[Accuracy of multi-task network based on vision Transformer in the three-dimensional upper airway analysis].

Objective: To explore the accuracy of a multi-task model based on vision Transformer for analyzing the three-dimensional (3D) upper airway and its subregions, and to evaluate its clinical applicability. Methods: According to the inclusion and exclusion criteria, cone-beam CT (CBCT) data of 10 patients [4 males and 6 females, (20.8±2.7) years] who had their first visit to the Department of Orthodontics in the Hospital of Stomatology, Wuhan University from January 2012 to January 2020 were retrospectively selected. The 3D slicer software was used to segment the upper airway and pharyngeal airway and measure their volumes as the gold standard. The Dolphin 3D software was used to segment the pharyngeal airway and its subregions and measure their volumes as the gold standard. A multi-task model based on vision Transformer developed by the research team for automatic segmentation and volume measurement of the upper airway and its subregions. All the measurements were conducted by the same attending physician. The Bland-Altman analysis and intraclass correlation coefficient (ICC) were used to evaluate the consistency between the multi-task network and the gold standard in the upper airway segmentation and volume measurements, and the paired t test was used to compare the differences between the multi-tasking model and the gold standard. Results: The mean volume deviation of the upper airway segmented by multi-task model and 3D Slicer was -979.6 mm3, and the ICC was 0.97. The mean volume deviation of the pharyngeal airway, nasopharynx, velopharynx, glossopharynx and hypopharynx segmented by multi-task network and Dolphin 3D were 2 069.5, -950.1, -823.6, -813.9 and 4 003.4 mm3, respectively. In addition, ICC in pharyngeal airway, nasopharynx, velopharynx, glossopharynx and hypopharynx were 0.97, 0.94, 0.96, 0.96 and 0.69, respectively. Conclusions: The multi-task model based on vision Transformer produced different errors in the segmentation of 3D upper airway and its subregions. The segmentation of the nasopharynx, velopharynx and glossopharynx was in good agreement with the gold standard, while the segmentation of hypopharynx was poor, suggesting that the robustness and generalization of this model should be further enhanced.

Reasonable Risk Ratio of Palate Surgery: A New Critical Analysis.

OBJECTIVE.: A new critical complication risk analysis, the reasonable risk ratio (RRR or R3) for palate surgeries in obstructive sleep apnea patients. METHODS.: Analysis from published meta-analyses, systematic reviews on success rates, and complications encountered for 3 palate surgeries, expansion sphincter pharyngoplasty (ESP), barbed repositioning pharyngoplasty (BRP) and modified uvulopalatopharyngoplasty (mUPPP), over 20 years. The RRR is derived from a ratio of the percentage of each respective complication over the success rate of that particular surgical procedure. The benchmark RRR of tonsillectomy is set at 0.035 to 0.078. An RRR below this benchmark value is more favorable as tonsillectomy is a widely accepted ENT procedure with risks to benefit well accepted. RESULTS.: The RRR for foreign body (FB) sensation (BRP) ranged from 0.03 to 0.23 (mean RRR of 0.14), FB sensation (ESP) 0.01, FB sensation (mUPPP) ranged from 0.33 to 0.55 (mean RRR of 0.44). The RRR for swallowing difficulties (BRP) ranged from 0.04 to 0.23 (mean RRR of 0.11), mUPPP, was 0.37; no reported swallowing difficulties with the ESP. The RRR for velopharyngeal insufficiency (VPI) (BRP) ranged from 0.009 to 0.18 (mean RRR of 0.07), and RRR VPI (mUPPP) was 0.14. The RRR (BRP) for dry throat was 0.06 and the mUPPP was 0.35, with no reported VPI or dry throat for ESP. The overall RRR for the BRP was 0.09, ESP was 0.01 and mUPPP was 0.29. CONCLUSION.: RRR provides a summarized data-driven, statistical guide to aid decision-making, and helps in patient counseling. BRP and ESP have been shown to have less complications compared to mUPPP.Level of evidence: IV.

Correlation between oral cavity volume and upper airway changes in skeletal Class III patients undergoing bimaxillary orthognathic surgery: a pilot cone-beam computed tomography study.

