A Deep-Learning Approach for Vocal Fold Pose Estimation in Videoendoscopy

Accurate vocal fold (VF) pose estimation is crucial for diagnosing larynx diseases that can eventually lead to VF paralysis. The videoendoscopic examination is used to assess VF motility, usually estimating the change in the anterior glottic angle (AGA). This is a subjective and time-consuming procedure requiring extensive expertise. This research proposes a deep learning framework to estimate VF pose from laryngoscopy frames acquired in the actual clinical practice. The framework performs heatmap regression relying on three anatomically relevant keypoints as a prior for AGA computation, which is estimated from the coordinates of the predicted points. The assessment of the proposed framework is performed using a newly collected dataset of 471 laryngoscopy frames from 124 patients, 28 of whom with cancer. The framework was tested in various configurations and compared with other state-of-the-art approaches (direct keypoints regression and glottal segmentation) for both pose estimation, and AGA evaluation. The proposed framework obtained the lowest root mean square error (RMSE) computed on all the keypoints (5.09, 6.56, and 6.40 pixels, respectively) among all the models tested for VF pose estimation. Also for the AGA evaluation, heatmap regression reached the lowest mean average error (MAE) ( 5 . 87 ∘ ). Results show that relying on keypoints heatmap regression allows to perform VF pose estimation with a small error, overcoming drawbacks of state-of-the-art algorithms, especially in challenging images such as pathologic subjects, presence of noise, and occlusion.

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.

Development and Application of Automated Vocal Fold Tracking Software in a Rat Surgical Model

OBJECTIVE

The rat is a widely used model for studying vocal fold (VF) function after recurrent laryngeal nerve injury, but common techniques for evaluating rat VF motion remain subjective and imprecise. To address this, we developed a software package, called RatVocalTracker1.0 (RVT1.0), to quantify VF motion and tested it on rats with iatrogenic unilateral vocal fold paralysis (VFP).

METHODS

A deep neural network was trained to identify the positions of the VFs and arytenoid cartilages (ACs) in transoral laryngoscope videos of the rat glottis. Software was developed to estimate glottic midline, VF displacement, VF velocity, and AC angle. The software was applied to laryngoscope videos of adult rats before and after right recurrent and superior laryngeal nerve transection (N = 15; 6M, 9F). All software calculated metrics were compared before and after injury and validated against manually calculated metrics.

RESULTS

RVT1.0 accurately tracked and quantified VF displacement, VF velocity, and AC angle. Significant differences were found before and after surgery for all RVT1.0 calculated metrics. There was strong agreement between programmatically and manually calculated measures. Automated analysis was also more efficient than nearly all manual methods.

CONCLUSION

This approach provides fast, accurate assessment of VF motion in rats with minimal labor and allows for quantitative comparison of lateral differences in movement. Through this novel analysis method, we can differentiate healthy movement from unilateral VFP. RVT1.0 is open-source and will be a valuable tool for researchers using the rat model for laryngology research.

LEVEL OF EVIDENCE

NA Laryngoscope, 134:340-346, 2024.

Deep Learning Techniques and Imaging in Otorhinolaryngology-A State-of-the-Art Review

Over the last decades, the field of medicine has witnessed significant progress in artificial intelligence (AI), the Internet of Medical Things (IoMT), and deep learning (DL) systems. Otorhinolaryngology, and imaging in its various subspecialties, has not remained untouched by this transformative trend. As the medical landscape evolves, the integration of these technologies becomes imperative in augmenting patient care, fostering innovation, and actively participating in the ever-evolving synergy between computer vision techniques in otorhinolaryngology and AI. To that end, we conducted a thorough search on MEDLINE for papers published until June 2023, utilizing the keywords 'otorhinolaryngology', 'imaging', 'computer vision', 'artificial intelligence', and 'deep learning', and at the same time conducted manual searching in the references section of the articles included in our manuscript. Our search culminated in the retrieval of 121 related articles, which were subsequently subdivided into the following categories: imaging in head and neck, otology, and rhinology. Our objective is to provide a comprehensive introduction to this burgeoning field, tailored for both experienced specialists and aspiring residents in the domain of deep learning algorithms in imaging techniques in otorhinolaryngology.

