Use of deep learning to segment bolus during videofluoroscopic swallow studies.

Anatomical segmentations generated using artificial intelligence (AI) have the potential to significantly improve video fluoroscopic swallow study (VFS) analysis. AI segments allow for various metrics to be determined without additional time constraints streamlining and creating new opportunities for analysis. While the opportunity is vast, it is important to understand the challenges and limitations of the underlying AI task. This work evaluates a bolus segmentation network. The first swallow of thin or liquid bolus from 80 unique patients were manually contoured from bolus first seen in the oral cavity to end of swallow motion. The data was split into a 75/25 training and validation set and a 4-fold cross validation was done. A U-Net architecture along with variations were tested with the dice coefficient as the loss function and overall performance metric. The average validation set resulted in a dice coefficient of 0.67. Additional analysis to characterize the variability of images and performance on sub intervals was conducted indicating high variability among the processes required for training the network. It was found that bolus in the oral cavity consistently degrades performance due to misclassification of teeth and unimportant residue. The dice coefficients dependence on structure size can have substantial effects on the reported value. This work shows the efficacy of bolus segmentation and identifies key areas that are detriments to the performance of the network.

Effects of Device-Facilitated Lingual Strengthening Therapy on Dysphagia Related Outcomes in Patients Post-Stroke: A Randomized Controlled Trial.

BACKGROUND: Swallowing impairments resulting from stroke have few rehabilitative options. Prior evidence suggests lingual strengthening exercise may provide some benefit, but more randomized controlled trials are required. The purpose of this study was to examine efficacy of progressive lingual resistance training on lingual pressure generative capacity and swallowing outcomes for individuals with dysphagia after stroke. METHODS: Participants with dysphagia within 6 months of acute stroke were randomly assigned to: (1) treatment: progressive resistance tongue exercise using pressure sensors for 12 weeks with usual care; or (2) control: usual care only. Outcomes were measured at baseline, 8 and 12 weeks to assess group differences in lingual pressure generation, swallow safety, efficiency, oral intake, and swallowing quality of life. RESULTS: Final sample included 19 participants [treatment (N = 9) and control (N = 10)] with 16 males and 3 females (mean age = 69.33). Functional Oral Intake Scale (FOIS) scores improved significantly (p = 0.04) in the treatment group from baseline to 8 weeks compared to usual care (control). No significant differences between treatment groups were identified for other outcomes; large effect sizes were detected for group differences in lingual pressure generative capacity from baseline to 8 weeks at the anterior sensor (d = .95) and posterior sensor (d = 0.96), and vallecular residue of liquids (baseline to 8-week d = 1.2). CONCLUSIONS: Lingual strengthening exercise resulted in significant improvements in functional oral intake for patients with post-stroke dysphagia as compared to usual care after 8 weeks. Future studies should include a larger sample size and address treatment impact on specific aspects of swallow physiology.

Effects of Food and Liquid Properties on Swallowing Physiology and Function in Adults.

Foods and liquids have properties that are often modified as part of clinical dysphagia management to promote safe and efficient swallowing. However, recent studies have questioned whether this practice is supported by the evidence. To address this, a scoping review was conducted to answer the question: "Can properties of food and liquids modify swallowing physiology and function in adults?" Online search in six databases yielded a set of 4235 non-duplicate articles. Using COVIDENCE software, two independent reviewers screened the articles by title and abstract, and 229 full-text articles were selected for full-text review. One-hundred eleven studies met the inclusion criteria for qualitative synthesis and assessment of risk of bias. Three randomized controlled trials and 108 non-randomized studies were analyzed. Large amounts of variability in instrumental assessment, properties of food and liquids, and swallowing measures were found across studies. Sour, sweet, and salty taste, odor, carbonation, capsaicin, viscosity, hardness, adhesiveness, and cohesiveness were reported to modify the oral and pharyngeal phase of swallowing in both healthy participants and patients with dysphagia. Main swallow measures modified by properties of food and liquids were penetration/aspiration, oral transit time, lingual pressures, submental muscle contraction, oral and pharyngeal residue, hyoid and laryngeal movement, pharyngeal and upper esophageal sphincter pressures, and total swallow duration. The evidence pooled in this review supports the clinical practice of food texture and liquid consistency modification in the management of dysphagia with the caveat that all clinical endeavors must be undertaken with a clear rationale and patient-specific evidence that modifying food or liquid benefits swallow safety and efficiency while maintaining quality of life.