OBJECTIVES: To evaluate changes of the upper airway and oral cavity volumes in patients with skeletal Class III malocclusion undergoing bimaxillary orthognathic surgery, and to analyze the correlation between postoperative upper airway decrease and the amount of jaw movement and oral cavity volume reduction. MATERIALS AND METHODS: Thirty patients (16 males and 14 females) undergoing bimaxillary surgery were included. Three-dimensional reconstruction of the upper airway and oral cavity were performed using preoperative (T0) and postoperative (T1) (6 months) cone-beam computed tomography scans. RESULTS: The volume, sagittal area and minimum cross-sectional area of the upper airway were diminished (P < .001). The decrease in volume and minimum cross-sectional area in the oropharyngeal region of the upper airway were weakly correlated with B-point posterior movement (P < .05). Total oral cavity volume was decreased, with maxillary oral volume increasing and mandibular oral volume decreasing (P < .001). Upper airway decrease was highly correlated with total oral volume reduction and mandibular oral volume reduction, with the most significant correlation being with total oral volume reduction (P < .001). CONCLUSIONS: Class III bimaxillary surgery reduced the volume, sagittal area, and minimum cross-sectional area of the upper airway as well as oral cavity volume. Upper airway changes were weakly correlated with anterior-posterior mandibular movement but significantly correlated with oral cavity volume changes. Thus, oral cavity volume reduction is a crucial factor of upper airway decrease in patients with skeletal Class III malocclusion undergoing bimaxillary orthognathic surgery.

Identifying sex from pharyngeal images using deep learning algorithm.

The pharynx is one of the few areas in the body where blood vessels and immune tissues can readily be observed from outside the body non-invasively. Although prior studies have found that sex could be identified from retinal images using artificial intelligence, it remains unknown as to whether individuals' sex could also be identified using pharyngeal images. Demographic information and pharyngeal images were collected from patients who visited 64 primary care clinics in Japan for influenza-like symptoms. We trained a deep learning-based classification model to predict reported sex, which incorporated a multiple instance convolutional neural network, on 20,319 images from 51 clinics. Validation was performed using 4869 images from the remaining 13 clinics not used for the training. The performance of the classification model was assessed using the area under the receiver operating characteristic curve. To interpret the model, we proposed a framework that combines a saliency map and organ segmentation map to quantitatively evaluate salient regions. The model achieved the area under the receiver operating characteristic curve of 0.883 (95% CI 0.866-0.900). In subgroup analyses, a substantial improvement in classification performance was observed for individuals aged 20 and older, indicating that sex-specific patterns between women and men may manifest as humans age (e.g., may manifest after puberty). The saliency map suggested the model primarily focused on the posterior pharyngeal wall and the uvula. Our study revealed the potential utility of pharyngeal images by accurately identifying individuals' reported sex using deep learning algorithm.

[Analysis of the difference of therapeutic effect and predictive factors between postural and non-postural OSA after modified uvulopalatopharyngoplasty].

Objective:To analyze the factors influencing the outcome of uvulopalatopharyngoplasty in positional obstructive sleep apnea（POSA） and non-positional OSA（NPOSA） patients, and to explore the differences between the two groups. Methods:The data of 101 patients with obstructive sleep apnea who received treatment from November 2020 to November 2023 were retrospectively analyzed. Among them, 45 positional patients（POSA group） and 56 non-positional patients（NPOSA group）, who underwent overnight polysomnography were included. The upper airway（UA） anatomy was evaluated by three-dimensional computer tomography（3D-CT）. All patients received revised uvulopalatopharyngoplasty with uvula preservation and were followed using polysomnography for at least three months postoperatively. Results:The overall effective rate was 55.45%. The surgical success rate in POSA undergoing UPPP was higher than NPOSA（POSA 30/45, 66.7% versus NPOSA 26/56, 46.4%, P=0.042）. The H-UPPP effect of POSA was negatively correlated with the minimum lateral airway of the Velopharyngeal airway（r=-0.505, P<0.001）, the minimum lateral airway of the glossopharyngeal airway（r=-0.474, P=0.001） and the minimum cross-sectional area（r=-0.394, P=0.007）. Logistic analysis showed that minimal lateral airway of the glossopharynxgeum（mLAT）（OR 0.873; 95%CI 0.798-0.955, P=0.003） was a significant predictor for surgical outcomes among POSA patients. In NPOSA, age（OR 0.936; 95%CI 0.879-0.998, P=0.042） was a significant predictor for surgical outcomes. Conclusion:The effect of H-UPPP was higher in POSA than in NPOSA. The width of glossopharyngeal mLAT was an important predictor of POSA efficacy. Age was a predictor of NPOSA efficacy.

