Premium
Prediction of forearm bone shape based on partial least squares regression from partial shape
Author(s) -
Oura Keiichiro,
Otake Yoshito,
Shigi Atsuo,
Yokota Futoshi,
Murase Tsuyoshi,
Sato Yoshinobu
Publication year - 2017
Publication title -
the international journal of medical robotics and computer assisted surgery
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.556
H-Index - 53
eISSN - 1478-596X
pISSN - 1478-5951
DOI - 10.1002/rcs.1807
Subject(s) - partial least squares regression , forearm , regression , shape analysis (program analysis) , computer science , orthodontics , medicine , mathematics , anatomy , statistics , static analysis , programming language
Background Computer‐assisted corrective osteotomy using a mirror image of the normal contralateral shape as reference is increasingly used. Instead, we propose to use the shape predicted by statistical learning to deal with cases demonstrating bilateral abnormality, such as bilateral trauma, congenital disease, and metabolic disease. Methods Computed tomography (CT) scans of 100 normal forearms were used in this study. The whole bone shape was predicted from its partial shape based on statistical learning of the other 99 bones. Accuracy was evaluated by average symmetric surface distance (ASD), and translational and rotational errors. Results ASDs for predicted shapes were 0.71–1.03 mm. Mean absolute translational and rotational errors were 0.48–1.76 mm and 0.99–6.08°, respectively. Conclusion Normal bone shape was predicted with an acceptable accuracy from its partial shape using statistical learning. Predicted shape can be an alternative to a mirror image, which may enable reduced radiation exposure and examination costs.