Investigation of Embodied Language Processing on Command-Swallow Performance in Healthy Participants.

Purpose During videofluoroscopic examination of swallowing, patients commonly are instructed to hold a bolus in their mouth until they hear a verbal instruction to swallow, which usually consists of the word swallow and is commonly referred to as the command swallow condition. The language-induced motor facilitation theory suggests that linguistic processes associated with the verbal command to swallow should facilitate the voluntary component of swallowing. As such, the purpose of the study was to examine the linguistic influences of the verbal command on swallowing. Method Twenty healthy young adult participants held a 5-ml liquid bolus in their mouth and swallowed the bolus after hearing one of five acoustic stimuli presented randomly: congruent action word (swallow), incongruent action word (cough), congruent pseudoword (spallow), incongruent pseudoword (pough), and nonverbal stimulus (1000-Hz pure tone). Suprahyoid muscle activity during swallowing was measured via surface electromyography (sEMG). Results The onset and peak sEMG latencies following the congruent action word swallow were shorter than latencies following the pure tone and pseudowords but were not different from the incongruent action word. The lack of difference between swallow and cough did not negate the positive impact of real words on timing. In contrast to expectations, sEMG activity duration and rise time were longer following the word swallow than the pure tone and pseudowords but were not different from cough. No differences were observed for peak suprahyoid muscle activity amplitude and fall times. Conclusions Language facilitation was observed in swallowing. The clinical utility of the information obtained in the study may depend on the purposes for using the command swallow and the type of patient being assessed. However, linguistic processing under the command swallow condition may alter swallow behaviors and suggests that linguistic inducement could be useful as a compensatory technique for patients with difficulty initiating oropharyngeal swallows.

The Prediction of Risk of Penetration-Aspiration Via Hyoid Bone Displacement Features.

Videofluoroscopic swallow studies are widely used in clinical and research settings to assess swallow function and to determine physiological impairments, diet recommendations, and treatment goals for people with dysphagia. Videofluoroscopy can be used to analyze biomechanical events of swallowing, including hyoid bone displacement, to differentiate between normal and disordered swallow functions. Previous research has found significant associations between hyoid bone displacement and penetration/aspiration during swallowing, but the predictive value of hyoid bone displacement during swallowing has not been explored. The primary objective of this study was to build a model based on aspects of hyoid bone displacement during swallowing to predict the extent of airway penetration or aspiration during swallowing. Aspects of hyoid bone displacement from 1433 swallows from patients referred for videofluoroscopy were analyzed to determine which aspects predicted risk of penetration and aspiration according to the Penetration-Aspiration Scale. A generalized estimating equation incorporating components of hyoid bone displacement and variables shown to impact penetration and aspiration (such as age, bolus volume, and viscosity) was used to evaluate penetration and aspiration risk. Results indicated that anterior-horizontal hyoid bone displacement was the only aspect of hyoid bone displacement predictive of penetration and aspiration risk. Further research should focus on improving the model performance by identifying additional physiological swallowing events that predict penetration and aspiration risk. The model built for this study, and future modified models, will be beneficial for clinicians to use in the assessment and treatment of people with dysphagia, and for potentially tracking improvement in hyolaryngeal excursion resulting from dysphagia treatment, thus mitigating adverse outcomes that can occur secondary to dysphagia.

High-Resolution Cervical Auscultation Signal Features Reflect Vertical and Horizontal Displacements of the Hyoid Bone During Swallowing.

Millions of people across the globe suffer from swallowing difficulties, known as dysphagia, which can lead to malnutrition, pneumonia, and even death. Swallowing cervical auscultation, which has been suggested as a noninvasive screening method for dysphagia, has not been associated yet with any physical events. In this paper, we have compared the hyoid bone displacement extracted from the videofluoroscopy images of 31 swallows to the signal features extracted from the cervical auscultation recordings captured with a tri-axial accelerometer and a microphone. First, the vertical displacement of the anterior part of the hyoid bone is related to the entropy rate of the superior-inferior swallowing vibrations and to the kurtosis of the swallowing sounds. Second, the vertical displacement of the posterior part of the hyoid bone is related to the bandwidth of the medial-lateral swallowing vibrations. Third, the horizontal displacements of the posterior and anterior parts of the hyoid bone are related to the spectral centroid of the superior-inferior swallowing vibrations and to the peak frequency of the medial-lateral swallowing vibrations, respectively. At last, the airway protection scores and the command characteristics were associated with the vertical and horizontal displacements, respectively, of the posterior part of the hyoid bone. Additional associations between the patients' characteristics and auscultations' signals were also observed. The hyoid bone maximal displacement is a cause of swallowing vibrations and sounds. High-resolution cervical auscultation may offer a noninvasive alternative for dysphagia screening and additional diagnostic information.

