USA) was used for data analysis. Results: Single-attempt intubation was comparable between the groups (99.3% versus 97.2%, P = 0.197). In contrast, the external assistance as BURP (0.75% versus 6.99%, P = 0.009) and the time taken for intubation (P = 0.008) were reduced in group M significantly. Conclusion: The between-the-fingers grip seems as effective as the standard grip to hold the ETT during intubation. However, it proved to be better as it can reduce the requirement for external assistance in BURP.

Comparing the posture and comfort of anaesthesiologists during laryngoscopy and tracheal intubation in the head-elevated laryngoscopy position in supine position and with a 25° backup: A randomised clinical crossover trial.

Background and Aims: The head-elevated laryngoscopy position (HELP) and a 25° backup have been proposed to enhance glottic visualisation, yet concerns about ergonomic discomfort hinder their widespread adoption. This study compares the comfort and posture adopted by anaesthesiologists while performing laryngoscopy and tracheal intubation with patients in HELP while in a supine position or with 25° backup. Methods: The study included 48 patients aged 18-60 years with normal airways and 12 experienced anaesthesiologists. Patients were randomised into two groups using permuted block randomisation. Anaesthesiologists performed laryngoscopy and intubation in supine HELP and 25° backup HELP positions. Anaesthesiologist's posture was determined by measuring the angles of neck, wrist, elbow, back and knee joints, which were compared using Student's t-test, and subjective comfort assessed on a Likert scale was compared using the Chi-square test. As mentioned by the anaesthesiologist, Cormack- Lehane grading was also noted and compared using a Chi-square test between groups, taking a P value <0.05 as significant. Results: Both positions demonstrated comparable anaesthesiologist posture (P = 0.919) and comfort (P = 0.644). However, the 25° backup HELP positions significantly improved Cormack-Lehane grades, with 68% achieving grade 1 compared to 31% in the supine HELP group (P = 0.012). Haemodynamic stability and tracheal intubation time showed no significant differences between the groups (P = 0.475 and 0.117, respectively), and no complications were reported in either group. Conclusion: Anaesthesiologists' posture and comfort during laryngoscopy and tracheal intubation are similar between supine and 25° backup in patients with easy airways.

Laryngeal microsurgery under Transnasal Humidified Rapid Insufflation Ventilatory Exchange.

Objective: Since 2015, Transnasal Humidified Rapid Insufflation Ventilatory Exchange (THRIVE) has been used in general anesthesia for preoxygenation or difficult exposure airway management. Its use offers new opportunities in laryngology. THRIVE increases apnea time and frees the access to the upper airway. However, its use may be less stable than orotracheal intubation. The main objective of this work was to evaluate the feasibility of laryngeal microsurgery under THRIVE including using Laser. Study Design: Retrospective. Setting: A total of N = 99 patients with laryngeal microsurgery (with or without CO2 laser) under THRIVE were included successively from January 1, 2020 to January 30, 2022. Method: Medical history, comorbidities, clinical and surgical data were extracted and analyzed. Two groups were constituted regarding the "success" (use of THRIVE along all the procedure) or the "failure" (need for an endotracheal tube) of the use of THRIVE during the procedure. Results: A failure occurred in N = 15/99 patients (15.2%) mainly due to refractory hypoxia. The odd ratios (OR) for THRIVE failure were: OR = 6.6 [2.9-35] for overweight (BMI >25 kg/m2); OR = 3.8 [1.7-18.7] for ASA score >2; OR = 4.7 [2.3-24.7] for the use of CO2 laser. Elderly patients and patients with pulmonary pathology were not statistically at greater risk of THRIVE failure. No adverse event was described. Conclusion: This work confirms the feasibility of laryngeal microsurgery under THRIVE, including with CO2 laser. Overweight, ASA >2 and lower fraction of inspired oxygen during CO2 laser use increased the risk for orotracheal intubation.

Laryngeal Foreign Body Aspiration in Infancy: A Diagnostic Challenge.

