Your browser doesn't support javascript.
loading
Development and validation of predictive models for skeletal malocclusion classification using airway and cephalometric landmarks.
Marya, Anand; Inglam, Samroeng; Chantarapanich, Nattapon; Wanchat, Sujin; Rithvitou, Horn; Naronglerdrit, Prasitthichai.
Afiliación
  • Marya A; Faculty of Dentistry, Thammasat University, Klong Luang, Pathumthani, 12120, Thailand.
  • Inglam S; Faculty of Dentistry, Thammasat University, Klong Luang, Pathumthani, 12120, Thailand.
  • Chantarapanich N; Department of Mechanical Engineering, Faculty of Engineering at Sriracha, Kasetsart University, Sriracha, Chonburi, 20230, Thailand.
  • Wanchat S; Department of Mechanical Engineering, Faculty of Engineering at Sriracha, Kasetsart University, Sriracha, Chonburi, 20230, Thailand.
  • Rithvitou H; Faculty of Dentistry, University of Puthisastra, Phnom Phen, 12211, Cambodia.
  • Naronglerdrit P; Department of Computer Engineering, Faculty of Engineering at Sriracha, Kasetsart University, Sriracha, Chonburi, 20230, Thailand. prasitthichai@eng.src.ku.ac.th.
BMC Oral Health ; 24(1): 1064, 2024 Sep 11.
Article en En | MEDLINE | ID: mdl-39261793
ABSTRACT

OBJECTIVE:

This study aimed to develop a deep learning model to predict skeletal malocclusions with an acceptable level of accuracy using airway and cephalometric landmark values obtained from analyzing different CBCT images.

BACKGROUND:

In orthodontics, multitudinous studies have reported the correlation between orthodontic treatment and changes in the anatomy as well as the functioning of the airway. Typically, the values obtained from various measurements of cephalometric landmarks are used to determine skeletal class based on the interpretation an orthodontist experiences, which sometimes may not be accurate.

METHODS:

Samples of skeletal anatomical data were retrospectively obtained and recorded in Digital Imaging and Communications in Medicine (DICOM) file format. The DICOM files were used to reconstruct 3D models using 3DSlicer (slicer.org) by thresholding airway regions to build up 3D polygon models of airway regions for each sample. The 3D models were measured for different landmarks that included measurements across the nasopharynx, the oropharynx, and the hypopharynx. Male and female subjects were combined as one data set to develop supervised learning models. These measurements were utilized to build 7 artificial intelligence-based supervised learning models.

RESULTS:

The supervised learning model with the best accuracy was Random Forest, with a value of 0.74. All the other models were lower in terms of their accuracy. The recall scores for Class I, II, and III malocclusions were 0.71, 0.69, and 0.77, respectively, which represented the total number of actual positive cases predicted correctly, making the sensitivity of the model high.

CONCLUSION:

In this study, it is observed that the Random Forest model was the most accurate model for predicting the skeletal malocclusion based on various airway and cephalometric landmarks.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Cefalometría / Tomografía Computarizada de Haz Cónico / Puntos Anatómicos de Referencia / Maloclusión Límite: Adolescent / Female / Humans / Male Idioma: En Revista: BMC Oral Health Asunto de la revista: ODONTOLOGIA Año: 2024 Tipo del documento: Article País de afiliación: Tailandia Pais de publicación: Reino Unido
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Cefalometría / Tomografía Computarizada de Haz Cónico / Puntos Anatómicos de Referencia / Maloclusión Límite: Adolescent / Female / Humans / Male Idioma: En Revista: BMC Oral Health Asunto de la revista: ODONTOLOGIA Año: 2024 Tipo del documento: Article País de afiliación: Tailandia Pais de publicación: Reino Unido