A multi-stage transfer learning strategy for diagnosing a class of rare laryngeal movement disorders

BACKGROUND

It remains hard to directly apply deep learning-based methods to assist diagnosing essential tremor of voice (ETV) and abductor and adductor spasmodic dysphonia (ABSD and ADSD). One of the main challenges is that, as a class of rare laryngeal movement disorders (LMDs), there are limited available databases to be investigated. Another worthy explored research question is which above sub-disorder benefits most from diagnosis based on sustained phonations. The question is from the fact that sustained phonations can help detect pathological voice from healthy voice.

METHOD

A transfer learning strategy is developed for LMD diagnosis with limited data, which consists of three fundamental parts. (1) An extra vocally healthy database from the International Dialects of English Archive (IDEA) is employed to pre-train a convolutional autoencoder. (2) The transferred proportion of the pre-trained encoder is explored. And its impact on LMD diagnosis is also evaluated, yielding a two-stage transfer model. (3) A third stage is designed following the initial two stages to embed information of pathological sustained phonation into the model. This stage verifies the different effects of applying sustained phonation on diagnosing the three sub-disorders, and helps boost the final diagnostic performance.

RESULTS

The analysis in this study is based on clinician-labeled LMD data obtained from the Vanderbilt University Medical Center (VUMC). We find that diagnosing ETV shows sensitivity to sustained phonation within the current database. Meanwhile, the results show that the proposed multi-stage transfer learning strategy can produce (1) accuracy of 65.3% on classifying normal and other three sub-disorders all at once, (2) accuracy of 85.3% in differentiating normal, ABSD, and ETV, and (3) accuracy of 77.7% for normal, ADSD and ETV. These findings demonstrate the effectiveness of the proposed approach.

Artificial Intelligence for Upper Aerodigestive Tract Endoscopy and Laryngoscopy: A Guide for Physicians and State-of-the-Art Review

OBJECTIVE

The endoscopic and laryngoscopic examination is paramount for laryngeal, oropharyngeal, nasopharyngeal, nasal, and oral cavity benign lesions and cancer evaluation. Nevertheless, upper aerodigestive tract (UADT) endoscopy is intrinsically operator-dependent and lacks objective quality standards. At present, there has been an increased interest in artificial intelligence (AI) applications in this area to support physicians during the examination, thus enhancing diagnostic performances. The relative novelty of this research field poses a challenge both for the reviewers and readers as clinicians often lack a specific technical background.

DATA SOURCES

Four bibliographic databases were searched: PubMed, EMBASE, Cochrane, and Google Scholar.

REVIEW METHODS

A structured review of the current literature (up to September 2022) was performed. Search terms related to topics of AI, machine learning (ML), and deep learning (DL) in UADT endoscopy and laryngoscopy were identified and queried by 3 independent reviewers. Citations of selected studies were also evaluated to ensure comprehensiveness.

CONCLUSIONS

Forty-one studies were included in the review. AI and computer vision techniques were used to achieve 3 fundamental tasks in this field: classification, detection, and segmentation. All papers were summarized and reviewed.

IMPLICATIONS FOR PRACTICE

This article comprehensively reviews the latest developments in the application of ML and DL in UADT endoscopy and laryngoscopy, as well as their future clinical implications. The technical basis of AI is also explained, providing guidance for nonexpert readers to allow critical appraisal of the evaluation metrics and the most relevant quality requirements.

Diagnosis of vocal cord dysfunction/inducible laryngeal obstruction: An International Delphi Consensus Study

BACKGROUND

Vocal cord dysfunction/inducible laryngeal obstruction (VCD/ILO) is characterized by breathing difficulties in association with excessive supraglottic or glottic laryngeal narrowing. The condition is common and can occur independently; however, it may also be comorbid with other disorders or mimic them. Presentations span multiple specialties and misdiagnosis or delayed diagnosis is commonplace. Group-consensus methods can efficiently generate internationally accepted diagnostic criteria and descriptions to increase clinical recognition, enhance clinical service availability, and catalyze research.

OBJECTIVES

We sought to establish consensus-based diagnostic criteria and methods for VCD/ILO.

METHODS

We performed a modified 2-round Delphi study between December 7, 2021, and March 14, 2022. The study was registered at ANZCTR (Australian New Zealand Clinical Trials Registry; ACTRN12621001520820p). In round 1, experts provided open-ended statements that were categorized, deduplicated, and amended for clarity. These were presented to experts for agreement ranking in round 2, with consensus defined as ≥70% agreement.

