Customized k-nearest neighbourhood analysis in the management of adolescent idiopathic scoliosis using 3D markerless asymmetry analysis. Issue 7 (19th May 2019)

• Record Type: Journal Article
• Authors: Ghaneei, Maliheh; Ekyalimpa, Ronald; Westover, Lindsey; Parent, Eric C.; Adeeb, Samer
• Is Part Of: Computer methods in biomechanics and biomedical engineering. Volume 22:Issue 7(2019)
• Page Start: 696
• Page End: 705
• Publication Date: 2019-05-19
• Subjects: Adolescent idiopathic scoliosis (AIS) -- surface topography -- 3D markerless asymmetry analysis -- classification -- k-Nearest neighbour; Biomechanics -- Data processing -- Periodicals; Biomedical engineering -- Periodicals; Biomechanics -- Periodicals; Biomedical Engineering -- methods -- Periodicals; Computing Methodologies -- Periodicals; 612.7
• DOI: 10.1080/10255842.2019.1584795
• Languages: English
• ISSNs: 1025-5842

Abstract

Abstract: Adolescent Idiopathic Scoliosis (AIS) is a 3D spinal deformity characterized by curvature and rotation of the spine. Markerless surface topography (ST) analysis has been proposed for diagnosing and monitoring AIS to reduce the X-ray radiation exposure to patients. This method captures scans of the cosmetic deformity of the torso using visible, radiation-free light. The asymmetry analysis of the torso, represented as a deviation contour map with deviation patches outlining the areas of cosmetic asymmetries, has previously been shown to predict the severity and progression of the condition in comparison with radiographs, by using classification trees. While the classification results were promising, it was reported that some mild curves were erroneously diagnosed. Furthermore, this approach is highly sensitive to threshold values selected in the decision trees. Therefore, this study aims to define a custom Neighbourhood Classifier algorithm for AIS classification to improve the accuracy, sensitivity, and specificity of predicting curve severity and curve progression in AIS. Curve severity was predicted with 80% accuracy (sensitivity = 81%; specificity = 79%) for thoracic-thoracolumbar curves and 72% (sensitivity = 93%; specificity = 53%) for lumbar curves. This represents an improvement over the previous method with curve severity accuracies of 77% and 63% for thoracic-thoracolumbar and lumbar curves, respectively. Additionally, curve progression was predicted with 93% accuracy (sensitivity = 83%; specificity = 95%) representing a substantial improvement over the previous method with an accuracy of 59%. The current method has shown the potential to further reduce radiation exposure for AIS patients by avoiding X-rays for mild and non-progressive curves identified using ST analysis.