Premium
Contour interpolated radial basis functions with spline boundary correction for fast 3D reconstruction of the human articular cartilage from MR images
Author(s) -
Javaid Zarrar,
Boocock Mark G.,
McNair Peter J.,
Unsworth Charles P.
Publication year - 2016
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.4941076
Subject(s) - thin plate spline , spline interpolation , radial basis function , interpolation (computer graphics) , spline (mechanical) , visualization , artificial intelligence , computer science , computer vision , cartilage , mathematics , medicine , anatomy , image (mathematics) , physics , bilinear interpolation , artificial neural network , thermodynamics
Purpose: The aim of this work is to demonstrate a new image processing technique that can provide a “near real‐time” 3D reconstruction of the articular cartilage of the human knee from MR images which is user friendly. This would serve as a point‐of‐care 3D visualization tool which would benefit a consultant radiologist in the visualization of the human articular cartilage. Methods: The authors introduce a novel fusion of an adaptation of the contour method known as “contour interpolation (CI)” with radial basis functions (RBFs) which they describe as “CI‐RBFs.” The authors also present a spline boundary correction which further enhances volume estimation of the method. A subject cohort consisting of 17 right nonpathological knees (ten female and seven male) is assessed to validate the quality of the proposed method. The authors demonstrate how the CI‐RBF method dramatically reduces the number of data points required for fitting an implicit surface to the entire cartilage, thus, significantly improving the speed of reconstruction over the comparable RBF reconstruction method of Carr. The authors compare the CI‐RBF method volume estimation to a typical commercial package ( 3d doctor ), Carr's RBF method, and a benchmark manual method for the reconstruction of the femoral, tibial, and patellar cartilages. Results: The authors demonstrate how the CI‐RBF method significantly reduces the number of data points ( p ‐value < 0.0001) required for fitting an implicit surface to the cartilage, by 48%, 31%, and 44% for the patellar, tibial, and femoral cartilages, respectively. Thus, significantly improving the speed of reconstruction ( p ‐value < 0.0001) by 39%, 40%, and 44% for the patellar, tibial, and femoral cartilages over the comparable RBF model of Carr providing a near real‐time reconstruction of 6.49, 8.88, and 9.43 min for the patellar, tibial, and femoral cartilages, respectively. In addition, it is demonstrated how the CI‐RBF method matches the volume estimation of a typical commercial package ( 3d doctor ), Carr's RBF method, and a benchmark manual method for the reconstruction of the femoral, tibial, and patellar cartilages. Furthermore, the performance of the segmentation method used for the extraction of the femoral, tibial, and patellar cartilages is assessed with a Dice similarity coefficient, sensitivity, and specificity measure providing high agreement to manual segmentation. Conclusions: The CI‐RBF method provides a fast, accurate, and robust 3D model reconstruction that matches Carr's RBF method, 3d doctor , and a manual benchmark method in accuracy and significantly improves upon Carr's RBF method in data requirement and computational speed. In addition, the visualization tool has been designed to quickly segment MR images requiring only four mouse clicks per MR image slice.