[The choice of method of surgical treatment of velopharyngeal insufficiency]. / Vybor metoda khirurgicheskogo lecheniya nebno-glotochnoi nedostatochnosti.

OBJECTIVE: To establish the criteria for selecting surgical treatments for velopharyngeal disfunction and to evaluate their effectiveness.Materials and Methods. 34 patients with velopharyngeal insufficiency underwent surgery at the National Medical Research Center for Surgery and Maxillofacial Surgery. Five common surgical methods for treating velopharyngeal disfunction were employed. RESULTS: The choice of surgery was primarily based on the anatomical and functional state of the muscle lifting the soft palate, specifically its position, which was determined visually or by MRI. Repositioning of the muscle helped to improve or restore speech in patients with velopharyngeal disfunction through surgeries such as secondary cleft revision, Furlow's palatoplasty, and triangular miomucosal flaps. In cases of soft palate palsy or correct positioning of the m. levator veli palatini, the focus of surgical treatment shifted to the pharynx, where surgeries like pharyngoplasty with a posterior pharyngeal flap and Hynes pharyngoplasties were performed. These also improved or restored speech in patients, though more towards improvement than complete restoration. If the muscle's position was optimal, the choice of treatment method subsequently depended on the results of additional nasopharyngoscopy: determining the size of the opening and the type of velopharyngeal closure. Besides the common methods used for speech management, various surgical procedures were combined based on the clinical situation. CONCLUSION: The position of the levator muscle is very important for its function. The optimal treatment for velopharyngeal disfunction, especially in patients with large openings, involved using a buccal flap alone or in combination with triangular mucosal-muscle flaps, where the highest percentage of normal speech rate was achieved.

[Prospects for the use of ozone therapy and low-intensity laser therapy in the treatment of atrophic pharyngitis]. / Perspektivy primeneniya ozonoterapii i nizkointensivnoi lazeroterapii pri lechenii atroficheskogo faringita.

Chronic pharyngitis (CP) is one of the most common diseases of the oropharynx. The number of referrals from patients with CP reaches 70% of the total number of referrals to an otorhinolaryngologist. The development of this disease is facilitated by the neuro-reflex factor and a violation of trophic and metabolic processes. It should be noted that of all forms of CP, the greatest impact on the quality of life is noted precisely in atrophic pharyngitis (AP), due to the presence of pronounced subjective sensations from the oropharynx. Many of the modern methods of treatment do not provide a lasting effect due only to the application, superficial local effect on the altered mucous membrane of the posterior pharyngeal wall, without taking into account the changes caused by a violation of trophic processes in the tissue. A promising direction in the treatment of atrophic pharyngitis is the use of a combined technique - ozone therapy and low-intensity laser therapy. The article presents the results of the application of fine-drip irrigation of the mucous membrane of the posterior pharyngeal wall with Ozonide oil in combination with low-intensity laser radiation on the projection of vessels supplying blood to the middle parts of the oropharynx. OBJECTIVE: Improving the effectiveness of treatment of patients with atrophic pharyngitis through the use of ozone therapy and low-intensity laser therapy. MATERIAL AND METHODS: A single-center experimental controlled randomized open-label study of 90 patients with AP aged 18 and over was conducted. All patients were randomly divided into three groups depending on the treatment performed: group I - traditional treatment method (rinsing the oropharynx with antiseptic solutions, the use of tablets for resorption), group II - treatment with ozone therapy (fine drip irrigation of the mucous membrane of the posterior pharyngeal wall with Ozonide oil), group III - treatment with ozone therapy and laser therapy. During the examination of patients, anamnesis collection, examination of ENT organs, cytological and microbiological examination of the mucous membrane of the posterior pharyngeal wall, contact endoscopy of the mucous membrane of the posterior pharyngeal wall were performed. 5-point visual analogue scales (VAS) were used to assess complaints and pharyngoscopic signs. RESULTS: Our results showed a statistically significant improvement in the quality of life of patients with AP (p=0.012), an improvement in the pharyngoscopic picture (p=0.003). The results obtained by us indicate an improvement in microcirculation under the influence of ozone therapy and low-intensity laser radiation. The technique using ozone therapy and low-intensity laser therapy is characterized by a bactericidal and fungicidal effect. There is a decrease in the total contamination of the posterior wall of the oropharynx with pathogenic and saprophytic microflora (there is a decrease in the contamination of the posterior wall of the pharynx with saprophytic and pathogenic microflora (p≤0.05), the differences are statistically significant). The technique using ozone therapy and low-intensity laser therapy has a pronounced anti-inflammatory effect, which was expressed in a decrease in the severity of dyskeratosis and hyperkeratosis. Thus, the use of ozone therapy in combination with laser therapy opens up new prospects for pathogenetically sound and effective treatment of AP.

