Problem Statement: While CT (Computed Tomography) is commonly used, its diagnostic accuracy for chronic sinusitis remains uncertain. Moreover, the high cost of CT examinations limits its use as a routine diagnostic method. There is an urgent need to develop an AI-assisted diagnostic model for sinusitis.
Objective: The primary aim of this study is to develop an AI-assisted diagnostic model for sinusitis that can improve diagnostic accuracy and accessibility compared to traditional CT methods.
Methodology: This study utilized a retrospective approach, focusing on patients diagnosed with chronic sinusitis via CT and normal patients admitted to the People's Hospital between January 2018 and January 2019. A total of 5000 sinus CT images were collected. All cases underwent T (targeted) coronal plain scans in the hospital's CT room, ensuring complete CT images. In constructing the chronic sinusitis classification model based on deep learning, 5000 CT images of soft tissue windows and sinuses were gathered. This included 1000 CT images for each of the four groups diagnosed with sphenoid sinusitis, frontal sinusitis, ethmoid sinusitis, and maxillary sinusitis, along with 1000 images from normal cases (250 images per group). The sigmoid function replaced the softmax function, and the binary cross-entropy function was used to assess the model's predictive accuracy.
Results: The model achieved an accuracy of 85.8%, outperforming doctors with low (71.7%), medium (78.4%), and senior (73.4%) qualifications. The model demonstrated high accuracy, superior feature extraction, and resolution capabilities.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1177/09287329241309799 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Nasal irrigation solution is less cytotoxic to nasal epithelial cells than nasal spray.
Indian J Otolaryngol Head Neck Surg
February 2025
Division of Otolaryngology and Head and Neck Surgery, University of British Columbia, Vancouver, Canada.
Background: Recent studies have demonstrated that corticosteroid delivered by nasal irrigation is superior to nasal spray in the treatment of chronic rhinosinusitis patients who have undergone sinus surgery. However, the local cytotoxicity of both delivery methods has not been previously evaluated. In this study we aimed to evaluate the cytotoxicity of corticosteroid prepared nasal irrigation solution and commercially available corticosteroid nasal spray.
View Article and Find Full Text PDFBilateral Sinonasal Glomangiopericytoma: A Rare Case Report Misdiagnosed as Benign Nasal Polyps.
Indian J Otolaryngol Head Neck Surg
February 2025
ENT and Neck and Head Surgery Department, University Medical Center Mohammed VI, Marrakech, Marrakech Morocco.
This study aims to present a case of Sinonasal glomangiopericytoma (SNGPC) in a 43-year-old woman, emphasizing the diagnostic challenges and highlighting the importance of considering rare tumors in the differential diagnosis of nasal polyps. We describe the clinical presentation, diagnostic process, and treatment outcomes of a patient presenting with chronic bilateral nasal obstruction, anosmia, and intermittent epistaxis. Initial diagnosis of benign nasal polyps was made based on endoscopic findings, followed by histopathological analysis confirming bilateral SNGPC.
View Article and Find Full Text PDFSirt5 affects the metabolic remodeling of eosinophils by negatively regulating the level of succinylation modification of Pkm2 in eosinophilic chronic rhinosinusitis.
World J Otorhinolaryngol Head Neck Surg
March 2025
Objectives: This study aims to investigate the role of Sirt5 in regulating eosinophil maturation and activation, specifically focusing on primary eosinophils in mice at the genetic level. Additionally, the study aims to elucidate the underlying mechanism of Sirt5 in eosinophilic inflammation metabolism and identify potential drug targets for the treatment of chronic sinusitis. The findings of this study will provide new insights and a solid theoretical basis for the development of novel therapeutic strategies for eosinophilic chronic rhinosinusitis (eCRS).
View Article and Find Full Text PDFUsing Machine Learning Models to Diagnose Chronic Rhinosinusitis: Analysis of Pre-Treatment Patient-Generated Health Data to Predict Cardinal Symptoms and Sinonasal Inflammation.
Am J Rhinol Allergy
March 2025
Department of Otolaryngology - Head and Neck Surgery, University of Washington, Seattle, WA, USA.
BackgroundThe diagnosis of chronic rhinosinusitis (CRS) relies upon patient-reported symptoms and objective nasal endoscopy and/or computed tomography (CT) findings. Many patients, at the time of evaluation by an otolaryngologist or rhinologist, lack objective findings confirming CRS and do not have this disease.ObjectiveWe hypothesized that a machine learning model (MLM) could predict probable CRS using patient-reported data acquired prior to rhinologist-directed treatment.
View Article and Find Full Text PDFAssociation between allergic rhinitis, nasal polyps, chronic sinusitis and chronic respiratory diseases: a mendelian randomization study.
BMC Pulm Med
March 2025
Department of Respiratory and Critical Care Medicine, General Hospital of Ningxia Medical University, Yinchuan, China.
Background: Epidemiological investigations provide considerable evidence supporting the coexistence of upper airway ailments with lower airway disorders, but the association between common nasal diseases, such as allergic rhinitis, chronic sinusitis, nasal polyps, and chronic respiratory conditions require further exploration.
Methods: In this study, a two-sample mendelian randomization was employed to explore the potential association between allergic rhinitis, nasal polyps, and chronic sinusitis with various chronic respiratory diseases. For the primary analysis, summary statistics related to chronic respiratory diseases were obtained from the UK Biobank of European ancestry.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!