Search Results (1,178)

Objective: To develop and evaluate artificial intelligence (AI)-based models for detecting laryngeal cancer using laryngoscope images. Methods: Two deep learning models were designed. The first identified and selected vocal cord images from laryngoscope datasets; the second localized laryngeal cancer within the selected images. Both employed FCN–ResNet101. Datasets were annotated by otolaryngologists, preprocessed (cropping, normalization), and augmented (horizontal/vertical flip, grid distortion, color jitter). Performance was assessed using Intersection over Union (IoU), Dice score, accuracy, precision, recall, F1 score, and per-image inference time. Results: The vocal cord selection model achieved a mean IoU of 0.6534 and mean Dice score of 0.7692, with image-level accuracy of 0.9972. The laryngeal cancer model achieved a mean IoU of 0.6469 and mean Dice score of 0.7515, with accuracy of 0.9860. Real-time inference was observed (0.0244–0.0284 s/image). Conclusions: By integrating a vocal cord selection model with a lesion detection model, the proposed platform enables accurate and fast detection of laryngeal cancer from laryngoscope images under the current experimental setting. Full article

Background: Tracheobronchopathia osteochondroplastica (TO) is a rare benign disorder characterized by submucosal cartilaginous and osseous nodules of the tracheobronchial tree, typically sparing the posterior membranous wall. Involvement of the vocal cords is exceedingly rare and may result in critical airway obstruction. The underlying genetic and molecular mechanisms of TO remain largely unexplored. Case presentation: We report a rare case of TO extending from the vocal cords to the bronchi in a 76-year-old man who initially presented with pneumonia and later developed acute respiratory failure due to severe airway narrowing, necessitating emergency tracheostomy. Bronchoscopy and computed tomography revealed diffuse calcified nodules involving the anterior and lateral airway walls, including the subglottic region. Histopathology demonstrated chronic inflammatory cell infiltration with squamous metaplasia. To explore the molecular basis of this condition, whole-genome sequencing (WGS) was performed using peripheral blood samples—the first such application in TO. WGS identified 766 germline mutations (including 27 high-impact variants) and 66 structural variations. Candidate genes were implicated in coagulation and inflammation (KNG1), arachidonic acid metabolism and extracellular matrix remodeling (PLA2G4D), ciliary dysfunction and mineralization (TMEM67), vascular calcification (CDKN2B-AS1), smooth muscle function (MYLK4), abnormal calcification (TRPV2, SPRY2, BAZ1B), fibrotic signaling (AHNAK2), and mucosal barrier integrity (MUC12/MUC19). Notably, despite systemic germline mutations, calcification was restricted to the airway. Conclusions: This case highlights that TO with vocal cord involvement can progress beyond a benign course to cause life-threatening airway obstruction. Integrating clinical, histological, and genomic findings, we propose a novel pathophysiological model in which systemic genetic susceptibility interacts with local immune cell infiltration and fibroblast-driven extracellular matrix remodeling, resulting in airway-restricted dystrophic calcification. This first genomic characterization of TO provides new insights into its pathogenesis and suggests that multi-omics approaches may enable future precision medicine strategies for this rare airway disease. Full article

Background/Objectives: Arterial stiffness is an independent cardiovascular risk factor, and arterial velocity pulse index (AVI) and arterial pressure–volume index (API) are practical oscillometric markers. Shigin, a traditional Japanese vocal recitation practice characterised by abdominal breathing, has limited physiological evidence. This cross-sectional exploratory study examined the association between long-term shigin practice and arterial stiffness in older adults. Methods: Community-dwelling adults aged ≥60 years were classified into shigin practitioners (≥10 years), physically active non-practitioners, and inactive non-practitioners. AVI and API were measured using an upper-arm oscillometric device. Blood pressure, heart rate, salivary α-amylase (morning, standardised conditions), and peak expiratory flow were assessed. Results: Both shigin practitioners and active non-practitioners showed lower AVI and API, lower blood pressure, higher peak expiratory flow, and lower salivary α-amylase than inactive non-practitioners (p < 0.01). These associations remained significant after adjustment for blood pressure, heart rate, and sex. Conclusions: Long-term shigin practice was associated with arterial stiffness indices comparable to those of physically active older adults, without implying causality. Full article

