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.

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, 134:4066-4070, 2024.

Ultrasound in Causes of Stridor in Children.

Airway ultrasound (US) is an easily available, portable, radiation-free imaging modality for quick, non-invasive, dynamic evaluation of the airway without sedation. This is useful in children with stridor, which is an emergency due to upper airway obstruction requiring immediate management. Several causes of stridor including laryngomalacia, laryngeal cyst, subglottic hemangioma, vocal cord palsy, and lymphatic malformations can be evaluated accurately. Thin musculature and unossified cartilages in children provide a good acoustic window. Thus, airway US is valuable, but underutilized for the evaluation of children with stridor. In this case-based review, we describe the technique, indications, anatomy, and pathologies on airway US.

Swallowing computed tomography and virtual reality as novel imaging modalities for the diagnosis of clicking larynx: Two case reports.

Globus sensation and pain causes are difficult to identify by conventional examination methods. With technology advances, new imaging methods including swallowing computed tomography (CT) and virtual reality (VR) have emerged and are contributing to definite diagnoses. We report two cases of cervical discomfort diagnosed as clicking larynx using swallowing CT/VR . Case 1 is a 55-year-old man. There were no findings on laryngoscopy or swallowing examinations, but swallowing CT/VR showed that the thyroid cartilage collided with the hyoid bone during swallowing, leading to the diagnosis of a clicking larynx. The patient was obese and is under observation hoping that weight loss will improve symptoms. Case 2 is a 32-year-old transgender man. He is receiving male hormones for gender identity disorder. He was diagnosed with a clicking larynx using swallowing CT/VR. Hormonal therapy may have increased the size of the thyroid cartilage, likely causing the symptoms. As they didn't choose surgical treatment, no symptomatic relief was achieved, but identifiying the cause contributed to improved patient satisfaction. Swallowing CT/VR is useful not only for evaluating the swallowing function, but also the underlying etiology of globus sensation and pain upon swallowing. Further clinical applications of this technique are expected for motion induced cervical symptoms.

Epiglottic Cyst With Slurred Speech Misdiagnosed as Acute Cerebral Infarction: A Case Report.

INTRODUCTION: Epiglottic cysts are cysts that occur under the mucosa of the epiglottis. Patients with severe cysts may have difficulty in breathing. Slurred speech usually occurs in cerebrovascular diseases, especially with slurred speech as the starting symptom. CASE REPORT: We describe the case of a patient with slurred speech as the first symptom. The patient was a 53-year-old man with slurred speech as the first symptom, and he was initially considered to have an acute cerebral infarction. However, the results of the cranial magnetic resonance imaging examination did not support the diagnosis. The possibility of neck tumor recurrence was considered based on past medical history. The findings of a computed tomography examination of the neck suggested an epiglottic cyst. The effect of anti-inflammatory and surgical treatment was significant, and speech returned to normal. CONCLUSION: This case emphasizes that neurologists need to be vigilant when dealing with patients with slurred speech, which may be one of the clinical manifestations of epiglottic cysts.

Rare cause of voice muffling: pyogenic vallecular cyst.

A vallecular cyst is a benign laryngeal cyst that rarely causes symptoms in adults. We report a rare case of an infected vallecular cyst in a man who is in his 60s with diabetes mellitus. The patient presented to us with acute onset of voice muffling and respiratory distress. He showed signs of sepsis and upper airway obstruction. He had spikes of high-grade fever with an elevated total white cell count (predominantly neutrophil count) and C reactive protein level. Plain cervical X-ray revealed a large, smooth, lobulated mass in the vallecular area. Direct laryngoscopic findings supported the diagnosis of an infected vallecular cyst with suppuration, which originated from the vallecula fossa. The cyst was drained and excised completely, and the pus culture revealed the presence of Klebsiella pneumoniae The patient responded well to the administration of intravenous cefuroxime for 2 weeks according to the sensitivity and culture test. He was discharged after the completion of the course of antibiotics, having recovered fully. This case illustrates the versatility of a plain cervical X-ray in giving clues about this rare, unexpected pathology.