Foreign body aspiration (FBA) is a significant cause of accidental death among children, with laryngeal FBA being relatively rare but potentially fatal due to airway obstruction. This report highlights a case of laryngeal FBA in an 11-month-old child, initially misdiagnosed as viral croup. Otolaryngological evaluation, particularly in the case of laryngeal FBA, may facilitate management. An 11-month-old male was brought to the emergency department, presenting with inspiratory stridor following a choking episode. A chest radiograph and CT scan of the chest were read as normal. He was suspected of having croup and treated with dexamethasone and racemic nebulized epinephrine, which led to temporary clinical improvement.  The child returned with persistent stridor to the emergency department eight days after his initial visit, prompting an otolaryngological consultation. Flexible laryngoscopy ultimately identified a star-shaped sequin lodged in the glottis. The foreign body was successfully removed via direct laryngoscopy and bronchoscopy (DLB). Following the removal, the patient demonstrated significant improvement and eventually made a full recovery. This case emphasizes the difficulty in diagnosing laryngeal FBA due to its non-specific symptoms and the limitations of imaging techniques. The importance of a thorough clinical history, physical examination, and proper imaging combined with a high index of suspicion is crucial for early diagnosis and treatment. Additionally, the report discusses the potential for severe complications if diagnosis and treatment are delayed, highlighting the need for awareness and prompt intervention in suspected laryngeal FBA cases.

Objective Comparison of White Light and Narrow-Band Imaging for Detecting Scars, Sulci and Nodules.

INTRODUCTION: Narrow-band imaging (NBI) can improve detection of lesions in the aerodigestive tract. However, its role in benign lesions of the larynx is unclear. This study aims to determine whether NBI improves the detection of scars, sulci, and nodules compared to panchromatic lighting using objective image analysis. METHODS: In total, 120 vocal folds (VFs) were analyzed with and without NBI (21 normal, 15 scars, 16 sulci, and 45 nodules). Each VF image had anterior, middle, and posterior thirds analyzed for brightness using an area morphometry software (Optimas 5.1a). The middle-third with the lesion was analyzed against surrounding VF segments for average and standard deviation (SD) in absolute grayscale. RESULTS: The use of panchromatic light resulted in greater illumination and grayscale values than NBI. All lesions tended to be in the mid-membranous fold. Under panchromatic light, change in brightness when comparing anterior versus middle (A-M) was +6.1% for normal, versus 6.5%, 8.1%, and 7.1% for sulci, nodules, and scars, respectively. Under NBI, they were 9.0% (normal), 12.3% (sulci), 13.7% (nodules), and 13.1% (scars). A greater SD of luminescence was observed at pathology sites (p < 0.05) when using NBI. The change in absolute grayscale at all lesion sites was greater when using NBI than when using panchromatic light (p < 0.05). CONCLUSION: NBI significantly enhanced the area of pathology in patients with nodules, sulci, and scars. Greater SD values in grayscale at pathologic sites were observed compared at normal sites. Thus, NBI may improve the detection of phonotraumatic lesions compared to panchromatic light. LEVEL OF EVIDENCE: N/A Laryngoscope, 2024.

Endotracheal Intubation Outside the Operating Room: Year in Review 2023.

Endotracheal intubation is a common lifesaving procedure that often is performed outside the operating room in a variety of clinical scenarios. Providers who perform intubation outside the operating room have variable degrees of training, skill development, and experience. A large number of studies were published in 2023 on the topic of intubations outside the operating room across a wide variety of settings and patient populations. Here, we review relevant papers on this topic published in 2023.

Hyperangulated vs. Macintosh videolaryngoscopy in adults with anticipated difficult airway management: a randomised controlled trial.