Introduction. Patent ductus arteriosus (PDA) is the most common cardiac anomaly in preterm newborns and may aggravate respiratory disease. Invasive closure options after failure of medical treatment include surgical ligation (SL) and transcatheter closure (TCC). Reports on side effects of intravenous contrast media are scarce. Methods. In this retrospective single-center study, we compared 35 preterm infants below 1500 g birth weight undergoing SL with 35 matched infants undergoing TCC. Outcomes were procedural success, complications and postprocedural ventilation. Results. Closure success was high in both groups (97% SL vs. 86% TCC, p = 0.106). One SL patient underwent re-operation after accidental clipping of the left pulmonary artery, and eight patients (24%) had endoscopy-diagnosed vocal cord palsy after SL. Six TCC patients had complications that required further action, including device embolization, device failure and one case of late device migration that resulted in aortic arch obstruction requiring intervention, and 4 TCC patients developed necrotizing enterocolitis (NEC)-like disease within 24 h, requiring surgery in one patient. SL was associated with longer duration of mechanical ventilation (24 h vs. 144 h, p < 0.001), as opposed to TCC, and higher rates of bronchopulmonary dysplasia (86% vs. 53%, p = 0.004). Discussion. Both techniques achieve high success but differ in complication profiles. TCC may reduce respiratory morbidity. NEC-like disease (probably linked to intravenous administration of contrast agents) warrants further investigation. Full article

Background/Objectives: Speech and motor control share overlapping neural mechanisms, yet their quantitative relationships in Parkinson’s disease (PD) remain underexplored. This study investigated bidirectional associations between acoustic voice features and objective motor metrics to better understand how vocal and motor systems relate in PD. Methods: Cross-sectional baseline data from participants in a randomized neuromodulation trial were analyzed (n = 13). Motor performance was captured using an Integrated Motion Analysis Suite (IMAS), which enabled quantitative, objective characterization of motor performance during balance, gait, and upper- and lower-limb tasks. Acoustic analyses included harmonic-to-noise ratio (HNR), smoothed cepstral peak prominence (CPPS), jitter, shimmer, median fundamental frequency (F0), F0 standard deviation (SD F0), and voice intensity. Univariate linear regressions were conducted in both directions (voice ↔ motor), as well as partial correlations controlling for PD motor symptom severity. Results: When modeling voice outcomes, faster motor performance and shorter movement durations were associated with acoustically clearer voice features (e.g., higher elbow flexion-extension peak speed with higher voice HNR, β = 8.5, R² = 0.56, p = 0.01). Similarly, when modeling motor outcomes, clearer voice measures were linked with faster movement speed and shorter movement durations (e.g., higher voice HNR with higher peak movement speed in elbow flexion/extension, β = 0.07, R² = 0.56, p = 0.01). Conclusions: Voice and motor measures in PD showed significant bidirectional associations, suggesting shared sensorimotor control. These exploratory findings, while limited by sample size, support the feasibility of integrated multimodal assessment for future longitudinal studies. Full article

Acoustic voice analysis demonstrates potential as a non-invasive biomarker for depression, yet its generalizability across languages remains underexplored. This cross-sectional study aimed to identify a set of cross-culturally consistent acoustic features for depression screening using distinct Vietnamese and Japanese voice datasets. We analyzed anonymized recordings from 251 participants, comprising 123 Vietnamese individuals assessed via the self-report Beck Depression Inventory (BDI) and 128 Japanese individuals assessed via the clinician-rated Hamilton Depression Rating Scale (HAM-D). From 6373 features extracted with openSMILE, a multi-stage selection pipeline identified 12 cross-cultural features, primarily from the auditory spectrum (AudSpec), Mel-Frequency Cepstral Coefficients (MFCCs), and logarithmic Harmonics-to-Noise Ratio (logHNR) domains. The cross-cultural model achieved a combined Area Under the Curve (AUC) of 0.934, with performance disparities observed between the Japanese (AUC = 0.993) and Vietnamese (AUC = 0.913) cohorts. This disparity may be attributed to dataset heterogeneity, including mismatched diagnostic tools and differing sample compositions (clinical vs. mixed community). Furthermore, the limited number of high-risk cases (n = 33) warrants cautious interpretation regarding the reliability of reported AUC values for severe depression classification. These findings suggest the presence of a core acoustic signature related to physiological psychomotor changes that may transcend linguistic boundaries. This study advances the exploration of global vocal biomarkers but underscores the need for prospective, standardized multilingual trials to overcome the limitations of secondary data analysis. Full article

