Search

Purpose: Accurate diagnosis and quantification of polyps and symptoms are pivotal for planning the therapeutic strategy of Chronic rhinosinusitis with nasal polyposis (CRSwNP). This pilot study aimed to develop an artificial intelligence (AI)-based image analysis system capable of segmenting nasal polyps from nasal endoscopy videos. Methods: Recorded nasal videoendoscopies from 52 patients diagnosed with CRSwNP between 2019 and 2022 were retrospectively analyzed. Images extracted were manually segmented on the web application Roboflow. A dataset of 342 images was generated and divided into training (80%), validation (10%), and testing (10%) sets. The Ultralytics YOLOv8.0.28 model was employed for automated segmentation. Results: The YOLOv8s-seg model consisted of 195 layers and required 42.4 GFLOPs for operation. When tested against the validation set, the algorithm achieved a precision of 0.91, recall of 0.839, and mean average precision at 50% IoU (mAP50) of 0.949. For the segmentation task, similar metrics were observed, including a mAP ranging from 0.675 to 0.679 for IoUs between 50% and 95%. Conclusions: The study shows that a carefully trained AI algorithm can effectively identify and delineate nasal polyps in patients with CRSwNP. Despite certain limitations like the focus on CRSwNP-specific samples, the algorithm presents a promising complementary tool to existing diagnostic methods. [ABSTRACT FROM AUTHOR]

Objectives: Nasal polyposis (NP) is a common and recurrent condition of the sinonasal cavity which has significant impact on patients' quality of life. NP pathophysiology involves a complex interplay of genetic, environmental, and immunological factors. Several studies have explored the association between human leukocyte antigen (HLA) class II alleles and NP, but the results have been conflicting. The aim of this meta-analysis is to investigate the association between HLA class II alleles, specifically HLA-DQA1, HLA-DQB1, and HLA-DRB1and NP risk. Methods: A systematic review was conducted using electronic databases, including PubMed, Google Scholar, and Cochrane Library, to identify studies investigating the association between HLA class II alleles and NP. Eligible studies were identified by specific inclusion and exclusion criteria. The odds ratios (ORs) with 95% confidence intervals (CIs) were used to assess the association between HLA class II alleles and NP risk. A random-effects model was used to calculate the pooled OR and corresponding 95% CI, and a study required a heterogeneity assessment value I 2 < 25% to be considered for analysis. Study design: Meta-analysis. Results: A total of four studies were included in this meta-analysis, involving a total of 258 NP alleles and 802 control alleles. The analysis indicated that DQA1*0201 (OR = 3.08, 95% CI [1.70, 5.59]) and DRB1*7 (OR = 2.04, 95% CI [1.14, 3.66]) were significantly associated with increased risk of NP. The analysis of the NP risk alleles DQA1*0201 and DRB1*7 had an I2 < 0% representing low heterogeneity. Sensitivity analysis with LFK indices showed minor asymmetry in either allele. Conclusions: This meta-analysis provides evidence that the HLA-DQA1*0201 and HLA-DRB1*7 alleles are risk factors for the development of NP. These findings could contribute to a better understanding of the genetic predisposition of NP and may have implications for the development of novel approaches for the prevention and treatment of this condition. [ABSTRACT FROM AUTHOR]