Pharyngeal phase of swallowing in post-stroke dysphagia: videoendoscopy and speech-language-hearing assessment. / Fase faríngea da deglutição na disfagia pós-AVE: achados videoendoscópios e da avaliação fonoaudiológica.

PURPOSE: To investigate the outcomes of fiberoptic endoscopic evaluation of pharyngeal swallowing phase and clinical evaluation of swallowing among dysphagic individuals with and without chronic stroke in different food consistencies. METHODS: This is a cross-sectional and retrospective study based on data collection from medical records. 134 swallowing video endoscopy exams of dysphagic patients were analyzed, in which they were divided into two groups according to the diagnosis of stroke, in which data were collected regarding mobility and strength of the tongue, phonation and cough efficiency, and the pharyngeal signs of dysphagia with four food consistencies from the International Dysphagia Diet Standardization Initiative (IDDSI), for comparison between groups. To analyze and classify the severity of pharyngeal residues, the Yale Pharyngeal Residue Severity Rating Scale (YPRSRS) was used by two independent professionals. RESULTS: There was a significant difference in the presence of pharyngeal residue, laryngeal penetration and laryngotracheal aspiration in all consistencies evaluated (level 0, 2, 4 and 7) (p= <0.001), in addition to the association with multiple swallowing in thin liquid, slightly thickened liquid and solid (level 0, 2 and 7) (p= 0.026). CONCLUSION: Dysphagic individuals diagnosed with stroke showed differences in videoendoscope signs of pharyngeal residue, laryngeal penetration and laryngotracheal aspiration, regardless of the food consistency assessed, compared to dysphagic individuals without the diagnosis. Just as there was a difference in the finding of multiple swallowing only in the consistencies of thin liquid, extremely thickened liquid and solid.

OBJETIVO: Investigar os achados videoendoscópios da fase faríngea da deglutição e da avaliação clínica da deglutição, entre indivíduos disfágicos com e sem AVE crônico em diferentes consistências alimentares. MÉTODO: Trata-se de um estudo transversal e retrospectivo com base na coleta de dados dos prontuários. Foram analisados 134 exames da videoendoscopia da deglutição de pacientes disfágicos, em que foram divididos em dois grupos de acordo com o diagnóstico de AVE, na qual, foram coletados dados com relação à mobilidade e força de língua, fonação e eficiência da tosse, e os sinais faríngeos de disfagia com quatro consistências alimentares do International Dysphagia Diet Standartisation Initiative (IDDSI), para comparação entre os grupos. Para análise e classificação da gravidade dos resíduos faríngeos, foi utilizado o Yale Pharyngeal Residue Severity Rating Scale (YPRSRS) por dois profissionais independentes. RESULTADOS: Houve diferença significativa com a presença de resíduos faríngeos, penetração laríngea e aspiração laringotraqueal em todas as consistências avaliadas (nível 0, 2, 4 e 7) (p= <0,001), além da associação com deglutições múltiplas em líquido ralo, líquido levemente espessado e sólido (nível 0, 2 e 7) (p= 0,026). CONCLUSÃO: Os indivíduos disfágicos com diagnóstico de acidente vascular encefálico apresentaram diferença nos sinais videoendoscópios de resíduos faríngeos, penetração laríngea e aspiração laringotraqueal independentemente da consistência alimentar avaliada, em comparação aos indivíduos disfágicos sem o diagnóstico. Assim como houve diferença no achado da deglutição múltipla apenas nas consistências de líquido ralo, líquido extremamente espessado e sólido.

