Details

Autor(en) / Beteiligte

• Dong, Wenjie
• Chen, Yaosen
• Li, Ankang
• Mei, Xiaoguang
• Yang, Yan

Titel

Automatic detection of adenoid hypertrophy on cone-beam computed tomography based on deep learning

Ist Teil von

• American journal of orthodontics and dentofacial orthopedics, 2023-04, Vol.163 (4), p.553-560.e3

Ort / Verlag

United States: Elsevier Inc

Erscheinungsjahr

2023

Quelle

MEDLINE

Beschreibungen/Notizen

• This study proposed an automatic diagnosis method based on deep learning for adenoid hypertrophy detection on cone-beam computed tomography. The hierarchical masks self-attention U-net (HMSAU-Net) for segmentation of the upper airway and the 3-dimensional (3D)-ResNet for diagnosing adenoid hypertrophy were constructed on the basis of 87 cone-beam computed tomography samples. A self-attention encoder module was added to the SAU-Net to optimize upper airway segmentation precision. The hierarchical masks were introduced to ensure that the HMSAU-Net captured sufficient local semantic information. We used Dice to evaluate the performance of HMSAU-Net and used diagnostic method indicators to test the performance of 3D-ResNet. The average Dice value of our proposed model was 0.960, which was superior to the 3DU-Net and SAU-Net models. In the diagnostic models, 3D-ResNet10 had an excellent ability to diagnose adenoid hypertrophy automatically with a mean accuracy of 0.912, a mean sensitivity of 0.976, a mean specificity of 0.867, a mean positive predictive value of 0.837, a mean negative predictive value of 0.981, and a F1 score of 0.901. The value of this diagnostic system lies in that it provides a new method for the rapid and accurate early clinical diagnosis of adenoid hypertrophy in children, allows us to look at the upper airway obstruction in three-dimensional space and relieves the work pressure of imaging doctors. •The proposed system can better assist dentists with screening children with adenoid hypertrophy early.•The performance of the proposed system is based on deep learning and is very close to human experts.•The diagnostic system is fast, noninvasive, and ideal for children.