RESULTS

Both rounds were completed by 47 international experts. In round 1, 1102 qualitative responses were received. Of the 200 statements presented to experts across 2 rounds, 130 (65%) reached consensus. Results were discussed at 2 international subject-specific conferences in June 2022. Experts agreed on a diagnostic definition for VCD/ILO and endorsed the concept of VCD/ILO phenotypes and clinical descriptions. The panel agreed that laryngoscopy with provocation is the gold standard for diagnosis and that ≥50% laryngeal closure on inspiration or Maat grade ≥2 define abnormal laryngeal closure indicative of VCD/ILO.

CONCLUSIONS

This Delphi study reached consensus on multiple aspects of VCD/ILO diagnosis and can inform clinical practice and facilitate research.

In Vivo Automatic and Quantitative Measurement of Adult Human Larynx and Vocal Fold Images

INTRODUCTION

Qualitative laryngoscopy belongs to a diagnostic routine. Nevertheless, quantitative morphometric measurements of laryngeal structures remain challenging. This study aimed to introduce a special laser projection device that can facilitate computer-assisted digitalized analysis and provide important quantitative information for diagnostics and treatment planning.

MATERIALS AND METHODS

The laryngeal images were captured with our device, which contained two parallel laser beams in order to provide the scaling reference. The maximum length of the vocal fold during respiration and vibration (phonation), vocal width at midpoint, total fold area, maximum cross-sectional area of the glottic space, and maximum vocal fold angle were determined and calculated. These parameters were analyzed and compared on the basis of age, sex, body height, body weight and body mass index.

RESULTS

A total of 87 subjects were enrolled in this study, comprising 39 males and 48 females. The age range for all subjects was 21 to 80 years old. The maximum value of the glottic area and vocal angle showed no significant gender difference. Both the respiration and vibration vocal fold length was significantly longer in males than in females. The vocal width revealed no gender difference, but the fold area during both respiration and phonation was significantly larger in men than in women. As for the respiration-to-vibration ratio of the vocal length, there was a trend, but without statistical significance (P = 0.06), toward a higher length compression ratio in men than in women. Meanwhile, age was found to have a strong relationship with vocal width during phonation. The width of vibration vocal fold decreased with aging significantly.

CONCLUSION

Our innovative module can provide reference parameters, which makes it possible to directly estimate the objective absolute values of relevant laryngeal structures. Our non-invasive approach can be used during routine laryngoscopy and the findings easily documented. In future, we can extend its clinical application to measure subtle laryngeal or hypopharyngeal changes, which are difficult to objectively quantify.

Predictive Outcomes of Deep Learning Measurement of the Anterior Glottic Angle in Bilateral Vocal Fold Immobility

OBJECTIVE

(1) To compare maximum glottic opening angle (anterior glottic angle, AGA) in patients with bilateral vocal fold immobility (BVFI), unilateral vocal fold immobility (UVFI) and normal larynges (NL), and (2) to correlate maximum AGA with patient-reported outcome measures.

METHODS

Patients wisth BVFI, UVFI, and NL were retrospectively studied. An open-source deep learning-based computer vision tool for vocal fold tracking was used to analyze videolaryngoscopy. Minimum and maximum AGA were calculated and correlated with three patient-reported outcomes measures.

RESULTS

Two hundred and fourteen patients were included. Mean maximum AGA was 29.91° (14.40° SD), 42.59° (12.37° SD), and 57.08° (11.14° SD) in BVFI (N = 70), UVFI (N = 70), and NL (N = 72) groups, respectively (p < 0.001). Patients requiring operative airway intervention for BVFI had an average maximum AGA of 24.94° (10.66° SD), statistically different from those not requiring intervention (p = 0.0001). There was moderate negative correlation between Dyspnea Index scores and AGA (Spearman r = -0.345, p = 0.0003). Maximum AGA demonstrated high discriminatory ability for BVFI diagnosis (AUC 0.92, 95% CI 0.81-0.97, p < 0.001) and moderate ability to predict need for operative airway intervention (AUC 0.77, 95% CI 0.64-0.89, p < 0.001).

CONCLUSIONS

A computer vision tool for quantitative assessment of the AGA from videolaryngoscopy demonstrated ability to discriminate between patients with BVFI, UVFI, and normal controls and predict need for operative airway intervention. This tool may be useful for assessment of other neurological laryngeal conditions and may help guide decision-making in laryngeal surgery.

