|
KMID : 1100520230290010016
|
|
Healthcare Informatics Research
2023 Volume.29 No. 1 p.16 ~ p.22
|
|
|
Application of a Multi-Layer Perceptron in Preoperative Screening for Orthognathic Surgery
|
|
Chaiprasittikul Natkritta
Thanathornwong Bhornsawan
Pornprasertsuk-Damrongsri Suchaya
Raocharernporn Somchart
Maponthong Somporn
Manopatanakul Somchai
|
|
|
Abstract
|
|
|
Objectives: Orthognathic surgery is used to treat moderate to severe occlusal discrepancies. Examinations and measurementsfor preoperative screening are essential procedures. A careful analysis is needed to decide whether cases require orthognathicsurgery. This study developed screening software using a multi-layer perceptron to determine whether orthognathic surgeryis required.
Methods: In total, 538 digital lateral cephalometric radiographs were retrospectively collected from a hospitaldata system. The input data consisted of seven cephalometric variables. All cephalograms were analyzed by the Detectron2detection and segmentation algorithms. A keypoint region-based convolutional neural network (R-CNN) was used for objectdetection, and an artificial neural network (ANN) was used for classification. This novel neural network decision supportsystem was created and validated using Keras software. The output data are shown as a number from 0 to 1, with casesrequiring orthognathic surgery being indicated by a number approaching 1.
Results: The screening software demonstrateda diagnostic agreement of 96.3% with specialists regarding the requirement for orthognathic surgery. A confusion matrixshowed that only 2 out of 54 cases were misdiagnosed (accuracy = 0.963, sensitivity = 1, precision = 0.93, F-value = 0.963,area under the curve = 0.96).
Conclusions: Orthognathic surgery screening with a keypoint R-CNN for object detection andan ANN for classification showed 96.3% diagnostic agreement in this study.
|
|
|
KEYWORD
|
|
|
Orthognathic Surgery, Cephalometry, Neural Network Models, Classification, Artificial Intelligence
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|