BACKGROUND: It is not certain whether the blade geometry of videolaryngoscopes, either a hyperangulated or Macintosh shape, affects glottic view, success rate and/or tracheal intubation time in patients with expected difficult airways. We hypothesised that using a hyperangulated videolaryngoscope blade would visualise a higher percentage of glottic opening compared with a Macintosh videolaryngoscope blade in patients with expected difficult airways. METHODS: We conducted an open-label, patient-blinded, randomised controlled trial in adult patients scheduled to undergo elective ear, nose and throat or oral and maxillofacial surgery, who were anticipated to have a difficult airway. All airway operators were consultant anaesthetists. Patients were allocated randomly to tracheal intubation with either hyperangulated (C-MAC D-BLADE™) or Macintosh videolaryngoscope blades (C-MAC™). The primary outcome was the percentage of glottic opening. First attempt success was designated a key secondary outcome. RESULTS: We assessed 2540 adults scheduled for elective head and neck surgery for eligibility and included 182 patients with expected difficult airways undergoing orotracheal intubation. The percentage of glottic opening visualised, expressed as median (IQR [range]), was 89 (69-99 [0-100])% with hyperangulated videolaryngoscope blades and 54 (9-90 [0-100])% with Macintosh videolaryngoscope blades (p < 0.001). First-line hyperangulated videolaryngoscopy failed in one patient and Macintosh videolaryngoscopy in 12 patients (13%, p = 0.002). First attempt success rate was 97% with hyperangulated videolaryngoscope blades and 67% with Macintosh videolaryngoscope blades (p < 0.001). CONCLUSIONS: Glottic view and first attempt success rate were superior with hyperangulated videolaryngoscope blades compared with Macintosh videolaryngoscope blades when used by experienced anaesthetists in patients with difficult airways.

Efficacy of bougie first approach for endotracheal intubation with video laryngoscopy during continuous chest compression: a randomized crossover manikin trial.

BACKGROUND: Endotracheal intubation is challenging during cardiopulmonary resuscitation, and video laryngoscopy has showed benefits for this procedure. The aim of this study was to compare the effectiveness of various intubation approaches, including the bougie first, preloaded bougie, endotracheal tube (ETT) with stylet, and ETT without stylet, on first-attempt success using video laryngoscopy during chest compression. METHODS: This was a randomized crossover trial conducted in a general tertiary teaching hospital. We included anesthesia residents in postgraduate year one to three who passed the screening test. Each resident performed intubation with video laryngoscopy using the four approaches in a randomized sequence on an adult manikin during continuous chest compression. The primary outcome was the first-attempt success defined as starting ventilation within a one minute. RESULTS: A total of 260 endotracheal intubations conducted by 65 residents were randomized and analyzed with 65 procedures in each group. First-attempt success occurred in 64 (98.5%), 57 (87.7%), 56 (86.2%), and 46 (70.8%) intubations in the bougie-first, preloaded bougie, ETT with stylet, and ETT without stylet approaches, respectively. The bougie-first approach had a significantly higher possibility of first-attempt success than the preloaded bougie approach [risk ratio (RR) 8.00, 95% confidence interval (CI) 1.03 to 62.16, P = 0.047], the ETT with stylet approach (RR 9.00, 95% CI 1.17 to 69.02, P = 0.035), and the ETT without stylet approach (RR 19.00, 95% CI 2.62 to 137.79, P = 0.004) in the generalized estimating equation logistic model accounting for clustering of intubations operated by the same resident. In addition, the bougie first approach did not result in prolonged intubation or increased self-reported difficulty among the study participants. CONCLUSIONS: The bougie first approach with video laryngoscopy had the highest possibility of first-attempt success during chest compression. These results helped inform the intubation approach during CPR. However, further studies in an actual clinical environment are warranted to validate these findings. TRIAL REGISTRATION: Clinicaltrials.gov; identifier: NCT05689125; date: January 18, 2023.

Multi-Instance Learning for Vocal Fold Leukoplakia Diagnosis Using White Light and Narrow-Band Imaging: A Multicenter Study.