LEVEL OF EVIDENCE

III Laryngoscope, 133:2285-2291, 2023.

Vocal cord dysfunction/inducible laryngeal obstruction-2022 Melbourne Roundtable Report

Vocal cord dysfunction/inducible laryngeal obstruction (VCD/ILO), is a common condition characterized by breathlessness associated with inappropriate laryngeal narrowing. Important questions remain unresolved, and to improve collaboration and harmonization in the field, we convened an international Roundtable conference on VCD/ILO in Melbourne, Australia. The aims were to delineate a consistent approach to VCD/ILO diagnosis, appraise disease pathogenesis, outline current management and model(s) of care and identify key research questions. This report summarizes discussions, frames key questions and details recommendations. Participants discussed clinical, research and conceptual advances in the context of recent evidence. The condition presents in a heterogenous manner, and diagnosis is often delayed. Definitive diagnosis of VCD/ILO conventionally utilizes laryngoscopy demonstrating inspiratory vocal fold narrowing >50%. Computed tomography of the larynx is a new technology with potential for swift diagnosis that requires validation in clinical pathways. Disease pathogenesis and multimorbidity interactions are complex reflecting a multi-factorial, complex condition, with no single overarching disease mechanism. Currently there is no evidence-based standard of care since randomized trials for treatment are non-existent. Recent multidisciplinary models of care need to be clearly articulated and prospectively investigated. Patient impact and healthcare utilization can be formidable but have largely escaped inquiry and patient perspectives have not been explored. Roundtable participants expressed optimism as collective understanding of this complex condition evolves. The Melbourne VCD/ILO Roundtable 2022 identified clear priorities and future directions for this impactful condition.

Vocal cord dysfunction/inducible laryngeal obstruction: novel diagnostics and therapeutics

INTRODUCTION

Vocal cord dysfunction/inducible laryngeal obstruction (VCD/ILO) is an important medical condition but understanding of the condition is imperfect. It occurs in healthy people but often co-exists with asthma. Models of VCD/ILO pathophysiology highlight predisposing factors rather than specific mechanisms and disease expression varies between people, which is seldom appreciated. Diagnosis is often delayed, and the treatment is not evidence based.

AREAS COVERED

A unified pathophysiological model and disease phenotypes have been proposed. Diagnosis is conventionally made by laryngoscopy during inspiration with vocal cord narrowing >50% Recently, dynamic CT larynx was shown to have high specificity (>80%) with potential as a noninvasive, swift, and quantifiable diagnostic modality. Treatment entails laryngeal retraining with speech pathology intervention and experimental therapies such as botulinum toxin injection. Multidisciplinary team (MDT) clinics are a novel innovation with demonstrated benefits including accurate diagnosis, selection of appropriate treatment, and reductions in oral corticosteroid exposure.

EXPERT OPINION

Delayed diagnosis of VCD/ILO is pervasive, often leading to detrimental treatments. Phenotypes require validation and CT larynx can reduce the necessity for laryngoscopy, thereby fast-tracking diagnosis. MDT clinics can optimize management. Randomized controlled trials are essential to validate speech pathology intervention and other treatment modalities and to establish international standards of care.

Re-Training of Convolutional Neural Networks for Glottis Segmentation in Endoscopic High-Speed Videos

Endoscopic high-speed video (HSV) systems for visualization and assessment of vocal fold dynamics in the larynx are diverse and technically advancing. To consider resulting "concepts shifts" for neural network (NN)-based image processing, re-training of already trained and used NNs is necessary to allow for sufficiently accurate image processing for new recording modalities. We propose and discuss several re-training approaches for convolutional neural networks (CNN) being used for HSV image segmentation. Our baseline CNN was trained on the BAGLS data set (58,750 images). The new BAGLS-RT data set consists of additional 21,050 images from previously unused HSV systems, light sources, and different spatial resolutions. Results showed that increasing data diversity by means of preprocessing already improves the segmentation accuracy (mIoU + 6.35%). Subsequent re-training further increases segmentation performance (mIoU + 2.81%). For re-training, finetuning with dynamic knowledge distillation showed the most promising results. Data variety for training and additional re-training is a helpful tool to boost HSV image segmentation quality. However, when performing re-training, the phenomenon of catastrophic forgetting should be kept in mind, i.e., adaption to new data while forgetting already learned knowledge.

