Automated diagnosis of adenoid hypertrophy with lateral cephalogram in children based on multi-scale local attention

Adenoid hypertrophy can lead to adenoidal mouth breathing, which can result in "adenoid face" and, in severe cases, can even lead to respiratory tract obstruction. The Fujioka ratio method, which calculates the ratio of adenoid (A) to nasopharyngeal (N) space in an adenoidal-cephalogram (A/N), is a well-recognized and effective technique for detecting adenoid hypertrophy. However, this process is time-consuming and relies on personal experience, so a fully automated and standardized method needs to be designed. Most of the current deep learning-based methods for automatic diagnosis of adenoids are CNN-based methods, which are more sensitive to features similar to adenoids in lateral views and can affect the final localization results. In this study, we designed a local attention-based method for automatic diagnosis of adenoids, which takes AdeBlock as the basic module, fuses the spatial and channel information of adenoids through two-branch local attention computation, and combines the downsampling method without losing spatial information. Our method achieved mean squared error (MSE) 0.0023, mean radial error (MRE) 1.91, and SD (standard deviation) 7.64 on the three hospital datasets, outperforming other comparative methods.

Application of Artificial Intelligence in Orthodontics: Current State and Future Perspectives

In recent years, there has been the notable emergency of artificial intelligence (AI) as a transformative force in multiple domains, including orthodontics. This review aims to provide a comprehensive overview of the present state of AI applications in orthodontics, which can be categorized into the following domains: (1) diagnosis, including cephalometric analysis, dental analysis, facial analysis, skeletal-maturation-stage determination and upper-airway obstruction assessment; (2) treatment planning, including decision making for extractions and orthognathic surgery, and treatment outcome prediction; and (3) clinical practice, including practice guidance, remote care, and clinical documentation. We have witnessed a broadening of the application of AI in orthodontics, accompanied by advancements in its performance. Additionally, this review outlines the existing limitations within the field and offers future perspectives.

MIB-ANet: A novel multi-scale deep network for nasal endoscopy-based adenoid hypertrophy grading

Introduction

To develop a novel deep learning model to automatically grade adenoid hypertrophy, based on nasal endoscopy, and asses its performance with that of E.N.T. clinicians.

Methods

A total of 3,179 nasoendoscopic images, including 4-grade adenoid hypertrophy (Parikh grading standard, 2006), were collected to develop and test deep neural networks. MIB-ANet, a novel multi-scale grading network, was created for adenoid hypertrophy grading. A comparison between MIB-ANet and E.N.T. clinicians was conducted.

Results

In the SYSU-SZU-EA Dataset, the MIB-ANet achieved 0.76251 F1 score and 0.76807 accuracy, and showed the best classification performance among all of the networks. The visualized heatmaps show that MIB-ANet can detect whether adenoid contact with adjacent tissues, which was interpretable for clinical decision. MIB-ANet achieved at least 6.38% higher F1 score and 4.31% higher accuracy than the junior E.N.T. clinician, with much higher (80× faster) diagnosing speed.

Discussion

The novel multi-scale grading network MIB-ANet, designed for adenoid hypertrophy, achieved better classification performance than four classical CNNs and the junior E.N.T. clinician. Nonetheless, further studies are required to improve the accuracy of MIB-ANet.

Effect of adenoid hypertrophy on the upper airway and craniomaxillofacial region

BACKGROUND

In recent years, annual incidences of adenoid hypertrophy (AH), a highly common tissue lesion in children, have increased. Currently, research on AH has focused on its obstruction of nasal cavity function, and little has been written on its influence on the upper airway's bone structure. For this reason, our present study seeks to determine the influence of AH on both the morphological development characteristics of the upper airway and the craniofacial features in children, with the goal being to offer more choices for diagnosing and treating the condition in the future.

METHODS

From June 2019 to December 2020 in Department of Orthodontics, Beijing Stomatological Hospital, Capital Medical University, 38 children with AH admitted to the Department of Otolaryngology [research group (RG)] and 35 children [control group (CG)] who underwent orthodontic treatment over the same time span were selected as the research objects. X-ray examination of the lateral position of the head, observation of the maxillofacial structure, and detection of the children's height, growth factors, and sleep status, and analysis of the differences between the two groups.

RESULTS

The height of RG, insulin-like growth factor-1 (IGF-1) as well as insulin-like growth factor binding protein-3 (IGFBP-3) were all lower than CG (P<0.05), the upper airway became narrower, and the malocclusion was aggravated (P<0.05). Cephalometric measurement showed that the angle between the subspinale and sella at nasion (SNA angle) and the angle between the subspinale and supraemental at nasion (ANB angle) of RG children decreased, and the angle between the supraemental and sella at nasion (SNB angle) increased (P<0.05). In addition, the sleep quality of RG was significantly lower than that of CG (P<0.05).

CONCLUSIONS

AH can change a child's breathing mode and function by giving rise to upper airway stenosis, and by inducing deformities of their craniomaxillofacial region and oral cavity, thus disrupting their normal growth and development.