OBJECTIVES: Vocal fold leukoplakia (VFL) is a precancerous lesion of laryngeal cancer, and its endoscopic diagnosis poses challenges. We aim to develop an artificial intelligence (AI) model using white light imaging (WLI) and narrow-band imaging (NBI) to distinguish benign from malignant VFL. METHODS: A total of 7057 images from 426 patients were used for model development and internal validation. Additionally, 1617 images from two other hospitals were used for model external validation. Modeling learning based on WLI and NBI modalities was conducted using deep learning combined with a multi-instance learning approach (MIL). Furthermore, 50 prospectively collected videos were used to evaluate real-time model performance. A human-machine comparison involving 100 patients and 12 laryngologists assessed the real-world effectiveness of the model. RESULTS: The model achieved the highest area under the receiver operating characteristic curve (AUC) values of 0.868 and 0.884 in the internal and external validation sets, respectively. AUC in the video validation set was 0.825 (95% CI: 0.704-0.946). In the human-machine comparison, AI significantly improved AUC and accuracy for all laryngologists (p < 0.05). With the assistance of AI, the diagnostic abilities and consistency of all laryngologists improved. CONCLUSIONS: Our multicenter study developed an effective AI model using MIL and fusion of WLI and NBI images for VFL diagnosis, particularly aiding junior laryngologists. However, further optimization and validation are necessary to fully assess its potential impact in clinical settings. LEVEL OF EVIDENCE: 3 Laryngoscope, 2024.

Laryngeal Cancer Screening During Flexible Video Laryngoscopy Using Large Computer Vision Models.

OBJECTIVE: Develop an artificial intelligence assisted computer vision model to screen for laryngeal cancer during flexible laryngoscopy. METHODS: Using laryngeal images and flexible laryngoscopy video recordings, we developed computer vision models to classify video frames for usability and cancer screening. A separate model segments any identified lesions on the frames. We used these computer vision models to construct a video stream annotation system. This system classifies findings from flexible laryngoscopy as "potentially malignant" or "probably benign" and segments any detected lesions. Additionally, the model provides a confidence level for each classification. RESULTS: The overall accuracy of the flexible laryngoscopy cancer screening model was 92%. For cancer screening, it achieved a sensitivity of 97.7% and a specificity of 76.9%. The segmentation model attained an average precision at a 0.50 intersection-over-union of 0.595. The confidence level for positive screening results can assist clinicians in counseling patients regarding the findings. CONCLUSION: Our model is highly sensitive and adequately specific for laryngeal cancer screening. Segmentation helps endoscopists identify and describe potential lesions. Further optimization is required to enable the model's deployment in clinical settings for real-time annotation during flexible laryngoscopy.

Comparison of Force Distribution during Laryngoscopy with the C-MAC D-BLADE and Macintosh-Style Blades: A Randomised Controlled Clinical Trial.

Background: The geometry of a laryngoscope's blade determines the forces acting on the pharyngeal structures to a relevant degree. Knowledge about the force distribution along the blade may prospectively allow for the development of less traumatic blades. Therefore, we examined the forces along the blades experienced during laryngoscopy with the C-MAC D-BLADE and blades of the Macintosh style. We hypothesised that lower peak forces are applied to the patient's pharyngeal tissue during videolaryngoscopy with a C-MAC D-BLADE compared to videolaryngoscopy with a C-MAC Macintosh-style blade and direct laryngoscopy with a Macintosh-style blade. Beyond that, we assumed that the distribution of forces along the blade differs depending on the respective blade's geometry. Methods: After ethical approval, videolaryngoscopy with the D-BLADE or the Macintosh blade, or direct laryngoscopy with the Macintosh blade (all KARL STORZ, Tuttlingen, Germany), was performed on 164 randomly assigned patients. Forces were measured at six positions along each blade and compared with regard to mean force, peak force and spatial distribution. Furthermore, the duration of the laryngoscopy was measured. Results: Mean forces (all p < 0.011) and peak forces at each sensor position (all p < 0.019) were the lowest with the D-BLADE, whereas there were no differences between videolaryngoscopy and direct laryngoscopy with the Macintosh blades (all p > 0.128). With the D-BLADE, the forces were highest at the blade's tip. In contrast, the forces were more evenly distributed along the Macintosh blades. Videolaryngoscopy took the longest with the D-BLADE (p = 0.007). Conclusions: Laryngoscopy with the D-BLADE resulted in significantly lower forces acting on pharyngeal and laryngeal tissue compared to Macintosh-style blades. Interestingly, with the Macintosh blades, we found no advantage for videolaryngoscopy in terms of force application.

