Semi-automated Phalanx Bone Segmentation Using the Expectation Maximization Algorithm

Abstract

Medical imaging technologies have allowed for in vivo exploration and evaluation of the human musculoskeletal system. Three-dimensional bone models generated using image segmentation techniques provide a means to optimize individualized orthopaedic surgical procedures using engineering analyses. However, many of the current segmentation techniques are not clinically practical due to the required time and human intervention. As a proof of concept, we demonstrate the use of an expectation maximization (EM) algorithm to segment the hand phalanx bones, and hypothesize that this semi-automated technique will improve on the efficiency while providing similar definitions as compared to a manual rater. Our results show a relative overlap of the proximal, middle, and distal phalanx bones of 0.83, 0.79, and 0.72 for the EM technique when compared to validated manual segmentations. The EM segmentations were also compared to 3D surface scans of the cadaveric specimens, which resulted in distance maps showing an average distance for the proximal, middle, and distal phalanx bones of 0.45, 0.46, and 0.51 mm, respectively. The EM segmentation improved on the segmentation speed of the manual techniques by a factor of eight. Overall, the manual segmentations had greater relative overlap metric values, which suggests that the manual segmentations are a better fit to the actual surface of the bone. As shown by the comparison to the bone surface scans, the EM technique provides a similar representation of the anatomic structure and offers an increase in efficiency that could help to reduce the time needed for defining anatomical structures from CT scans.

A Study on the Feasibility of Active Contours on Automatic CT Bone Segmentation

“…8,9 Most of the methods have shown success in certain anatomical structures where they have been optimized, such as carpal bones, 9 acetabulum and femoral head, 10 spinal canal, 11 pelvis, 7,12 vertebrae, 13 ribs, 14 and phalanx bones. 15 In, 8 two methods were validated on knee bone segmentation, which is also the subject of this study. The first one was a four-step process 16 that contains region-growing using local adaptive thresholds, discontinued-boundary closing, anatomically oriented boundary adjustment, and manual correction.…”

EM Segmentation of the Distal Femur and Proximal Tibia: A High-Throughput Approach to Anatomic Surface Generation

“…Nevertheless, the metrics revealed overlap values better than those observed in the EM segmentation evaluation of the phalanx bones. 20 One EM segmentation of the tibia, out of the 144 regions segmented, was an outlier in our dataset; this resulted from a suboptimal registration for that specific image. In this case, manual editing of the EM label map could be utilized to provide an accurate segmentation.…”

“…20 It involved the selection of eight anatomical landmarks per finger to initialize a Thirion Demon's registration between an atlas and a subject image. The deformation field from the registration was then used to warp the probability maps from the atlas onto the subject's individual phalanx bones.…”

Growing multiblock structures: a semi-automated approach to block placement for multiblock hexahedral meshing

“…After acquiring a three-dimensional data-set, image processing and segmentation are required to recognise regions of interest from the surrounding structures. Various efforts have concentrated on the automated identification of orthopaedic structures from the surrounding soft tissues (Ehrhardt et al 2001;Sebastian et al 2003;Gelaude et al 2006;Saparin et al 2006;Wang et al 2006;Gassman et al 2008;Ramme et al 2009). Generation of surfaces from the resulting segmentation allows for visualisation, qualitative and quantitative evaluation of these structures.…”