Automated Adenoid Hypertrophy Assessment with Lateral Cephalometry in Children Based on Artificial Intelligence

Adenoid hypertrophy may lead to pediatric obstructive sleep apnea and mouth breathing. The routine screening of adenoid hypertrophy in dental practice is helpful for preventing relevant craniofacial and systemic consequences. The purpose of this study was to develop an automated assessment tool for adenoid hypertrophy based on artificial intelligence. A clinical dataset containing 581 lateral cephalograms was used to train the convolutional neural network (CNN). According to Fujioka's method for adenoid hypertrophy assessment, the regions of interest were defined with four keypoint landmarks. The adenoid ratio based on the four landmarks was used for adenoid hypertrophy assessment. Another dataset consisting of 160 patients' lateral cephalograms were used for evaluating the performance of the network. Diagnostic performance was evaluated with statistical analysis. The developed system exhibited high sensitivity (0.906, 95% confidence interval [CI]: 0.750-0.980), specificity (0.938, 95% CI: 0.881-0.973) and accuracy (0.919, 95% CI: 0.877-0.961) for adenoid hypertrophy assessment. The area under the receiver operating characteristic curve was 0.987 (95% CI: 0.974-1.000). These results indicated the proposed assessment system is able to assess AH accurately. The CNN-incorporated system showed high accuracy and stability in the detection of adenoid hypertrophy from children' lateral cephalograms, implying the feasibility of automated adenoid hypertrophy screening utilizing a deep neural network model.

Adenoid measurement accuracy: A comparison of lateral skull film, flexible endoscopy, and intraoperative rigid endoscopy (gold standard)

OBJECTIVE

To compare the accuracy of lateral skull film, flexible endoscopy, and intraoperative rigid endoscopy in assessment of adenoid size.

METHODS

A cross-sectional study was conducted in 43 pediatric patients undergoing ENT surgery from July 2017 to December 2018. All patients underwent preoperative lateral skull film, flexible endoscopy, and intraoperative rigid endoscopy.

RESULTS

The average adenoidal-nasopharyngeal (A/N) ratio obtained from lateral skull film, flexible endoscopy, and intraoperative rigid endoscopy was 72.9, 79.5, and 81.6, respectively. There was a moderate correlation between A/N ratio from lateral skull film and intraoperative rigid endoscopy (Pearson's correlation: 0.567, p˂0.001). Whereas, the A/N ratio from flexible endoscopy compared to intraoperative rigid endoscopy showed a stronger correlation (Pearson's correlation: 0.791, p˂0.001). From linear regression analysis, the intraoperative adenoid measurement was estimated from the results of flexible endoscopy (intraoperative rigid endoscopy: 0.72 [flexible endoscopy] +24.47) and lateral skull film (intraoperative rigid endoscopy = 0.65 [lateral skull film] + 34) CONCLUSION: Flexible endoscopy yields the most accuracy in the assessment of adenoid size and nasopharynx visualization, without radiation exposure or anesthesia. Despite less accuracy, lateral skull film is more availability in every hospital. The correlation of adenoid size measurement in this study can also be applied for the actual size of adenoid.

Automated Radiographic Evaluation of Adenoid Hypertrophy Based on VGG-Lite

Adenoid hypertrophy is a pathological hyperplasia of the adenoids, which may cause snoring and apnea, as well as impede breathing during sleep. The lateral cephalogram is commonly used by dentists to screen for adenoid hypertrophy, but it is tedious and time-consuming to measure the ratio of adenoid width to nasopharyngeal width for adenoid assessment. The purpose of this study was to develop a screening tool to automatically evaluate adenoid hypertrophy from lateral cephalograms using deep learning. We proposed the deep learning model VGG-Lite, using the largest data set (1,023 X-ray images) yet described to support the automatic detection of adenoid hypertrophy. We demonstrated that our model was able to automatically evaluate adenoid hypertrophy with a sensitivity of 0.898, a specificity of 0.882, positive predictive value of 0.880, negative predictive value of 0.900, and F1 score of 0.889. The comparison of model-only and expert-only detection performance showed that the fully automatic method (0.07 min) was about 522 times faster than the human expert (36.6 min). Comparison of human experts with or without deep learning assistance showed that model-assisted human experts spent an average of 23.3 min to evaluate adenoid hypertrophy using 100 radiographs, compared to an average of 36.6 min using an entirely manual procedure. We therefore concluded that deep learning could improve the accuracy, speed, and efficiency of evaluating adenoid hypertrophy from lateral cephalograms.

Modified adenoid grading system for evaluating adenoid size in children: a prospective validation study

Nasal endoscopy is the best choice for evaluation of adenoid size, but very few studies published on the endoscopic quantitative assessment. This study aimed to newly propose and validate a modified adenoid grading system (MAGS) with the existing endoscopic scoring methods of adenoid size. A prospective study on children with chronic mouth breathing and having endoscopic nasal examination was conducted. Digital images obtained during endoscopic examination were evaluated with the traditional method and the MGAS. Adenoid size was also evaluated by intraoperative nasal endoscopy among those underwent adenoidectomy. One hundred and thirty patients were enrolled. The MAGS showed high inter-rater reliability with a Kappa score of 0.869. Sixty of 130 patients underwent adenoidectomy and assessed with intraoperative nasal endoscopy. The MAGS significantly correlated to the percentage of nasopharyngeal obstruction of intraoperative endoscopy (Spearman's r = 0.796, gamma coefficient = 0.94), and the percentage of choanal obstruction of preoperative endoscopy (Spearman's r = 0.816, gamma coefficient = 0.859). Our findings suggest that the MAGS has high reliability and validity for assessment of adenoid size. It may be a more suitable and reliable grading system for endoscopic evaluation of adenoid size.