구순열 비변형의 객관적 평가를 위한 Neural Network의 적용

Objective assessment of cleft lip nose deformity by neural network

Cleft palate is a congenital deformity condition with separation of the two sides of the lip resulting in nose deformity. Evaluation of surgical corrections and outcome assessments for nose deformity due to the cleft lip depends mainly on doctor's subjective judgment. An objective method for evaluation of the condition and surgical outcome of nose deformity due to the cleft palate is needed. This study aimed at objective assessment of a cleft palate nose deformity condition by analyzing the following parameters obtained from photographic images of a cleft palate patients: (1) angle difference between two nostril axes. (2) center of the nostril and distance between two centers. (3) overlapped area of two nostrils, and (4) the overlapped area ratio of the two nostrils. A regression equation of doctor's grades was obtained using the eight parameters. Three plastic surgeons gave us the grades for the each photographic image by 10 increments with maximum grade of 100. The average reproducibility of the grades given by the three plastic surgeons and the three laymen using the developed program was $10.8{\pm}4.6%$ and $7.4{\pm}1.8%$, respectively. Kappa values representing the degree of consensus of the plastic surgeons and the three laymen were 0.43 and 0.83. respectively. Correlation coefficient of the grades evaluated by the surgeons and obtained by the neural network was 0.798. In conclusion. the developed neural network model provided us better reproducibility and much better consensus than doctor's subjective evaluation in addition to objectiveness and easy application.