OpenHSV: an open platform for laryngeal high-speed videoendoscopy.

High-speed videoendoscopy is an important tool to study laryngeal dynamics, to quantify vocal fold oscillations, to diagnose voice impairments at laryngeal level and to monitor treatment progress. However, there is a significant lack of an open source, expandable research tool that features latest hardware and data analysis. In this work, we propose an open research platform termed OpenHSV that is based on state-of-the-art, commercially available equipment and features a fully automatic data analysis pipeline. A publicly available, user-friendly graphical user interface implemented in Python is used to interface the hardware. Video and audio data are recorded in synchrony and are subsequently fully automatically analyzed. Video segmentation of the glottal area is performed using efficient deep neural networks to derive glottal area waveform and glottal midline. Established quantitative, clinically relevant video and audio parameters were implemented and computed. In a preliminary clinical study, we recorded video and audio data from 28 healthy subjects. Analyzing these data in terms of image quality and derived quantitative parameters, we show the applicability, performance and usefulness of OpenHSV. Therefore, OpenHSV provides a valid, standardized access to high-speed videoendoscopy data acquisition and analysis for voice scientists, highlighting its use as a valuable research tool in understanding voice physiology. We envision that OpenHSV serves as basis for the next generation of clinical HSV systems.

Diagnostic Value of Narrow Band Imaging in Visualization of Pathological Lesions in Larynx and Hypopharynx.

INTRODUCTION: Narrow Band Imaging (NBI) is an endoscopic optical imaging enhancement technology that improves the contrast of mucosal surface texture and enhances visualization of mucosal and submucosal vasculature. Due to its properties, it can visualize suspected malignant or precancerous lesions earlier than conventional white light endoscopy. The aim of this study was to analyze the benefit of NBI in visualization of precancerous and malignant lesions in preoperative and intraoperative diagnostics and correlation with histopathologic results. METHODS: A total of 589 patients with suspicious laryngeal or hypopharyngeal lesion were investigated using conventional white light endoscopy (WLE) and NBI endoscopy with high-definition TV (HDTV NBI) from 10/2013 to 12/2019. Patients were divided into two groups based on pre-operative NBI examination (group A, 345 patients) and intraoperative NBI examination (group B, 244 patients). All suspicious lesions were graded to 5 types of Ni classification and correlated with histopathologic results. The SPSS version 8.0.4 statistical software package was used for statistical analysis. In diagnosing premalignant and malignant lesions sensitivity, specificity, positive predictive value, and negative predictive value were calculated. RESULTS: The agreement between NBI endoscopy and histopathological analysis in group A was statistically significant (Қ = 0.76, p < 0.001), with a sensitivity of 86.2% (95% IS: 65.4-95.2) and specificity of 90.9% (95% IS: 70.6-94.1). Moreover, in group B was proven almost perfect agreement between NBI and histopathological analysis (Қ = 0.8461, p < 0.001), with a sensitivity of 84.0% (95% IS: 60.2-92.4) and specificity of 96.0% (95% IS: 87.0-99.2). CONCLUSIONS: Based on our results, NBI using the Ni classification has great potential in improving diagnosis of precancerous and malignant lesions and correlates strongly with histopathologic results. It serves as a useful adjunct to white light endoscopy in the diagnosis of laryngeal and hypopharyngeal lesions, especially using HDTV NBI.

Localised laryngotracheal amyloidosis: a differential diagnosis not to forget.

We present a case of multifocal laryngotracheal amyloidosis (LTA) in a 43-year-old man with persistent and progressive dysphonia and dyspnoea, and a first inconclusive histology. Although laryngeal amyloidosis accounts for fewer than 1% of all benign laryngeal tumours, it is in fact the most common site of amyloid deposition in the head, neck and respiratory tract. The clinical scenario is non-specific and diagnosis depends on a high degree of suspicion and on histology. Imaging is useful in mapping lesions, which are often more extensive than they appear during laryngoscopy. Despite being a benign entity, the prognosis is variable with a high-rate and long-latency recurrences, requiring long-term follow-up.