LARNet-STC: Spatio-temporal orthogonal region selection network for laryngeal closure detection in endoscopy videos

The vocal folds (VFs) are a pair of muscles in the larynx that play a critical role in breathing, swallowing, and speaking. VF function can be adversely affected by various medical conditions including head or neck injuries, stroke, tumor, and neurological disorders. In this paper, we propose a deep learning system for automated detection of laryngeal adductor reflex (LAR) events in laryngeal endoscopy videos to enable objective, quantitative analysis of VF function. The proposed deep learning system incorporates our novel orthogonal region selection network and temporal context. This network learns to directly map its input to a VF open/close state without first segmenting or tracking the VF region. This one-step approach drastically reduces manual annotation needs from labor-intensive segmentation masks or VF motion tracks to frame-level class labels. The proposed spatio-temporal network with an orthogonal region selection subnetwork allows integration of local image features, global image features, and VF state information in time for robust LAR event detection. The proposed network is evaluated against several network variations that incorporate temporal context and is shown to lead to better performance. The experimental results show promising performance for automated, objective, and quantitative analysis of LAR events from laryngeal endoscopy videos with over 90% and 99% F1 scores for LAR and non-LAR frames respectively.

Exercise-induced laryngeal obstruction (EILO) in athletes: a narrative review by a subgroup of the IOC Consensus on 'acute respiratory illness in the athlete'

Exercise-induced laryngeal obstruction (EILO) is caused by paradoxical inspiratory adduction of laryngeal structures during exercise. EILO is an important cause of upper airway dysfunction in young individuals and athletes, can impair exercise performance and mimic lower airway dysfunction, such as asthma and/or exercise-induced bronchoconstriction. Over the past two decades, there has been considerable progress in the recognition and assessment of EILO in sports medicine. EILO is a highly prevalent cause of unexplained dyspnoea and wheeze in athletes. The preferred diagnostic approach is continuous visualisation of the larynx (via laryngoscopy) during high-intensity exercise. Recent data suggest that EILO consists of different subtypes, possibly caused via different mechanisms. Several therapeutic interventions for EILO are now in widespread use, but to date, no randomised clinical trials have been performed to assess their efficacy or inform robust management strategies. The aim of this review is to provide a state-of-the-art overview of EILO and guidance for clinicians evaluating and treating suspected cases of EILO in athletes. Specifically, this review examines the pathophysiology of EILO, outlines a diagnostic approach and presents current therapeutic algorithms. The key unmet needs and future priorities for research in this area are also covered.

Vocal cord lesions classification based on deep convolutional neural network and transfer learning

PURPOSE

Laryngoscopy, the most common diagnostic method for vocal cord lesions (VCLs), is based mainly on the visual subjective inspection of otolaryngologists. This study aimed to establish a highly objective computer-aided VCLs diagnosis system based on deep convolutional neural network (DCNN) and transfer learning.

METHODS

To classify VCLs, our method combined the DCNN backbone with transfer learning on a system specifically finetuned for a laryngoscopy image dataset. Laryngoscopy image database was collected to train the proposed system. The diagnostic performance was compared with other DCNN-based models. Analysis of F1 score and receiver operating characteristic curves were conducted to evaluate the performance of the system.

RESULTS

Beyond the existing VCLs diagnosis method, the proposed system achieved an overall accuracy of 80.23%, an F1 score of 0.7836, and an area under the curve (AUC) of 0.9557 for four fine-grained classes of VCLs, namely, normal, polyp, keratinization, and carcinoma. It also demonstrated robust classification capacity for detecting urgent (keratinization, carcinoma) and non-urgent (normal, polyp), with an overall accuracy of 0.939, a sensitivity of 0.887, a specificity of 0.993, and an AUC of 0.9828. The proposed method also outperformed clinicians in the classification of normal, polyps, and carcinoma at an extremely low time cost.

CONCLUSION

The VCLs diagnosis system succeeded in using DCNN to distinguish the most common VCLs and normal cases, holding a practical potential for improving the overall diagnostic efficacy in VCLs examinations. The proposed VCLs diagnosis system could be appropriately integrated into the conventional workflow of VCLs laryngoscopy as a highly objective auxiliary method.

High Prevalence of Exercise-induced Laryngeal Obstruction in a Cohort of Elite Cross-country Skiers

INTRODUCTION

Exercise-induced laryngeal obstruction (EILO) is a differential diagnosis for asthma and prevalent in athletes referred for exercise-induced dyspnea. The aim of this study was to estimate the prevalence of EILO in elite cross-country skiers, known for a high prevalence of asthma.