Tourette syndrome (TS), or Tourette’s, is a tic disorder (TD) belonging to a group of neuropsychiatric conditions marked by recurrent motor movements or vocalizations known as tics. TD, including TS, typically begins in childhood between 4 and 18 years of age and affects approximately 3% of children and adolescents. The etiology and pathogenesis of TD are multifactorial, involving genetic, immunologic, psychological, and environmental factors. Evidence suggests that neurotransmitter dysregulation, particularly within the cortical dopaminergic networks of the basal ganglia and limbic system, which support motor control and cognition, may be involved in the development of TD. Nutritional factors may modulate TD through various mechanisms, including effects on neurotransmitter synthesis and metabolism, neurodevelopment, neural architecture, and neuroimmune activity. This review integrates current evidence on the roles of vitamins D, B6, and A, as well as iron, magnesium, zinc, and copper, in TD. For each micronutrient, its physiological and neurobiological functions are discussed, along with possible mechanistic links to TD pathophysiology. Additionally, we summarize the impact of nutrient deficiencies and assess available evidence regarding their potential therapeutic potential role in TD management. Overall, this synthesis highlights how nutritional status may influence TD onset and symptom severity, suggesting that nutrient-based interventions could potentially serve as valuable adjunctive strategies in treatment. Full article

Background: Videofluoroscopic swallow study (VFSS) is a key examination for assessing swallowing function. Although several artificial intelligence (AI) models for VFSS interpretation have shown high predictive accuracy through internal validations, AI models that have undergone external validation are rare. This study aims to develop an AI model that automatically diagnoses aspiration and penetration from VFSS videos and to evaluate the model’s performance through multicenter external validation. Methods: Among the 2343 VFSS videos collected, 309 cases of Q1-grade videos, which were free of artifacts and clearly showed the airway and vocal cords, were included in the internal validation dataset. The training, internal validation, and test datasets were divided in a 7:1:2 ratio, with 2012 images (aspiration = 532, penetration = 932, no airway invasion = 548) used for training. The AI model was developed and trained using You Only Look Once version 9, model c (YOLOv9_c). External validation of the AI model was conducted using 138 Q1 and Q2-grade VFSS videos from two different hospitals. Results: According to the internal validation, the YOLOv9_c model showed a training accuracy of 98.1%, a validation accuracy of 97.8%, and a test accuracy of 61.5%. From the confusion matrix analysis, the AI model’s diagnostic accuracy for aspiration in VFSS videos was 0.76 (AUC = 0.70), and for penetration, the diagnostic accuracy was 0.66 (AUC = 0.65). According to the external validation, the AI model demonstrated good performance in diagnosing aspiration (precision: 90.2%, AUC = 0.79) and penetration (precision: 78.3%, AUC = 0.80). The overall diagnostic accuracy of external validation for VFSS videos was 80.4%. Conclusions: We developed an AI model that automatically diagnoses aspiration and penetration when an entire VFSS video is input, and external validation showed good accuracy. In the future, to improve the performance of this AI model and facilitate its clinical application, research using training and validation with VFSS video data from more hospitals is needed. Full article