Improving Laryngoscopy Image Analysis Through Integration of Global Information and Local Features in VoFoCD Dataset.

The diagnosis and treatment of vocal fold disorders heavily rely on the use of laryngoscopy. A comprehensive vocal fold diagnosis requires accurate identification of crucial anatomical structures and potential lesions during laryngoscopy observation. However, existing approaches have yet to explore the joint optimization of the decision-making process, including object detection and image classification tasks simultaneously. In this study, we provide a new dataset, VoFoCD, with 1724 laryngology images designed explicitly for object detection and image classification in laryngoscopy images. Images in the VoFoCD dataset are categorized into four classes and comprise six glottic object types. Moreover, we propose a novel Multitask Efficient trAnsformer network for Laryngoscopy (MEAL) to classify vocal fold images and detect glottic landmarks and lesions. To further facilitate interpretability for clinicians, MEAL provides attention maps to visualize important learned regions for explainable artificial intelligence results toward supporting clinical decision-making. We also analyze our model's effectiveness in simulated clinical scenarios where shaking of the laryngoscopy process occurs. The proposed model demonstrates outstanding performance on our VoFoCD dataset. The accuracy for image classification and mean average precision at an intersection over a union threshold of 0.5 (mAP50) for object detection are 0.951 and 0.874, respectively. Our MEAL method integrates global knowledge, encompassing general laryngoscopy image classification, into local features, which refer to distinct anatomical regions of the vocal fold, particularly abnormal regions, including benign and malignant lesions. Our contribution can effectively aid laryngologists in identifying benign or malignant lesions of vocal folds and classifying images in the laryngeal endoscopy process visually.

An automated approach for real-time informative frames classification in laryngeal endoscopy using deep learning.

PURPOSE: Informative image selection in laryngoscopy has the potential for improving automatic data extraction alone, for selective data storage and a faster review process, or in combination with other artificial intelligence (AI) detection or diagnosis models. This paper aims to demonstrate the feasibility of AI in providing automatic informative laryngoscopy frame selection also capable of working in real-time providing visual feedback to guide the otolaryngologist during the examination. METHODS: Several deep learning models were trained and tested on an internal dataset (n = 5147 images) and then tested on an external test set (n = 646 images) composed of both white light and narrow band images. Four videos were used to assess the real-time performance of the best-performing model. RESULTS: ResNet-50, pre-trained with the pretext strategy, reached a precision = 95% vs. 97%, recall = 97% vs, 89%, and the F1-score = 96% vs. 93% on the internal and external test set respectively (p = 0.062). The four testing videos are provided in the supplemental materials. CONCLUSION: The deep learning model demonstrated excellent performance in identifying diagnostically relevant frames within laryngoscopic videos. With its solid accuracy and real-time capabilities, the system is promising for its development in a clinical setting, either autonomously for objective quality control or in conjunction with other algorithms within a comprehensive AI toolset aimed at enhancing tumor detection and diagnosis.

Vallecular Cysts in Newborns: A Case Series Demystifying the Obscured Anomaly.

A vallecular cyst is a rare diagnosis in newborns presented with stridor, which poses a significant threat to the well-being of infants. This potentially life-threatening condition is associated with a range of complications, including respiratory distress, feeding difficulties, and failure to thrive. Through this case series, we aim to shed light on the suspicion of vallecular cysts in newborns presenting with stridor and the complexities encountered during their management, highlighting the importance of early recognition and intervention. We presented a case series consisting of three newborns who presented with stridor and respiratory distress symptoms to our center. All three cases were diagnosed using a flexible laryngoscope, and surgical intervention was done. The vallecular cyst was removed, and subsequent follow-up showed no recurrence of the lesion. This case series highlights the importance of early suspicion and recognition of vallecular cysts in newborns, emphasizing the thorough examination during diagnostic evaluations. Proper surgical planning and appropriate ventilation strategies are essential for the successful management and resolution of symptoms.