The effect of different functional appliances on the sagittal pharyngeal airway dimension in skeletal class II: a retrospective study.

The aim of this study was to compare the changes in the sagittal pharyngeal airway dimension (SPAD) in adolescents with Class II mandibular retrusion treated with Invisalign Mandibular Advancement (IMA), prefabricated Myobrace (MB), and Twin block (TB). For this retrospective study, the pre-treatment and post-treatment lateral cephalograms of 60 patients who underwent myofunctional treatment, using either one of the tested appliances were gathered from the files of treated patients. Changes in the SPAD were measured in each group, and comparisons were carried out between the three study groups. Additionally, sagittal skeletal measurements were carried out. Comparisons of the study variables at T0 and T1 between the three groups were performed using one-way ANOVA, while comparisons of the difference (T1-T0) were performed using Kruskal Wallis test. A significant SPAD increase has been reported using the three tested appliances (p < 0.05), with the least change documented with MB use (p < 0.05). Significant antero-posterior improvements have been found with IMA, MB, and TB with an increase in the SNB°, and a decrease in ANB° and Wits appraisal (p < 0.05). Non-significant FMA° changes have been observed post-treatment in the three test groups (p > 0.05). The IMA, MB, and TB generated significant SPAD and sagittal changes, with both IMA and TB surpassing MB in the airway area improvement post-treatment. Moreover, the three tested Class II functional appliances did not affect the vertical dimension.

Neural network analysis of pharyngeal sounds can detect obstructive upper respiratory disease in brachycephalic dogs.

Brachycephalic obstructive airway syndrome (BOAS) is a highly prevalent respiratory disease affecting popular short-faced dog breeds such as Pugs and French bulldogs. BOAS causes significant morbidity, leading to poor exercise tolerance, sleep disorders and a shortened lifespan. Despite its severity, the disease is commonly missed by owners or disregarded by veterinary practitioners. A key clinical sign of BOAS is stertor, a low-frequency snoring sound. In recent years, a functional grading scheme has been introduced to semi-objectively grade BOAS based on the presence of stertor and other abnormal signs. However, correctly grading stertor requires significant experience and adding an objective component would aid accuracy and repeatability. This study proposes a recurrent neural network model to automatically detect and grade stertor in laryngeal electronic stethoscope recordings. The model is developed using a novel dataset of 665 labelled recordings taken from 341 dogs with diverse BOAS clinical signs. Evaluated via nested cross validation, the neural network predicts the presence of clinically significant BOAS with an area under the receiving operating characteristic of 0.85, an operating sensitivity of 71% and a specificity of 86%. The algorithm could enable widespread screening for BOAS to be conducted by both owners and veterinarians, improving treatment and breeding decisions.

Review of retropharyngeal and parapharyngeal nodal metastasis of papillary thyroid carcinoma.

BACKGROUND: Papillary thyroid carcinoma (PTC) is the most common type of thyroid cancer. In rare instances, PTC has metastasized to the retropharyngeal and parapharyngeal nodes. This is hypothesized to occur due to an aberrant lymphatic channel or via retrograde lymphatic flow following previous neck dissection. METHODS: A literature search was conducted with keywords "parapharyngeal," "retropharyngeal," and "papillary thyroid carcinoma." RESULTS: 46 articles were identified for a total of 135 cases. The most common presenting symptom was lymphadenopathy followed by pharyngeal mass and dyspnea. 38.03 % of patients were asymptomatic. Of cases including initial treatment history, 94.44 % had a history of neck dissection. The transcervical approach was the most utilized to resect the tumors, although in recent years trans-oral robotic surgery (TORS) has also been used. CONCLUSION: PTC metastatic to the retropharyngeal and parapharyngeal nodes is a rare occurrence that can be difficult to diagnose due its indolent nature.