Detection of Swallow Kinematic Events From Acoustic High-Resolution Cervical Auscultation Signals in Patients With Stroke.

OBJECTIVE: To examine whether there were any associations between high-resolution cervical auscultation (HRCA) acoustic signals recorded by a contact microphone and swallowing kinematic events during pharyngeal swallow as assessed by a videofluoroscopic (VF) examination. DESIGN: Prospective pilot study. SETTING: University teaching hospital, university research laboratories. PARTICIPANTS: Patients (N=35) with stroke who have suspected dysphagia (26 men + 9 women; age = 65.8±11.2). METHODS: VF recordings of 100 liquid swallows from 35 stroke patients were analyzed, and a variety of HRCA signal features to characterize each swallow were calculated. MAIN OUTCOME MEASURES: Percent of signal feature maxima (peak) occurring within 0.1 seconds of swallow kinematic event identified from VF recording. RESULTS: Maxima of HRCA signal features, such as standard deviation, skewness, kurtosis, centroid frequency, bandwidth, and wave entropy, were associated with hyoid elevation, laryngeal vestibule closure, and upper esophageal sphincter opening, and the contact of the base of the tongue and posterior pharyngeal wall. CONCLUSIONS: Although the kinematic source of HRCA acoustic signals has yet to be fully elucidated, these results indicate a strong relationship between these HRCA signals and several swallow kinematic events. There is a potential for HRCA to be developed for diagnostic and rehabilitative clinical management of dysphagia.

Dysphagia and its effects on swallowing sounds and vibrations in adults.

BACKGROUND: To utilize cervical auscultation as a means of screening for risk of dysphagia, we must first determine how the signal differs between healthy subjects and subjects with swallowing disorders. METHODS: In this experiment we gathered swallowing sound and vibration data from 53 (13 with stroke, 40 without) patients referred for imaging evaluation of swallowing function with videofluoroscopy. The analysis was limited to non-aspirating swallows of liquid with either thin (< 5 cps) or viscous ([Formula: see text]) consistency. After calculating a selection of generalized time, frequency, and time frequency features for each swallow, we compared our data against our findings in a previous experiment that investigated identical features for a different group of 56 healthy subjects. RESULTS: We found that nearly all of our chosen features for both vibrations and sounds showed significant differences between the healthy and disordered swallows despite the absence of aspiration. We also found only negligible differences between dysphagia as a symptom of stroke and dysphagia as a symptom of another condition. CONCLUSION: Non-aspirating swallows from healthy controls and patients with dysphagia have distinct feature patterns. These findings should greatly help the development of the cervical auscultation field and serve as a reference for future investigations into more specialized characterization methods.

A comparison between swallowing sounds and vibrations in patients with dysphagia.

The cervical auscultation refers to the observation and analysis of sounds or vibrations captured during swallowing using either a stethoscope or acoustic/vibratory detectors. Microphones and accelerometers have recently become two common sensors used in modern cervical auscultation methods. There are open questions about whether swallowing signals recorded by these two sensors provide unique or complementary information about swallowing function; or whether they present interchangeable information. This study aims to compare of swallowing signals recorded by a microphone and a tri-axial accelerometer from 72 patients (mean age 63.94 ± 12.58 years, 42 male, 30 female), who had videofluoroscopic examination. The participants swallowed one or more boluses of thickened liquids of different consistencies, including thin liquids, nectar-thick liquids, and pudding. A comfortable self-selected volume from a cup or a controlled volume by the examiner from a 5 ml spoon was given to the participants. A broad feature set was extracted in time, information-theoretic, and frequency domains from each of 881 swallows presented in this study. The swallowing sounds exhibited significantly higher frequency content and kurtosis values than the swallowing vibrations. In addition, the Lempel-Ziv complexity was lower for swallowing sounds than those for swallowing vibrations. To conclude, information provided by microphones and accelerometers about swallowing function are unique and these two transducers are not interchangeable. Consequently, the selection of transducer would be a vital step in future studies.

Anatomical Directional Dissimilarities in Tri-axial Swallowing Accelerometry Signals.