METHOD

Elite cross-country skiers were invited for screening of EILO. Screening consisted of clinical assessment, questionnaires, skin prick test, spirometry, eucapnic voluntary hyperventilation test, and continuous laryngoscopy during exercise test. Current asthma was defined as physician-diagnosed asthma and use of asthma medication during the last 12 months. EILO was defined as ≥2 points at the supraglottic or glottic level during exercise at maximal effort, using a visual grade score system.

RESULT

A total of 89 (51% female) cross-country skiers completed the study. EILO was identified in 27% of the skiers, 83% of whom were female. All skiers with EILO had supraglottic EILO, and there was no glottic EILO. Current asthma was present in 34 (38%) of the skiers, 10 (29%) of whom had concomitant EILO. In the skiers with EILO, a higher proportion reported wheeze or shortness of breath after exercise, compared with skiers without EILO. In skiers with EILO and current asthma, compared with skiers with asthma only, a higher proportion reported wheeze or shortness of breath after exercise. Asthma medication usage did not differ between these groups.

CONCLUSION

EILO is common in elite cross-country skiers, especially females. Asthma and EILO may coexist, and the prevalence of respiratory symptoms is higher in skiers with both. Testing for EILO should be considered in cross-country skiers with respiratory symptoms.

Orthogonal Region Selection Network for Laryngeal Closure Detection in Laryngoscopy Videos

Vocal folds (VFs) play a critical role in breathing, swallowing, and speech production. VF dysfunctions caused by various medical conditions can significantly reduce patients' quality of life and lead to life-threatening conditions such as aspiration pneumonia, caused by food and/or liquid "invasion" into the windpipe. Laryngeal endoscopy is routinely used in clinical practice to inspect the larynx and to assess the VF function. Unfortunately, the resulting videos are only visually inspected, leading to loss of valuable information that can be used for early diagnosis and disease or treatment monitoring. In this paper, we propose a deep learning-based image analysis solution for automated detection of laryngeal adductor reflex (LAR) events in laryngeal endoscopy videos. Laryngeal endoscopy image analysis is a challenging task because of anatomical variations and various imaging problems. Analysis of LAR events is further challenging because of data imbalance since these are rare events. In order to tackle this problem, we propose a deep learning system that consists of a two-stream network with a novel orthogonal region selection subnetwork. To our best knowledge, this is the first deep learning network that learns to directly map its input to a VF open/close state without first segmenting or tracking the VF region, which drastically reduces labor-intensive manual annotation needed for mask or track generation. The proposed two-stream network and the orthogonal region selection subnetwork allow integration of local and global information for improved performance. The experimental results show promising performance for the automated, objective, and quantitative analysis of LAR events from laryngeal endoscopy videos.Clinical relevance- This paper presents an objective, quantitative, and automatic deep learning based system for detection of laryngeal adductor reflex (LAR) events in laryngoscopy videos.

Is the healthy respiratory system built just right, overbuilt, or underbuilt to meet the demands imposed by exercise?

In the healthy, untrained young adult, a case is made for a respiratory system (airways, pulmonary vasculature, lung parenchyma, respiratory muscles, and neural ventilatory control system) that is near ideally designed to ensure a highly efficient, homeostatic response to exercise of varying intensities and durations. Our aim was then to consider circumstances in which the intra/extrathoracic airways, pulmonary vasculature, respiratory muscles, and/or blood-gas distribution are underbuilt or inadequately regulated relative to the demands imposed by the cardiovascular system. In these instances, the respiratory system presents a significant limitation to O₂ transport and contributes to the occurrence of locomotor muscle fatigue, inhibition of central locomotor output, and exercise performance. Most prominent in these examples of an "underbuilt" respiratory system are highly trained endurance athletes, with additional influences of sex, aging, hypoxic environments, and the highly inbred equine. We summarize by evaluating the relative influences of these respiratory system limitations on exercise performance and their impact on pathophysiology and provide recommendations for future investigation.