Transcriptional and epigenetic characterization of a new in vitro platform to model the formation of human pharyngeal endoderm.

BACKGROUND: The Pharyngeal Endoderm (PE) is an extremely relevant developmental tissue, serving as the progenitor for the esophagus, parathyroids, thyroids, lungs, and thymus. While several studies have highlighted the importance of PE cells, a detailed transcriptional and epigenetic characterization of this important developmental stage is still missing, especially in humans, due to technical and ethical constraints pertaining to its early formation. RESULTS: Here we fill this knowledge gap by developing an in vitro protocol for the derivation of PE-like cells from human Embryonic Stem Cells (hESCs) and by providing an integrated multi-omics characterization. Our PE-like cells robustly express PE markers and are transcriptionally homogenous and similar to in vivo mouse PE cells. In addition, we define their epigenetic landscape and dynamic changes in response to Retinoic Acid by combining ATAC-Seq and ChIP-Seq of histone modifications. The integration of multiple high-throughput datasets leads to the identification of new putative regulatory regions and to the inference of a Retinoic Acid-centered transcription factor network orchestrating the development of PE-like cells. CONCLUSIONS: By combining hESCs differentiation with computational genomics, our work reveals the epigenetic dynamics that occur during human PE differentiation, providing a solid resource and foundation for research focused on the development of PE derivatives and the modeling of their developmental defects in genetic syndromes.

Molecular characterization of Streptococcus pyogenes (StrepA) non-invasive isolates during the 2022-2023 UK upsurge.

At the end of 2022 into early 2023, the UK Health Security Agency reported unusually high levels of scarlet fever and invasive disease caused by Streptococcus pyogenes (StrepA or group A Streptococcus). During this time, we collected and genome-sequenced 341 non-invasive throat and skin S. pyogenes isolates identified during routine clinical diagnostic testing in Sheffield, a large UK city. We compared the data with that obtained from a similar collection of 165 isolates from 2016 to 2017. Numbers of throat-associated isolates collected peaked in early December 2022, reflecting the national scarlet fever upsurge, while skin infections peaked later in December. The most common emm-types in 2022-2023 were emm1 (28.7 %), emm12 (24.9 %) and emm22 (7.7 %) in throat and emm1 (22 %), emm12 (10 %), emm76 (18 %) and emm49 (7 %) in skin. While all emm1 isolates were the M1UK lineage, the comparison with 2016-2017 revealed diverse lineages in other emm-types, including emm12, and emergent lineages within other types including a new acapsular emm75 lineage, demonstrating that the upsurge was not completely driven by a single genotype. The analysis of the capsule locus predicted that only 51 % of throat isolates would produce capsule compared with 78% of skin isolates. Ninety per cent of throat isolates were also predicted to have high NADase and streptolysin O (SLO) expression, based on the promoter sequence, compared with only 56% of skin isolates. Our study has highlighted the value in analysis of non-invasive isolates to characterize tissue tropisms, as well as changing strain diversity and emerging genomic features which may have implications for spillover into invasive disease and future S. pyogenes upsurges.

Antibacterial and antibiofilm effect of Zinc Oxide nanoparticles on P. aeruginosa variants isolated from young patients with cystic fibrosis.