Speech is one of the earliest-affected modalities in Parkinson’s disease (PD). For more reliable PD evaluation, speech-based telediagnosis studies often use multiple samples from the same subject to capture variability in speech recordings. However, many existing studies split samples—rather than subjects—between training and testing, creating a biased experimental setup that allows data (samples) from the same subject to appear in both sets. This raises concerns for reliable PD evaluation due to data leakage, which results in over-optimistic performance (often close to 100%). In addition, detecting subtle vocal impairments from speech recordings using multiple feature extraction techniques often increases data dimensionality, although only some features are discriminative while others are redundant or non-informative. To address this and build a reliable speech-based PD telediagnosis system, the key contributions of this work are two-fold: (1) a uniform (fair) experimental setup employing subject-wise symmetric (stratified) splitting in 5-fold cross-validation to ensure better generalization in PD prediction, and (2) a novel hybrid data complexity-aware (HDC) feature selection method that improves class separability. This work further contributes to the research community by releasing a publicly accessible five-fold benchmark version of the Parkinson’s speech dataset for consistent and reproducible evaluation. The proposed HDC method analyzes multiple aspects of class separability to select discriminative features, resulting in reduced data complexity in the feature space. In particular, it uses data complexity measures (F4, F1, F3) to assess minimal feature overlap and ReliefF to evaluate the separation of borderline points. Experimental results show that the top-50 discriminative features selected by the proposed HDC outperform existing feature selection algorithms on five out of six classifiers, achieving the highest performance with 0.86 accuracy, 0.70 G-mean, 0.91 F1-score, and 0.58 MCC using an SVM (RBF) classifier. Full article

Cough sounds are a key acoustic indicator for detecting respiratory diseases in laying hens, which have become increasingly prevalent with the intensification of poultry housing systems. As an important early signal, cough sounds play a vital role in disease prevention and precision health management through timely recognition and spatial localization. In this study, an improved BiLSTM–TDOA method was proposed for the accurate recognition and localization of laying hen cough sounds. Nighttime audio data were collected and preprocessed to extract 81 acoustic features, including formant parameters, MFCC, LPCC, and their first and second derivatives. These features were then input into a BiLSTM-Attention model, which achieved a precision of 97.50%, a recall of 90.70%, and an F1-score of 0.9398. An improved TDOA algorithm was then applied for three-dimensional sound source localization, which resulted in mean absolute errors of 0.1453 m, 0.1952 m, and 0.1975 m along the X, Y, and Z axes across 31 positions. The results demonstrated that the proposed method enabled accurate recognition and 3D localization of abnormal vocalizations in laying hens, which will provide a novel approach for early detection, precise control, and intelligent health monitoring of respiratory diseases in poultry houses. Full article

Thyroid cancer survivors often experience worse quality of life than other cancer survivors, with fatigue and sleep disturbance being common contributors. In this prospective cohort from the ICaRe2 cancer registry, survivors completed the Brief Fatigue Inventory (BFI) and Pittsburgh Sleep Quality Index (PSQI) at enrollment and follow-up, with univariate and multivariable analyses identifying factors associated with fatigue and sleep quality. Among 249 survivors (83% female, median age 42), 205 completed the BFI and 224 the PSQI. Most were low (57%) or intermediate (34%) risk or recurrence at diagnosis, and 74% had no structural recurrence. Poor sleep and greater fatigue were significantly associated with female sex (p = 0.0003 and 0.001), younger age at diagnosis (p = 0.02 and 0.0006), and vocal cord paralysis (p = 0.01 and 0.046). Fatigue was also higher in those with hypoparathyroidism (p = 0.04). No associations were found with recurrence risk, therapy response, thyroid hormone type, or TSH levels. Younger female survivors, particularly those with vocal cord paralysis or hypoparathyroidism, are more prone to fatigue and poor sleep, highlighting potential targets for interventions to improve quality of life. Full article

Red deer (Cervus elaphus), as a highly vocal species, provide versatile ecosystem functions beyond grazing. Their flexible use of different habitats allows them to occupy a variety of ecosystems. As global efforts to conserve biodiversity increase, there is a growing need for new approaches to continuous wildlife monitoring. Bioacoustics is a rapidly developing field that provides valuable data, especially in environments that are difficult to access. The spatial occupancy of red deer in Kopački Rit Nature Park was investigated using passive acoustic devices during the rutting season (September–October) in 2023 and 2024. A total of 332,302 recordings were collected with AudioMoth devices configured to record for 1 min every 5 min over a 10-day period. A recognition model was trained on the Arbimon platform, and a random forest model was applied to the detection data. The occupancy model revealed differences in spatial occupancy between the two years. Although none of the tested covariates showed statistically significant effects, the observed differences likely reflect unmeasured ecological dynamics, such as hydrological variability and resource availability. These findings highlight the potential of passive acoustic monitoring as a reliable, non-invasive approach for large mammal studies. Full article

