Diseases of the nose and paranasal sinuses in child

Stenner, Markus; Rudack, Claudia

doi:10.3205/cto000113

Cited by 9 publications

(1 citation statement)

References 217 publications

(246 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Кроме четырех симптомов, которые описывают как типичные для АР (чихание, заложенность роса, обильное водянистое отделяемое и зуд в носу), в реальной клинической практике, особенно у детей младшего возраста, требуют внимания и другие проявления, связанные с нарушением носового дыхания: рецидивирующие респираторные инфекции, нарушения ночного сна, в возрастной перспективе -нарушения формирования лицевого скелета, нарушения прикуса зубов и т. п. [7,9,10].…”

Section: Introductionunclassified

Allergic rhinitis in children: a comprehensive approach to treatment

et al. 2022

View full text Add to dashboard Cite

Prevalence of allergic rhinitis among chronic upper respiratory diseases in pediatrics is one of highest. Beside anti-inflammatory drugs (topical steroids, antileukotrienes, antihistamines), reliever therapies are important too in treatment of allergic rhinitis. Decongestant prescription in children should lasts no more than 7–10 days; combination of alpha1-adrenomimetic with topical antihistamines is one of possible ways to improve the efficacy, for example, the combination of dimetindene maleate with phenylephrine as nasal drops. We present the results of retrospective evaluation of 625 patients aged from 0 to 17 years with allergic rhinitis, diagnosed not less than 12 month ago. Among examined group, mild allergic rhinitis prevalence was 56.9%, moderate 37.2% and severe 5.9%. During the year all patients experienced 1754 exacerbations (on average, 2.79 ± 1.13 exacerbations per patient). Contact with allergen (35.3%) and respiratory infections (28.8%) were more prevalent reasons of exacerbation; non-specific trigger provocation (pungent smells, air humidity or temperature change etc.) (19.8%) and unknown reason (16.4%) of allerhttps://doi.org/10.21518/2079-701X-2022-16-1-184-189 gic rhinitis exacerbation were less prevalent. When treated with combined nasal drops of dimetindene maleate and phenylephrine median [Q25; Q75] duration of exacerbation was a bit shorter 7.94 [6.25; 17.15] days, than using other decongestants, but difference was statistically insignificant. Combined nasal drops were maximal clinically efficient among patients under 12 years old with exacerbations, caused by allergens contacts. We did not register any adverse events caused by decongestant treatment, during our study. Patients with allergic rhinitis should be provided with written action plan for the disease exacerbation. Using as reliever therapy combined nasal drops (dimetindene maleate and phenylephrine) registered for patients from 1 year old, decrease number of medicines and reduce allergic rhinitis exacerbations duration.

show abstract

Section: Introductionunclassified

Allergic rhinitis in children: a comprehensive approach to treatment

et al. 2022

View full text Add to dashboard Cite

show abstract

Supervised Contrastive Learning to Classify Paranasal Anomalies in the Maxillary Sinus

Bhattacharya

Becker

Behrendt

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Using deep learning techniques, anomalies in the paranasal sinus system can be detected automatically in MRI images and can be further analyzed and classified based on their volume, shape and other parameters like local contrast. However due to limited training data, traditional supervised learning methods often fail to generalize. Existing deep learning methods in paranasal anomaly classification have been used to diagnose at most one anomaly. In our work, we consider three anomalies. Specifically, we employ a 3D CNN to separate maxillary sinus volumes without anomaly from maxillary sinus volumes with anomaly. To learn robust representations from a small labelled dataset, we propose a novel learning paradigm that combines contrastive loss and cross-entropy loss. Particularly, we use a supervised contrastive loss that encourages embeddings of maxillary sinus volumes with and without anomaly to form two distinct clusters while the cross-entropy loss encourages the 3D CNN to maintain its discriminative ability. We report that optimising with both losses is advantageous over optimising with only one loss. We also find that our training strategy leads to label efficiency. With our method, a 3D CNN classifier achieves an AUROC of 0.85 ± 0.03 while a 3D CNN classifier optimised with cross-entropy loss achieves an AUROC of 0.66 ± 0.1. Our source code is available at https://github. com/dawnofthedebayan/SupConCE_MICCAI_22.

show abstract