Abstract

Patients suffering from pectus excavatum often experience psychosocial distress due to perceived anomalies in their physical appearance. The ability to visually inform patients about their expected aesthetic outcome after surgical correction is still lacking. This study aims to develop an automatic, patient-specific model to predict aesthetic outcome after the Nuss procedure. Patients prospectively received preoperative and postoperative 3-dimensional optical surface scanning of their chest during the Nuss procedure. A prediction model was composed based on nonlinear least squares data-fitting, regression methods and a 2-dimensional Gaussian function with adjustable amplitude, variance, rotation, skewness, and kurtosis components. Morphological features of pectus excavatum were extracted from preoperative images using a previously developed surface analysis tool to generate a patient-specific model. Prediction accuracy was evaluated through cross-validation, utilizing the mean root squared deviation and maximum positive and negative deviations as performance measures. The prediction model was evaluated on 30 (90% male) prospectively imaged patients. The model achieved an average root mean squared deviation of 6.3 ± 2.0 mm, with average maximum positive and negative deviations of 12.7 ± 6.1 and -10.2 ± 5.7 mm, respectively, between the predicted and actual postoperative aesthetic result. Our developed 2-dimensional Gaussian model based on 3-dimensional optical surface images is a clinically promising tool to predict postsurgical aesthetic outcome in patients with pectus excavatum. Prediction of the aesthetic outcome after the Nuss procedure potentially improves information provision and expectation management among patients. Further research should assess whether increasing the sample size may reduce deviations and improve performance.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call