This study examines the impact of vocal fold (VF) lesions located on the superior surface on glottal airflow dynamics and tissue oscillatory behaviors using biomechanical simulations of a two-layered realistic VF model. It is hypothesized that morphological changes in the VFs due to the presence of a lesion cause changes in tissue elasticity and rheological properties, contributing to dysphonia. Previous research has lacked the integration of lesions in computational simulations of anatomically accurate larynx-VF models to explore their effects on phonation and contribution to voice disorders. Addressing the current gap in literature, this paper considers a computational model of a two-layered VF structure incorporating a lesion that represents a hemorrhagic polyp. A three-dimensional, subject-specific, multilayered geometry of VFs is constructed based on STL files derived from a human larynx CT scan, and a fluid–structure interaction (FSI) methodology is employed to simulate the coupling of glottal airflow and VF tissue dynamics. To evaluate the effects of the lesion’s presence, two FSI models, one with a lesion embedded in the cover layer and one without, are simulated and compared. Analysis of airflow dynamics and tissue vibrational patterns between these two models is used to determine the impact of the lesion on the biomechanical characteristics of phonation. The polyp is found to slightly increase airflow resistance through the glottis and disrupt vibratory symmetry by decreasing the vibration frequency of the affected fold, leading to weaker and less rhythmic oscillations. The results also indicate that the lesion increases tissue stress in the affected fold, which agrees with clinical observations. While quantitative ranges depend on lesion size and tissue properties, these consistent and physically meaningful trends highlight the biomechanical mechanisms by which lesions influence phonation. Full article

Understanding music styles is essential for music information retrieval, personalized recommendation, and AI-assisted content creation. However, existing work typically addresses tasks such as emotion classification and singing style classification independently, thereby neglecting the intrinsic relationships between them. In this study, we introduce a multi-task learning framework that jointly models these two tasks to enable explicit knowledge sharing and mutual enhancement. Our results indicate that joint optimization consistently outperforms single-task counterparts, demonstrating the value of leveraging inter-task correlations for more robust singing style analysis. To assess the generality and adaptability of the proposed framework, we evaluate it across various backbone architectures, including Transformer, TextCNN, and BERT, and observe stable performance improvements in all cases. Experiments on a benchmark dataset, which were self-constructed and collected through professional recording devices, further show that the framework not only achieves the best accuracy on both tasks on our dataset under a singer-wise split, but also yields interpretable insights into the interplay between emotional expression and stylistic characteristics in vocal performance. Full article

Background: Emotional prosody refers to the variations in pitch, pause, melody, rhythm, and stress of pronunciation conveying emotional meaning during speech. Although several studies demonstrated that the cerebellum is involved in the network subserving recognition of emotional facial expressions, there is only preliminary evidence suggesting its possible contribution to recognising emotional prosody by modulating the activity of cerebello-prefrontal circuits. The present study aims to further explore the role of the left and right cerebellum in the recognition of emotional prosody in a sample of healthy individuals who were required to identify emotions (happiness, anger, sadness, surprise, disgust, and neutral) from vocal stimuli selected from a validated database (EMOVO corpus). Methods: Anodal transcranial Direct Current Stimulation (tDCS) was used in offline mode to modulate cerebellar activity before the emotional prosody recognition task, and functional near-infrared spectroscopy (fNIRS) was used to monitor stimulation-related changes in oxy- and deoxy- haemoglobin (O2HB and HHB) in prefrontal areas (PFC). Results: Right cerebellar stimulation reduced reaction times in the recognition of all emotions (except neutral and disgust) as compared to both the sham and left cerebellar stimulation, while accuracy was not affected by the stimulation. Haemodynamic data revealed that right cerebellar stimulation reduced O2HB and increased HHB in the PFC bilaterally relative to the other stimulation conditions. Conclusions: These findings are consistent with the involvement of the right cerebellum in modulating emotional processing and in regulating cerebello-prefrontal circuits. Full article