Two step convolutional neural network for automatic glottis localization and segmentation in stroboscopic videos

Precise analysis of the vocal fold vibratory pattern in a stroboscopic video plays a key role in the evaluation of voice disorders. Automatic glottis segmentation is one of the preliminary steps in such analysis. In this work, it is divided into two subproblems namely, glottis localization and glottis segmentation. A two step convolutional neural network (CNN) approach is proposed for the automatic glottis segmentation. Data augmentation is carried out using two techniques :  1) Blind rotation (WB), 2) Rotation with respect to glottis orientation (WO). The dataset used in this study contains stroboscopic videos of 18 subjects with Sulcus vocalis, in which the glottis region is annotated by three speech language pathologists (SLPs). The proposed two step CNN approach achieves an average localization accuracy of 90.08% and a mean dice score of 0.65.

An Open-Source Computer Vision Tool for Automated Vocal Fold Tracking From Videoendoscopy

OBJECTIVES

Contemporary clinical assessment of vocal fold adduction and abduction is qualitative and subjective. Herein is described a novel computer vision tool for automated quantitative tracking of vocal fold motion from videolaryngoscopy. The potential of this software as a diagnostic aid in unilateral vocal fold paralysis is demonstrated.

STUDY DESIGN

Case-control.

METHODS

A deep-learning algorithm was trained for vocal fold localization from videoendoscopy for automated frame-wise estimation of glottic opening angles. Algorithm accuracy was compared against manual expert markings. Maximum glottic opening angles between adults with normal movements (N = 20) and those with unilateral vocal fold paralysis (N = 20) were characterized.

RESULTS

Algorithm angle estimations demonstrated a correlation coefficient of 0.97 (P < .001) and mean absolute difference of 3.72° (standard deviation [SD], 3.49°) in comparison to manual expert markings. In comparison to those with normal movements, patients with unilateral vocal fold paralysis demonstrated significantly lower maximal glottic opening angles (mean 68.75° ± 11.82° vs. 49.44° ± 10.42°; difference, 19.31°; 95% confidence interval [CI] [12.17°-26.44°]; P < .001). Maximum opening angle less than 58.65° predicted unilateral vocal fold paralysis with a sensitivity of 0.85 and specificity of 0.85, with an area under the receiver operating characteristic curve of 0.888 (95% CI [0.784-0.991]; P < .001).

CONCLUSION

A user-friendly software tool for automated quantification of vocal fold movements from previously recorded videolaryngoscopy examinations is presented, termed automated glottic action tracking by artificial intelligence (AGATI). This tool may prove useful for diagnosis and outcomes tracking of vocal fold movement disorders.

LEVEL OF EVIDENCE

IV Laryngoscope, 131:E219-E225, 2021.

Measuring Vallecular Volume on Flexible Endoscopic Evaluation of Swallowing: A Proof of Concept Study

Currently, no method exists to measure the size of pharyngeal and laryngeal structures on endoscopy. Imaging for dysphagia diagnostic techniques, for the most part, still relies on qualitative assumptions and cursory visual examinations to induce patients' swallowing safety and function. In this proof of concept study, we measured vallecular cavity volume using simultaneous modified barium swallows (MBS) and flexible endoscopic evaluation of swallowing (FEES). Similar to the three-dimensional image compilation fields of facial reconstruction, medical imagery, and forensic science, this proposed methodology combines the two-dimensional images yielded in FEES and MBS videos to calculate estimates of the valleculae in a 3D perspective. A tracking tool was used to measure distances on MBS, while endoscopic specifications were used to find distances on FEES. This combination of ratio measurements allowed for measurement on both the MBS and FEES. In a sample of n = 37 dysphagia patients referred for MBS/FEES studies, the mean distance from the tip of endoscope to the closest point of epiglottis was 25.38 mm, the mean vallecular area outlined on MBS video was 84.72 mm², the mean epiglottal width was 18.16 mm, and the mean vallecular volume was 1.55 mL. Future application could include tracking growth of tumors, glottic opening, volume of residue and tracking of any other important outcome involving movement, size, and targets of interest with higher precision.

Prevalence and impact of comorbid laryngeal dysfunction in asthma: A systematic review and meta-analysis

BACKGROUND

Laryngeal or vocal cord dysfunction has long been regarded as a mimic of asthma; however, recent evidence indicates that it may be a significant comorbid condition in patients with asthma.

OBJECTIVE

We aimed to systematically estimate the prevalence of comorbid laryngeal dysfunction (LD) in adults with asthma and characterize its clinical impact on asthma.