Diagnostic Value and Pathological Correlation of Narrow Band Imaging Classification in Laryngeal Lesions.

OBJECTIVES: To explore the diagnostic value and pathological correlation of narrow band imaging (NBI) classification in laryngeal lesions. METHODS: A total of 112 patients (123 lesions) with laryngeal lesions from July 2018 to May 2019 were selected in this study. All patients were examined by NBI and white light imaging endoscopy. The NBI endoscopy was applied to classify the observed lesion sites according to intraepithelial papillary capillary loop pattern. The gold standard of diagnosis was pathological results. To evaluate the consistency of NBI classification and pathological results. RESULTS: The sensitivity, specificity, positive predictive value, and negative predictive value of the diagnosis for benign, precancerous, and malignant lesions under the NBI endoscopy were 90.91%, 81.19%, 74.07%, 85.42%; 41.67%, 92.93%, 58.82%, 86.79%; and 93.51%, 65.22%, 91.14%, 68.18%, respectively. There was a high consistency between NBI classification and pathological results (κ = 0.679, P < .001). CONCLUSIONS: The NBI classification can improve the accuracy of the diagnosis of laryngeal lesions. It is important for early diagnosis and treatment of vocal cord leukoplakia and laryngeal cancer.

Videolaryngoscopy Quality with Protective Cover of Intraoral Odontologic Camera Evaluation in Vocal Fold Coverage Lesions.

INTRODUCTION: The examination of the larynx with indirect visualization is one of a series of steps in otorhinolaryngological evaluation. In the past this exam was performed more commonly with mirrors and headlights, but for at least the last four decades physicians have resorted to assessing the laryngopharynx with both rigid and fiberoptic instruments. The rigid 70° laryngoscope is the most used in our practice, its main drawback being the time-consuming resterilization process needed between scope usages in different patients. Recently we have been using a disposable protective cover over the rigid scope to obviate instrument contamination and thus the office time delays. OBJECTIVE: To investigate the maintenance of image quality in videolaryngoscopy (VDL), with and without a protective cover of intraoral odontologic camera (PCIOC), in patients with benign lesions of the vocal fold. METHODS: Quantitative and accurate cross-sectional study of VDL images with and without PCIOC. The images were captured by videolaringoscope of digital camera chip-on-the-tip type in an otorhinolaryngological care center. We studied patients presenting with vocal fold nodules, intracordal cysts, polyps, and Reinke's edema. All judges evaluating the images were otorhinolaryngologists. The exams with and without PCIOC were presented in a randomized form. The data of professionals' answers were analyzed by means of descriptive statistics and application of variables association tests. RESULTS: Thirty professionals participated in the study. There was no statistically significant difference between the probability of success in exams performed with or without PCIOC, nor between the perception of image quality and the number of correct answers in the diagnosis. In the polyp lesion without PCIOC there was a statistically significant difference between the confidence level of the diagnosis (and the number of correct answers (P = 0.037). CONCLUSION: There is no difference between VDL diagnoses of vocal fold coverage lesions with and without PCIOC, maintaining image quality in both VDL exams.

Clicking larynx syndrome - a diagnostic and surgical challenge.

When swallowing, a clicking in the throat may uncommonly occur, causing great discomfort and pain. This unpleasant event may lead health professionals to attribute the symptoms to psychogenic aetiology. The case of a 49-year-old female is presented, who reported an audible bilateral clicking in the throat, associated with neck and throat pain when swallowing or turning her neck. From the ENT examination and palpation of the neck during patient swallowing, we located the source of the clicking on the left. However, during palpation from side to side, the patient suffered bilateral pain. Laryngeal computed tomography with a 3D reconstruction showed a short distance between the hyoid bone and the superior part of the thyroid cornua, accompanied by posterior-medially displaced bilateral superior cornua in the thyrohyoid region. The bilateral sensation of throat pain during swallowing or palpation, in combination with our desire to maintain laryngeal symmetry, led us to a two-sided exeresis of the superior thyroid cornua. This resulted in immediate and complete relief of the symptoms. Although it is an uncommon complaint, clicking larynx syndrome should be considered as a differential diagnosis.