Swallowing accelerometry is a noninvasive approach currently under consideration as an instrumental screening test for swallowing difficulties, with most current studies focusing on the swallowing vibrations in the anterior-posterior (A-P) and superior-inferior (S-I) directions. However, the displacement of the hyolaryngeal structure during the act of swallowing in patients with dysphagia involves declination of the medial-lateral (M-L), which suggests that the swallowing vibrations in the M-L direction have the ability to reveal additional details about the swallowing function. With this motivation, we performed a broad comparison of the swallowing vibrations in all three anatomical directions. Tri-axial swallowing accelerometry signals were concurrently collected from 72 dysphagic patients undergoing videofluoroscopic evaluation of swallowing (mean age: 63.94 ± 12.58 years period). Participants swallowed one or more thickened liquids with different consistencies including thin-thick liquids, nectar-thick liquids, and pudding-thick liquids with either a comfortable self-selected volume from a cup or a controlled volume by the examiner from a 5-ml spoon. Swallows were grouped based on the viscosity of swallows and the participant's stroke history. Then, a comprehensive set of features was extracted in multiple signal domains from 881 swallows. The results highlighted inter-axis dissimilarities among tri-axial swallowing vibrations including the extent of variability in the amplitude of signals, the degree of predictability of signals, and the extent of disordered behavior of signals in time-frequency domain. First, the upward movement of the hyolaryngeal structure, representing the S-I signals, were actually more variable in amplitude and showed less predictable behavior than the sideways and forward movements, representing the A-P and M-L signals, during swallowing. Second, the S-I signals, which represent the upward movement of the hyolaryngeal structure, behaved more disordered in the time-frequency domain than the sideways movement, M-L signals, in all groups of study except for the pudding swallows in the stroke group. Third, considering the viscosity and the participant's pathology, thin liquid swallows in the nonstroke group presented the most directional differences among all groups of study. In summary, despite some directional dissimilarities, M-L axis accelerometry characteristics are similar to those of the two other axes. This indicates that M-L axis characteristics, which cannot be observed in videofluoroscopic images, can be adequately derived from the A-P and S-I axes.

The effects of compressive sensing on extracted features from tri-axial swallowing accelerometry signals.

Acquiring swallowing accelerometry signals using a comprehensive sensing scheme may be a desirable approach for monitoring swallowing safety for longer periods of time. However, it needs to be insured that signal characteristics can be recovered accurately from compressed samples. In this paper, we considered this issue by examining the effects of the number of acquired compressed samples on the calculated swallowing accelerometry signal features. We used tri-axial swallowing accelerometry signals acquired from seventeen stroke patients (106 swallows in total). From acquired signals, we extracted typically considered signal features from time, frequency and time-frequency domains. Next, we compared these features from the original signals (sampled using traditional sampling schemes) and compressively sampled signals. Our results have shown we can obtain accurate estimates of signal features even by using only a third of original samples.

A statistical analysis of cervical auscultation signals from adults with unsafe airway protection.

BACKGROUND: Aspiration, where food or liquid is allowed to enter the larynx during a swallow, is recognized as the most clinically salient feature of oropharyngeal dysphagia. This event can lead to short-term harm via airway obstruction or more long-term effects such as pneumonia. In order to non-invasively identify this event using high resolution cervical auscultation there is a need to characterize cervical auscultation signals from subjects with dysphagia who aspirate. METHODS: In this study, we collected swallowing sound and vibration data from 76 adults (50 men, 26 women, mean age 62) who underwent a routine videofluoroscopy swallowing examination. The analysis was limited to swallows of liquid with either thin (<5 cps) or viscous (≈300 cps) consistency and was divided into those with deep laryngeal penetration or aspiration (unsafe airway protection), and those with either shallow or no laryngeal penetration (safe airway protection), using a standardized scale. After calculating a selection of time, frequency, and time-frequency features for each swallow, the safe and unsafe categories were compared using Wilcoxon rank-sum statistical tests. RESULTS: Our analysis found that few of our chosen features varied in magnitude between safe and unsafe swallows with thin swallows demonstrating no statistical variation. We also supported our past findings with regard to the effects of sex and the presence or absence of stroke on cervical ausculation signals, but noticed certain discrepancies with regards to bolus viscosity. CONCLUSIONS: Overall, our results support the necessity of using multiple statistical features concurrently to identify laryngeal penetration of swallowed boluses in future work with high resolution cervical auscultation.