METHODS

Electronic databases were searched for relevant studies published until June 2019. Studies were included if LD was objectively defined by direct visualization of laryngeal movement. Outcomes included the prevalence of LD and its association with clinical asthma indicators, such as severity, control, and quality of life. Random effects meta-analyses were performed to calculate the estimates.

RESULTS

A total of 21 studies involving 1637 patients were identified. Overall, the pooled prevalence of LD in adults with asthma was 25% (95% CI = 15%-37%; I² = 96%). Prevalence estimates differed according to the diagnostic test utilized, with the lowest overall prevalence (4% [95% CI = 0%-10%; I² = 90%]) seen when LD was diagnosed by resting laryngoscopy without external stimuli; however, it was much higher when diagnosed by laryngoscopy studies utilizing an external trigger, such as exercise (38% [95% CI = 24%-53%; I² = 90%]) or in studies using a computed tomography-based diagnostic protocol (36% [95% CI = 24%-49%; I² = 78%]). Only 7 studies reported the associations between LD and clinical asthma indicators; inconsistencies between studies limited meaningful conclusions.

CONCLUSION

LD may be a common comorbidity in asthma, affecting about 25% of adult patients. Further prospective studies are needed to better characterize its clinical impact and the benefits of detecting and managing LD in patients with asthma.

Fully automatic segmentation of glottis and vocal folds in endoscopic laryngeal high-speed videos using a deep Convolutional LSTM Network

The objective investigation of the dynamic properties of vocal fold vibrations demands the recording and further quantitative analysis of laryngeal high-speed video (HSV). Quantification of the vocal fold vibration patterns requires as a first step the segmentation of the glottal area within each video frame from which the vibrating edges of the vocal folds are usually derived. Consequently, the outcome of any further vibration analysis depends on the quality of this initial segmentation process. In this work we propose for the first time a procedure to fully automatically segment not only the time-varying glottal area but also the vocal fold tissue directly from laryngeal high-speed video (HSV) using a deep Convolutional Neural Network (CNN) approach. Eighteen different Convolutional Neural Network (CNN) network configurations were trained and evaluated on totally 13,000 high-speed video (HSV) frames obtained from 56 healthy and 74 pathologic subjects. The segmentation quality of the best performing Convolutional Neural Network (CNN) model, which uses Long Short-Term Memory (LSTM) cells to take also the temporal context into account, was intensely investigated on 15 test video sequences comprising 100 consecutive images each. As performance measures the Dice Coefficient (DC) as well as the precisions of four anatomical landmark positions were used. Over all test data a mean Dice Coefficient (DC) of 0.85 was obtained for the glottis and 0.91 and 0.90 for the right and left vocal fold (VF) respectively. The grand average precision of the identified landmarks amounts 2.2 pixels and is in the same range as comparable manual expert segmentations which can be regarded as Gold Standard. The method proposed here requires no user interaction and overcomes the limitations of current semiautomatic or computational expensive approaches. Thus, it allows also for the analysis of long high-speed video (HSV)-sequences and holds the promise to facilitate the objective analysis of vocal fold vibrations in clinical routine. The here used dataset including the ground truth will be provided freely for all scientific groups to allow a quantitative benchmarking of segmentation approaches in future.

A systematic review of surgical treatment for supraglottic exercise-induced laryngeal obstruction

Objectives

Exercise‐induced laryngeal obstruction (EILO) is a condition causing breathing difficulties and stridor during exercise. The condition has in severe cases been treated surgically with supraglottoplasty. The purpose of this systematic review is to assess the evidence and recommendations for surgical intervention in treating patients with EILO.

Methods

A systematic search was performed in PubMed and Embase to identify relevant studies describing surgical treatment of patients diagnosed with severe EILO. According to eligibility criteria, data were independently extracted by two reviewers. To assess the risk of bias of each included study, the Newcastle‐Ottawa scale (NOS) was used.

Results

The screening process identified 11 observational studies with a total of 75 patients. Findings indicated that many beneficial outcomes are to be found in surgical treatment for EILO. These indications were found both on visual verification of improvement of the laryngeal obstruction during exercise and patient self‐reported symptom severity. The average NOS score (4.3) indicated low level of evidence in the included studies.

Conclusion

Studies reporting effects of surgical treatment of EILO have shown promising results in patients with laryngeal obstruction. However, the heterogeneity of study methodologies and the level of evidence precludes definitive recommendations for or against supraglottoplasty at this time; prospective and methodologically robust studies are now needed.

Level of Evidence

4