Multi-instance learning based artificial intelligence model to assist vocal fold leukoplakia diagnosis: A multicentre diagnostic study.

OBJECTIVE: To develop a multi-instance learning (MIL) based artificial intelligence (AI)-assisted diagnosis models by using laryngoscopic images to differentiate benign and malignant vocal fold leukoplakia (VFL). METHODS: The AI system was developed, trained and validated on 5362 images of 551 patients from three hospitals. Automated regions of interest (ROI) segmentation algorithm was utilized to construct image-level features. MIL was used to fusion image level results to patient level features, then the extracted features were modeled by seven machine learning algorithms. Finally, we evaluated the image level and patient level results. Additionally, 50 videos of VFL were prospectively gathered to assess the system's real-time diagnostic capabilities. A human-machine comparison database was also constructed to compare the diagnostic performance of otolaryngologists with and without AI assistance. RESULTS: In internal and external validation sets, the maximum area under the curve (AUC) for image level segmentation models was 0.775 (95 % CI 0.740-0.811) and 0.720 (95 % CI 0.684-0.756), respectively. Utilizing a MIL-based fusion strategy, the AUC at the patient level increased to 0.869 (95 % CI 0.798-0.940) and 0.851 (95 % CI 0.756-0.945). For real-time video diagnosis, the maximum AUC at the patient level reached 0.850 (95 % CI, 0.743-0.957). With AI assistance, the AUC improved from 0.720 (95 % CI 0.682-0.755) to 0.808 (95 % CI 0.775-0.839) for senior otolaryngologists and from 0.647 (95 % CI 0.608-0.686) to 0.807 (95 % CI 0.773-0.837) for junior otolaryngologists. CONCLUSIONS: The MIL based AI-assisted diagnosis system can significantly improve the diagnostic performance of otolaryngologists for VFL and help to make proper clinical decisions.

Endoscopic Dyeing and Plasma Coblation-Assisted Open Neck Surgery for Pyriform Fossa Branchial Apparatus Anomalies in Adults.

Objective: Pyriform fossa (PF) branchial apparatus anomalies (PFBAA) are rare congenital third or fourth branchial apparatus anomalies (TBAA or FBAA). This article summarizes our paradigm in managing this condition by combining endoscopic procedures and open neck surgery. Methods: A retrospective review was undertaken concerning PFBAA cases treated at our tertiary medical institution between July 2020 and November 2023. Data were collected from case records. Three sequential steps were implemented: (1) direct laryngoscopy to identify internal orifice (IO), with injection of methylene blue into it; (2) open neck surgery to resect all inflammatory tissues, focusing on the ligation of the sinus tract out of PF; and (3) plasma coblation of IO mucosa. Results: In total, 7 cases (4 men and 3 women) were included (28-67 years old, median age 53). Presenting symptoms were various, with 6 lesions on the left and 1 on the right side. Preoperative (PO) fiberoptic laryngoscopy identified IO in 6 patients, while PO barium esophageal study identified outflow from PF in 4 patients. A preliminary diagnosis of PFBAA could be established in all cases (2 TBAA and 5 FBAA cases). Direct laryngoscopy after general anesthesia identified IO in all cases (2 on the base of PF and 5 on the apex of PF). All the surgical procedures were successful, with uneventful recovery in all the patients. No postoperative complications were observed. All the patients resumed oral fluid intake after confirmation of no pharyngeal fistula by barium esophageal study on the seventh postoperative day. The duration of follow-up was between 6 and 40 months (with a median duration of 27 months). No recurrence was observed. Conclusion: Open neck surgery, assisted by endoscopic dyeing of sinus tracts and plasma coblation of IO mucosa, is a suitable treatment for PFBAA in adults. This paradigm is effective and safe for senior surgeons.