A comparative analysis of DBSCAN, K-means, and quadratic variation algorithms for automatic identification of swallows from swallowing accelerometry signals.

BACKGROUND: Cervical auscultation with high resolution sensors is currently under consideration as a method of automatically screening for specific swallowing abnormalities. To be clinically useful without human involvement, any devices based on cervical auscultation should be able to detect specified swallowing events in an automatic manner. METHODS: In this paper, we comparatively analyze the density-based spatial clustering of applications with noise algorithm (DBSCAN), a k-means based algorithm, and an algorithm based on quadratic variation as methods of differentiating periods of swallowing activity from periods of time without swallows. These algorithms utilized swallowing vibration data exclusively and compared the results to a gold standard measure of swallowing duration. Data was collected from 23 subjects that were actively suffering from swallowing difficulties. RESULTS: Comparing the performance of the DBSCAN algorithm with a proven segmentation algorithm that utilizes k-means clustering demonstrated that the DBSCAN algorithm had a higher sensitivity and correctly segmented more swallows. Comparing its performance with a threshold-based algorithm that utilized the quadratic variation of the signal showed that the DBSCAN algorithm offered no direct increase in performance. However, it offered several other benefits including a faster run time and more consistent performance between patients. All algorithms showed noticeable differentiation from the endpoints provided by a videofluoroscopy examination as well as reduced sensitivity. CONCLUSIONS: In summary, we showed that the DBSCAN algorithm is a viable method for detecting the occurrence of a swallowing event using cervical auscultation signals, but significant work must be done to improve its performance before it can be implemented in an unsupervised manner.

Understanding differences between healthy swallows and penetration-aspiration swallows via compressive sensing of tri-axial swallowing accelerometry signals.

Swallowing accelerometry is a promising tool for non-invasive assessment of swallowing difficulties. A recent contribution showed that swallowing accelerometry signals for healthy swallows and swallows indicating laryngeal penetration or tracheal aspiration have different time-frequency structures, which may be problematic for compressive sensing schemes based on time-frequency dictionaries. In this paper, we examined the effects of different swallows on the accuracy of a compressive sensing scheme based on modulated discrete prolate spheroidal sequences. We utilized tri-axial swallowing accelerometry signals recorded from four patients during routinely schedule videofluoroscopy exams. In particular, we considered 77 swallows approximately equally distributed between healthy swallows and swallows presenting with some penetration/aspiration. Our results indicated that the swallow type does not affect the accuracy of a considered compressive sensing scheme. Also, the results confirmed previous findings that each individual axis contributes different information. Our findings are important for further developments of a device which is to be used for long-term monitoring of swallowing difficulties.

Gender effects on airway closure in head and neck cancer patients.

Age, gender, and bolus effects on the duration of laryngeal closure, the onset of laryngeal closure in relation to the first cricopharyngeal opening, and the duration of cricopharyngeal opening in head and neck cancer patients have not been well documented. Thirty-three head and neck cancer patients (middle-aged women and men, and older women and men) were evaluated with videofluoroscopy before and 3 months after their cancer treatment. At 3 months post-treatment, the mean duration of laryngeal closure was longer for women than for men at 1-, 5-, and 10-ml bolus volumes. The duration of laryngeal closure at 3 months post-treatment and the duration of cricopharyngeal opening at both pretreatment and 3 months post-treatment increased as liquid bolus volume increased. Gender effects were observed in the duration of laryngeal closure during swallow. Bolus effects were observed in the duration of laryngeal closure and cricopharyngeal opening.

Gender effects on airway closure in normal subjects.

The present study was designed to examine age and gender differences with respect to the duration of laryngeal closure, the onset of laryngeal closure in relation to the first cricopharyngeal opening, and the duration of cricopharyngeal opening for six different groups: normal younger men and women (22-29 years), normal middle-aged men and women (45-53 years), and normal older men and women (81-94 years) (10 subjects in each group for a total of 60 subjects). Data were collected by means of videofluoroscopic studies. During swallows of liquid barium, results indicated that normal older subjects had longer cricopharyngeal opening than younger subjects (P = 0.044). Results also revealed that the mean duration of laryngeal closure was significantly longer in women than in men (P = 0.013). The onset of laryngeal closure was significantly earlier in women than in men (P = 0.006). Also, bolus volume effects were observed for both the duration of laryngeal closure (P < 0.0001) and cricopharyngeal opening (P < 0.0001). During liquid barium swallows there was a linear increase in both the duration of laryngeal closure and cricopharyngeal opening.