Dual-energy CT for differentiating early glottic squamous cell carcinoma from chronic inflammation and leucoplakia of vocal cord: comparison with simulated conventional 120 kVp CT.

AIM: To evaluate the value of dual-energy (DE) computed tomography (CT) in discriminating early glottic squamous cell carcinoma (eGSCC) from chronic inflammation and leucoplakia of the vocal cord, and to compare the diagnostic efficiency of DECT with that of simulated conventional 120 kVp CT. MATERIALS AND METHODS: Seventy patients with glottic lesions confirmed by histopathology (38 cases with eGSCC, 11 cases with chronic inflammation, 21 cases with leucoplakia) were enrolled in this prospective study. The DECT-derived parameters were measured and compared using independent sample t-test. Receiver operating characteristic (ROC) curve was performed to evaluate the diagnostic performance, and comparison of the area under the ROC curve (AUC) was made using the Z test to further select the best diagnostic parameters. RESULTS: Significantly higher iodine concentration (IC), normalised IC (NIC), effective atomic number (Zeff), 40-100 keV (20 keV-interval), slope(k), and Mix-0.3 values were found in eGSCC than those in chronic inflammation, leucoplakia, and inflammation + leucoplakia (all p<0.05). Compared with attenuation measurement of simulated conventional 120 kVp CT, the NIC, 60 keV values derived from DECT showed significantly higher AUC in discriminating these glottic lesions (p<0.05). CONCLUSIONS: DECT is more accurate for differentiating eGSCC from chronic inflammation and leucoplakia when compared with simulated conventional 120 kVp CT.

Neural endophenotypes and predictors of laryngeal dystonia penetrance and manifestation.

Focal dystonias are the most common forms of isolated dystonia; however, the etiopathophysiological signatures of disorder penetrance and clinical manifestation remain unclear. Using an imaging genetics approach, we investigated functional and structural representations of neural endophenotypes underlying the penetrance and manifestation of laryngeal dystonia in families, including 21 probands and 21 unaffected relatives, compared to 32 unrelated healthy controls. We further used a supervised machine-learning algorithm to predict the risk for dystonia development in susceptible individuals based on neural features of identified endophenotypes. We found that abnormalities in prefrontal-parietal cortex, thalamus, and caudate nucleus were commonly shared between patients and their unaffected relatives, representing an intermediate endophenotype of laryngeal dystonia. Machine learning classified 95.2% of unaffected relatives as patients rather than healthy controls, substantiating that these neural alterations represent the endophenotypic marker of dystonia penetrance, independent of its symptomatology. Additional abnormalities in premotor-parietal-temporal cortical regions, caudate nucleus, and cerebellum were present only in patients but not their unaffected relatives, likely representing a secondary endophenotype of dystonia manifestation. Based on alterations in the parietal cortex and caudate nucleus, the machine learning categorized 28.6% of unaffected relative as patients, indicating their increased lifetime risk for developing clinical manifestation of dystonia. The identified endophenotypic neural markers may be implemented for screening of at-risk individuals for dystonia development, selection of families for genetic studies of novel variants based on their risk for disease penetrance, or stratification of patients who would respond differently to a particular treatment in clinical trials.

Radiology in Neurolaryngology.

The role of imaging in assessment of neurolaryngology will predominantly involve the assessment of pathology along that of laryngeal nerve pathways. The anatomical pathways of the vagus and laryngeal nerves are well described in standard anatomical textbooks and will not be detailed here. Whilst there are 3 principle laryngeal nerves/branches, the recurrent laryngeal nerve will clearly constitute the mainstay of imaging input. This chapter will elaborate on the pathology encountered at the various levels and the imaging characteristics of these disorders. Prior to this, there will be a summary of normal laryngeal imaging appearances to familiarise with the characteristics of radiological anatomy.