BACKGROUND: P. aeruginosa, a biofilm-forming bacteria, is the main cause of pulmonary infection in CF patients. We applied ZnO-np as a therapeutic agent for eradicating multi-drug resistance and biofilm-forming P. aeruginosa isolated from young CF patients. METHODS: A total of 73 throat and sputum samples taken from young CF patients were inquired. ZnO-np was synthesized and characterized in terms of size, shape, and structure for anti-bacterial activity. The antibiotic susceptibility of isolates before and after the addition of 16 µg/ml of ZnO was evaluated using disc diffusion and microtiter methods, respectively. The gene expression level of QS genes was assessed after treatment with 16 µg/ml ZnO-np. RESULTS: The optimum concentration of ZnO-np with a higher inhibitory zone was 16 µg/ml (MIC) and 32 µg/ml (MBC). All isolates were resistant to applied antibiotics, and about 45 % of isolates were strong biofilm-forming bacteria. After treatment with 16 µg/ml ZnO-np, all strains became susceptible to the applied antibiotic except for amikacin, which confers an intermediate pattern. About 63 % and 20 % of isolates were, respectively, non-biofilm and weak biofilm-forming bacteria following the addition of ZnO-np. Relative gene expression of gacA, lasR, and rhlR genes were downregulated significantly (P < 0.001). Although the retS did not have a significant reduction (P = 0.2) CONCLUSION: ZnO-np at a concentration of 16 µg/ml could significantly reduce the P. aeruginosa infection by altering the antibiotic susceptibility pattern and inhibiting biofilm formation. Due to their photocatalytic properties and their ability to penetrate the extracellular polysaccharide layer, ZnO nanoparticles can produce ROS, which increases their susceptibility to antibiotics. Nasal delivery of ZnO-np in the form of aerosol can be considered a potential strategy to decrease the mortality rate in CF patients at an early age.

Towards laryngeal cancer diagnosis using Dandelion Optimizer Algorithm with ensemble learning on biomedical throat region images.

Laryngeal cancer exhibits a notable global health burden, with later-stage detection contributing to a low mortality rate. Laryngeal cancer diagnosis on throat region images is a pivotal application of computer vision (CV) and medical image diagnoses in the medical sector. It includes detecting and analysing abnormal or cancerous tissue from the larynx, an integral part of the vocal and respiratory systems. The computer-aided system makes use of artificial intelligence (AI) through deep learning (DL) and machine learning (ML) models, including convolution neural networks (CNN), for automated disease diagnoses and detection. Various DL and ML approaches are executed to categorize the extraction feature as healthy and cancerous tissues. This article introduces an automated Laryngeal Cancer Diagnosis using the Dandelion Optimizer Algorithm with Ensemble Learning (LCD-DOAEL) method on Biomedical Throat Region Image. The LCD-DOAEL method aims to investigate the images of the throat region for the presence of laryngeal cancer. In the LCD-DOAEL method, the Gaussian filtering (GF) approach is applied to eliminate the noise in the biomedical images. Besides, the complex and intrinsic feature patterns can be extracted by the MobileNetv2 model. Meanwhile, the DOA model carries out the hyperparameter selection of MobileNetV2 architecture. Finally, the ensemble of three classifiers such as bidirectional long short-term memory (BiLSTM), regularized extreme learning machine (ELM), and backpropagation neural network (BPNN) models, are utilized for the classification process. A comprehensive set of simulations is conducted on the biomedical image dataset to highlight the efficient performance of the LCD-DOAEL technique. The comparison analysis of the LCD-DOAEL method exhibited a superior accuracy outcome of 97.54% over other existing techniques.

Performance enhancement of deep learning based solutions for pharyngeal airway space segmentation on MRI scans.

The automatic segmentation of the pharyngeal airway space has many potential medical use, one of which is to help facilitate the creation of the Tubingen Palatal Plate. Therefore, it is of great importance to understand which methods are suitable for this task. Here, neural network based solutions available in the literature are compared to find the best methods. Neural network models were chosen to encompass a diverse landscape. Some models were taken from the general semantic segmentation literature, while others were taken from the medical or pharyngeal airway space segmentation literature. Some models are convolutional neural networks, while others are transformer-based model or a mix of both convolutional and transformer-based model. These models include 2d/3d U-Net, Deeplabv3, YOLOv8, Swinv2 UNETR, SegFormer, and 3D MRU-Net. Furthermore, additional strategies to enhance performance were also considered. These strategies consisted of training two separate networks in multiple stages as well leveraging unlabeled data to pretrain the neural networks before fine-tuning them on the labeled data. It was found that out of all the models considered here, the 2d U-Net performed the best achieving an average dice score of 0.9180 ± 0.0111. Out of all the strategies to enhance performance, only two strategies improve the actual results but only by a small margin. Therefore, these strategies can be consider if a small increase in performance is desired from the 2d U-Net at the expense of computational resource.