Automated Adenoid Hypertrophy Assessment with Lateral Cephalometry in Children Based on Artificial Intelligence
Autor: | Yi Cao, Hong He, Lingyun Cao, Jiawei Zhou, Fang Hua, Jiarong Yan, Tingting Zhao |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
Medicine (General)
Clinical Biochemistry Mouth breathing Adenoid Article nasopharynx 03 medical and health sciences R5-920 0302 clinical medicine medicine cephalometry Craniofacial 030223 otorhinolaryngology Receiver operating characteristic business.industry adenoid hypertrophy deep learning 030206 dentistry Craniometry medicine.disease neural networks Confidence interval Obstructive sleep apnea stomatognathic diseases medicine.anatomical_structure Artificial intelligence medicine.symptom business Adenoid hypertrophy |
Zdroj: | Diagnostics Volume 11 Issue 8 Zhao, T, Zhou, J, Yan, J, Cao, L, Cao, Y, Hua, F & He, H 2021, ' Automated Adenoid Hypertrophy Assessment with Lateral Cephalometry in Children Based on Artificial Intelligence ', Diagnostics, vol. 11, no. 8, 1386 . https://doi.org/10.3390/diagnostics11081386 Diagnostics, Vol 11, Iss 1386, p 1386 (2021) |
ISSN: | 2075-4418 |
DOI: | 10.3390/diagnostics11081386 |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: | |
Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |